WO2025250651A1

WO2025250651A1 - Utilizing infrared data for control of fabrication processes

Info

Publication number: WO2025250651A1
Application number: PCT/US2025/031213
Authority: WO
Inventors: Kapil Sawlani; Kaihan Abidi Ashtiani; Paul M. Franzen; Rafsan Rabbi; Patging John Elsworth MARTIN; Bart J. Van Schravendijk; Ramesh Chandrasekharan
Original assignee: Lam Research Corp
Current assignee: Lam Research Corp
Priority date: 2024-05-30
Filing date: 2025-05-28
Publication date: 2025-12-04
Anticipated expiration: 2026-11-30

Abstract

Techniques for utilizing infrared data in conjunction with semiconductor fabrication processes are provided. In some embodiments, the techniques may involve receiving data from one or more infrared sensors associated with a process station. The techniques may further involve determining infrared temperature data and/or emissivity data. The techniques may further involve determining at least one of: 1) temperature information associated with one or more components of the process station; or 2) thickness information indicating a thickness of deposited materials on components of the process station or on a surface of a substrate undergoing processing using the infrared temperature data and/or the emissivity data. The techniques may further involve determining whether the temperature information and/or the thickness information is out of a target specification. The techniques may further involve taking at least one corrective action.

Description

UTILIZING INFRARED DATA FOR CONTROL OF FABRICATION PROCESSES

INCORPORATION BY REFERENCE

[0000] A PCT Request Form is filed concurrently with this specification as part of the present application. Each application that the present application claim benefit of or priority to as identified in the concurrently filed PCT Request Form is incorporated by reference herein in its entirety and for all purposes.

BACKGROUND

[0001] It may be desirable to monitor aspects of a fabrication process during performance of the fabrication process, after performance of the fabrication process, etc. For example, it may be useful to monitor temperature of various components within a process station. However, it can be difficult to monitor aspects of a fabrication process, particularly in real-time or near realtime.

[0002] The background description provided herein is for the purposes of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in this background section, as well as aspects of the description that may not otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present disclosure.

SUMMARY

[0003] Techniques disclosed herein relate to utilizing infrared data for control of fabrication processes. The techniques may be practiced with a processor-implemented method, a system comprising one or more processors and one or more processor-readable media, and/or one or more non-transitory processor-readable media.

[0004] In some embodiments, the techniques may involve receiving data from one or more infrared sensors associated with a process station of a semiconductor fabrication process chamber. The techniques may further involve determining infrared temperature data and/or emissivity data based on the received data. The techniques may further involve determining at least one of: 1) temperature information associated with one or more components of the process station; or 2) thickness information indicating a thickness of deposited materials on components of the process station or on a surface of a substrate undergoing processing in the process station using the infrared temperature data and/or the emissivity data. The techniques may further involve determining whether the temperature information and/or the thickness information is out of a target specification. The techniques may further involve in response to determining that the temperature information and/or the thickness information is out of the target specification, taking at least one corrective action.

[0005] In some examples, determining the temperature information associated with the one or more components of the process station comprises predicting an actual temperature of the one or more components based on the infrared temperature data and the emissivity data. In some examples, determining the actual temperature comprises providing the infrared temperature data and the emissivity data to a trained machine learning model configured to predict an actual temperature associated with a given infrared temperature and emissivity. In some examples, the trained machine learning model is trained using data from known material emissivities.

[0006] In some examples, the temperature information associated with the one or more components of the process station comprises temperature information associated with a pedestal. In some examples, the temperature information comprises two-dimensional information representing temperature variations across the pedestal. In some examples, detecting a heater dead zone region of the pedestal based on the two-dimensional information, and wherein the at least one corrective action comprises causing an alert to be generated indicative of the heater dead zone region.

[0007] In some examples, determining the thickness information comprises determining an emissivity of a surface of the components of the process station or the surface of the substrate undergoing processing based on ground truth temperature information and the infrared temperature data. In some examples, the thickness information is determined based on the emissivity of the surface and known material properties of the surface of the components or the surface of the substrate undergoing processing.

[0008] In some examples, determining whether the thickness information is out of the target specification comprises determining whether a thickness of deposited layers on the surface of the substrate is out of the target specification. In some examples, identifying an error in a deposition process occurring in the process station based on the thickness information being out of the target specification. In some examples, identifying the error in the deposition process comprises identifying at least one of: a reduction in gas within an ampoule or mass flow controller, or a failure in a valve that controls gas flow to the process station.

[0009] In some examples, determining whether the temperature information and/or the thickness information is out of a target specification occurs during performance of a fabrication process.

[0010] In some examples, determining whether the thickness information is out of the target specification comprises determining whether deposited material on components of the process station exceeds a threshold value. In some examples, the at least one corrective action comprises initiating a cleaning cycle based on the determination that the deposited material exceeds the threshold value.

[0011] In some examples, the emissivity data comprises global emissivity data applicable to an entire surface of a material of a particular type.

[0012] In some examples, the emissivity data comprises local emissivity data, and where the method further comprises determining global emissivity data that varies across the surface of the material based on the local emissivity data.

BRIEF DESCRIPTION OF THE DRAWINGS

[0013] FIG. 1 is a schematic diagram of an example multi-station process chamber in accordance with some embodiments.

[0014] FIG. 2 is a flowchart of an example process for taking an action based on temperature information and/or deposition thickness information obtained using infrared data in accordance with some embodiments.

[0015] FIG. 3 is a flowchart of an example process for determining temperature information using infrared data in accordance with some embodiments.

[0016] FIG. 4 is a flowchart of an example process for determining deposition thickness information using infrared data in accordance with some embodiments.

[0017] FIG. 5 is a graph that illustrates an example relationship between infrared temperature, actual temperature, and emissivity in accordance with some embodiments.

[0018] FIG. 6 presents an example computer system that may be employed to implement certain embodiments described herein.

DETAILED DESCRIPTION

[0019] In the following description, numerous specific details are set forth to provide a thorough understanding of the presented embodiments. The disclosed embodiments may be practiced without some or all of these specific details. In other instances, well-known process operations have not been described in detail to not unnecessarily obscure the disclosed embodiments. While the disclosed embodiments will be described in conjunction with the specific embodiments, it will be understood that it is not intended to limit the disclosed embodiments. [0020] It may be desirable to monitor aspects of a fabrication process during performance of the fabrication process, after performance of the fabrication process, etc. For example, it may be useful to monitor temperature of various components within a process station. As another example, it may be desirable to monitor deposition thickness, either on a surface of a wafer undergoing processing and/or on a surface of a process station. However, it can be difficult to monitor aspects of a fabrication process, particularly in real-time or near real-time. For example, because fabrication processes may occur at relatively high temperatures (e.g., above 400 degrees Celsius, above 500 degrees Celsius, above 600 degrees Celsius, etc.) and/or in the presence of gas chemistries that can cause monitoring sensors to break, it can be difficult to monitor aspects of a process station or a fabrication process in situ (e.g., while the fabrication process is occurring). Moreover, it may only be possible to have a limited number (e.g., one or two) of some types of monitoring sensors within the process station. For example, to monitor pedestal temperature, temperature data may be collected from a limited number (e.g., one or two) thermocouples disposed in the pedestal. However, due to the limited number of monitoring sensors, the obtained data may not cover an entire spatial region. For example, pedestal temperatures monitored using one or two thermocouples may not provide temperature data suitable to monitor the temperature of the entire pedestal, which may leave errors or anomalous conditions such as pedestal heater dead-zones undetected.

[0021] Disclosed herein are techniques for monitoring aspects of a fabrication process or a process station of a process chamber using infrared data. For example, in some embodiments, temperature information associated with a wafer undergoing processing and/or temperature information associated with one or more components of the process station (e.g., a pedestal of the process station on which a wafer resides while undergoing processing) may be determined using the infrared data. As another example, in some embodiments, film thickness on a surface of a wafer undergoing processing (e.g., during a deposition process, an etch process, etc.) and/or film thickness on one or more surfaces of the process station (e.g., station walls, a surface of a pedestal, etc.) may be determined. It should be noted that, in some embodiments, aspects of the fabrication process and/or the process station (which may include temperature information and/or film thickness information) may be determined in situ, e.g., during performance of the fabrication process. In situ monitoring may allow in situ process control to be performed, e.g., during the fabrication process. For example, in some embodiments, responsive to determining that a temperature of a component (e.g., a pedestal) and/or film thickness of a wafer undergoing processing deviates from an expected threshold or range, one or more corrective actions can be taken, e.g., by modifying process parameters and/or modifying control of various station components (e.g., an RF power source, gas flow rates, pedestal heater elements, etc.) to modify the temperature and/or the film thickness. In some embodiments, monitoring of aspects of the fabrication process and/or the process station may allow an alert of an impending or imminent failure to be flagged, e.g., to a process engineer or technician. For example, monitoring film thickness on a wafer may allow an anomalous condition, such as anomalous gas flow in an ampoule or mass flow controller or failure of a valve that delivers gas to the station, to be detected. As another example, monitoring temperature of a pedestal may allow a dead-zone of the pedestal (e.g., a relatively cooler region of the pedestal) to be detected as the dead-zone is developing. In other words, the techniques disclosed herein may allow for predictive maintenance that allows for replacement of parts prior to failure. Both in situ monitoring and control and predictive maintenance, as enabled using the techniques disclosed herein, may allow for improved functioning of semiconductor processing equipment. Moreover, the techniques disclosed herein may allow substrates to be processed with higher throughput such that a higher percentage of substrates meet specifications, and with less tool downtime.

[0022] In some embodiments, infrared data may be obtained using one or more infrared sensors or cameras. An infrared sensor or camera may be disposed in a viewport of a process station, which may be on a side wall of the station, a top wall of the station, or any other suitable location. A process station may have multiple (e.g., two, three, five, ten, etc.) infrared sensors or cameras. In some embodiments, the process station may be part of a process chamber having multiple (e.g., two, three, four, eight, ten, etc.) process stations, although it should be noted the techniques described herein may be practiced on a process chamber having multiple stations or a single station. The infrared data may be captured as raw voltage signals and transformed into a two-dimensional representation of infrared temperature. As used herein, an “actual temperature” refers to a ground truth temperature measurement, which may be obtained from, e.g., a thermocouple, a resistance temperature detector (RTD), or another type of temperature sensor. As used herein, “infrared temperature” refers to an estimated temperature based on the infrared data that is based on the infrared energy indicated in the infrared data, which may not necessarily account for the emissivity of surfaces represented in the infrared data. An infrared temperature may be determined based on calibration with an actual temperature. Because the infrared data may be represented as pixels of an image, each pixel indicating an infrared temperature of a region corresponding to the pixel, infrared temperatures may be determined for thousands or tens of thousands of points. In comparison, temperature information using physical thermocouples disposed in the station yield temperature data for a very limited region of a station (e.g., the region immediately around the thermocouple). Accordingly, the infrared data obtained and used herein may allow for substantially increased spatial resolution with which temperature information and/or film thickness information is determined, which may in turn enable high spatial resolution in detecting anomalies, in a fabrication process and/or a component of a process station.

[0023] In some implementations, the techniques disclosed herein may utilize a relationship between infrared temperature associated with a surface, emissivity of the surface, and an actual temperature of the surface. In some embodiments, the relationship between these three parameters may be learned, e.g., by a machine learning model, using experimental data. In some embodiments, temperature information associated with a component of a process station and/or a surface of a wafer may be determined by determining an infrared temperature based on infrared data, and estimating an emissivity of the surface imaged. The emissivity may be determined based on known material properties and/or based on experimental data. Using the infrared temperature and the emissivity, the actual temperature of the surface (e.g., a surface of a pedestal, a surface of a wafer, etc.) may be determined using the relationship between the infrared temperature, emissivity, and actual temperature.

[0024] In some implementations, film thickness information may be determined using a relationship between infrared temperature associated with a surface, emissivity of the surface, and an actual temperature of the surface. Similar to what is described above, in some embodiments, the relationship between these three parameters may be learned, e.g., by a machine learning model, using experimental data. In some embodiments, the actual temperature may be measured using one or more thermocouples or other physical temperature measuring sensors disposed in the station. The difference between the infrared temperature and the actual temperature (or “ground truth” temperature) may be due to the emissivity of the surface. Over time (e.g., during the course of a fabrication process, over time spanning use of the process station, etc.), the difference between the infrared temperature and the actual temperature may increase due to increasing film thickness which in turn changes the emissivity of the surface. Accordingly, the emissivity may be determined based at least in part on the difference between the infrared temperature (and/or changes in the infrared temperature over time) and the ground truth temperature, and, in some embodiments, based on known material properties of the surface. The film thickness may then be estimated based on the emissivity. The film thickness may be estimated using a trained machine learning model, which may have been trained using experimental data. It should be understood that, in some embodiments, changes in film thickness may be estimated based on infrared data without determining or estimating emissivity. By way of example, a particular process may involve depositing a predetermined film thickness (e.g., 60 Angstroms). Deposition of the target film thickness may be associated with a repeatable infrared signature. Continuing with this example, a change in the infrared signature may be detected, which may signify that the deposited film is more than or less than (i.e., deviates from) the desired film thickness associated with the repeatable infrared signature. This change in deposited film thickness may be due to system drift, change in precursor flux, an incidental process change, or any other suitable reason. Note that, as described below, the estimated film thickness (and/or a determination that film thickness deviates from a desired film thickness) may be used to initiate a cleaning cycle (e.g., responsive to the film thickness on a station surface exceeds a predetermined threshold), determining when a cleaning cycle is finished (e.g., responsive to the film thickness dropping below a predetermined threshold), determining a fabrication process has an anomaly (e.g., responsive to determining film thickness on a wafer undergoing processing is outside of a target range), triggering a flag, inhibiting performance of the process, or the like.

[0025] As described above, one or more process stations may be included in a multi-station processing tool. FIG. 1 shows a schematic view of an embodiment of a system that includes a multi-station processing tool. In some implementations, a multi-station processing tool may include an inbound load lock and an outbound load lock, either or both of which may include a remote plasma source. A robot at atmospheric pressure is configured to move wafers from a cassette loaded through a pod into an inbound load lock via an atmospheric port. A wafer is placed by the robot on a substrate holder in the inbound load lock, the atmospheric port is closed, and the load lock is pumped down. Where the inbound load lock includes a remote plasma source, the wafer may be exposed to a remote plasma treatment in the load lock prior to being introduced into a process chamber 100. Further, the wafer also may be heated in the inbound load lock as well, for example, to remove moisture and adsorbed gases. Next, a chamber transport port to process chamber 100 is opened, and another robot (not shown) places the wafer into the reactor on a substrate holder of a first station shown in the reactor for processing. While some implementations include load locks, it will be appreciated that, in some embodiments, direct entry of a wafer into a process station may be provided.

[0026] The depicted process chamber 100 includes four process stations, 102a, 102b, 102c, and 102d in the embodiment shown in FIG. 1. Each station may have a heated substrate holder, and gas line inlets. It will be appreciated that in some embodiments, each process station may have different or multiple purposes. For example, in some embodiments, a process station may be switchable between an ALD and plasma-enhanced ALD process mode. Additionally or alternatively, in some embodiments, process chamber 100 may include one or more matched pairs of ALD and plasma-enhanced ALD process stations. While the depicted process chamber 100 includes four stations, it will be understood that a process chamber according to the present disclosure may have any suitable number of stations. For example, in some embodiments, a process chamber may have five or more stations, while in other embodiments a process chamber may have three or fewer stations.

[0027] As illustrated in FIG. 1, one or more IR cameras may be disposed in or on a portion of a multi-station tool. For example, an IR camera may be disposed in or on a viewport of a station such that the IR camera is configured to capture IR data associated with the interior of the station. In the example shown in FIG. 1, each station 102a- 102d is associated with an IR camera, e.g., IR cameras 104a, 104b, 104c, and 104d, respectively. Note that a viewport for an IR camera may be one that allows the IR camera to capture a perspective or side view of the station, a top-down view of the station, or any combination thereof. In some implementations, a station may be associated with multiple IR cameras, e.g., that each capture a different view.

[0028] It should be understood that various references to RF power settings of the present disclosure are generally intended, unless otherwise indicated, to refer to the RF power setting per wafer. In embodiments involving multiple process stations in a multi-station processing tool, one or more RF power sources may be provided that serve multiple process stations (e.g., simultaneously and/or sequentially). In embodiments in which a single RF power source serves multiple process stations, the per-wafer power setting of the RF power source may be multiplied by the number of process stations being simultaneously provided with plasma at a desired power level. In other words, when the present disclosure describes an RF power setting of 300 watts, it should be understood that the RF power setting reflects a per-wafer value of 300 watts and that, in multi-station processing tools, the actual RF power setting of the RF power source may be the per-wafer power setting multiplied by the number of stations.

[0029] A multi-station processing tool may include a wafer handling system for transferring wafers within process chamber 100. In some embodiments, the wafer handling system may transfer wafers between various process stations and/or between a process station and a load lock. It will be appreciated that any suitable wafer handling system may be employed. Non-limiting examples include wafer carousels and wafer handling robots. FIG. 1 also depicts an embodiment of a system controller 108 employed to control process conditions and hardware states of the multi-station processing tool. System controller 108 may include one or more memory device, one or more mass storage device, and one or more processor. A processor may include a CPU or computer, analog, and/or digital input/output connections, stepper motor controller boards, etc.

[0030] In some embodiments, system controller 108 may be remote from the multi-station processing tool. In some embodiments, an edge controller 106 may be proximate to the multistation processing tool (e.g., in the same room or facility), and may operatively couple system controller 108 to the multi-station processing tool.

[0031] In some embodiments, system controller 108 controls all of the activities of the multistation processing too. System controller 108 executes system control software stored in a mass storage device, loaded into a memory device, and executed on or by a processor. Alternatively, the control logic may be hard coded in the system controller 108. Applications Specific Integrated Circuits, Programmable Logic Devices (e.g., field-programmable gate arrays, or FPGAs) and the like may be used for these purposes. In the following discussion, wherever “software” or “code” is used, functionally comparable hard coded logic may be used in its place. The system control software may include instructions for controlling the timing, mixture of gases, gas flow rates, chamber and/or station pressure, chamber and/or station temperature, wafer temperature, target power levels, RF power levels, substrate holder, chuck and/or susceptor position, and other parameters of a particular process performed by the multistation processing tool. The System control software may be configured in any suitable way. For example, various process tool component subroutines or control objects may be written to control operation of the process tool components used to carry out various process tool processes. The system control software may be coded in any suitable computer readable programming language.

[0032] In some embodiments, the system control software may include input/output control (IOC) sequencing instructions for controlling the various parameters described above. Other computer software and/or programs stored on a mass storage device and/or memory device associated with system controller 108 may be employed in some embodiments. Examples of programs or sections of programs for this purpose include a substrate positioning program, a process gas control program, a pressure control program, a heater control program, and a plasma control program.

[0033] A substrate positioning program may include program code for process tool components that are used to load the substrate onto a substrate holder and to control the spacing between the substrate and other parts of the multi-station processing tool.

[0034] A process gas control program may include code for controlling gas composition (e.g., iodine-containing silicon precursor gases, and nitrogen-containing gases, carrier gases and purge gases as described herein) and flow rates and optionally for flowing gas into one or more process stations prior to deposition in order to stabilize the pressure in the process station. A pressure control program may include code for controlling the pressure in the process station by regulating, for example, a throttle valve in the exhaust system of the process station, a gas flow into the process station, etc.

[0035] A heater control program may include code for controlling the current to a heating unit that is used to heat the substrate. Alternatively, the heater control program may control delivery of a heat transfer gas (such as helium) to the substrate.

[0036] A plasma control program may include code for setting RF power levels applied to the process electrodes in one or more process stations in accordance with the embodiments herein.

[0037] A pressure control program may include code for maintaining the pressure in the reaction chamber in accordance with the embodiments herein.

[0038] In some embodiments, there may be a user interface associated with system controller 108. The user interface may include a display screen, graphical software displays of the apparatus and/or process conditions, and user input devices such as pointing devices, keyboards, touch screens, microphones, etc.

[0039] In some embodiments, parameters adjusted by system controller 108 may relate to process conditions. Non-limiting examples include process gas composition and flow rates, temperature, pressure, plasma conditions (such as RF bias power levels), etc. These parameters may be provided to the user in the form of a recipe, which may be entered utilizing the user interface.

[0040] Signals for monitoring the process may be provided by analog and/or digital input connections of system controller 108 from various process tool sensors. The signals for controlling the process may be output on the analog and digital output connections of the multistation processing tool. Non-limiting examples of process tool sensors that may be monitored include mass flow controllers, pressure sensors (such as manometers), thermocouples, etc. Appropriately programmed feedback and control algorithms may be used with data from these sensors to maintain process conditions.

[0041] System controller 108 may provide program instructions for implementing the abovedescribed deposition processes. The program instructions may control a variety of process parameters, such as DC power level, RF bias power level, pressure, temperature, etc. The instructions may control the parameters to operate in-situ deposition of film stacks according to various embodiments described herein.

[0042] The edge controller 106 and/or the system controller 108 will typically include one or more memory devices and one or more processors configured to execute the instructions so that the apparatus will perform a method in accordance with disclosed embodiments. Machine- readable media containing instructions for controlling process operations in accordance with disclosed embodiments may be coupled to the edge controller 106 and/or the system controller.

[0043] In some implementations, the edge controller 106 and/or the system controller 108 are part of a system, which may be part of the above-described examples. Such systems can include semiconductor processing equipment, including a processing tool or tools, chamber or chambers, a platform or platforms for processing, and/or specific processing components (a wafer holder, a gas flow system, etc.). These systems may be integrated with electronics for controlling their operation before, during, and after processing of a semiconductor wafer or substrate. The electronics may be referred to as the “controller,” which may control various components or subparts of the system or systems. The edge controller 106 and/or the system controller 108, depending on the processing conditions and/or the type of system, may be programmed to control any of the processes disclosed herein, including the delivery of processing gases, temperature settings (e.g., heating and/or cooling), pressure settings, vacuum settings, power settings, radio frequency (RF) generator settings, RF matching circuit settings, frequency settings, flow rate settings, fluid delivery settings, positional and operation settings, wafer transfers into and out of a tool and other transfer tools and/or load locks connected to or interfaced with a specific system.

[0044] Broadly speaking, the edge controller 106 and/or the system controller 108 may be defined as electronics having various integrated circuits, logic, memory, and/or software that receive instructions, issue instructions, control operation, enable cleaning operations, enable endpoint measurements, and the like. The integrated circuits may include chips in the form of firmware that store program instructions, digital signal processors (DSPs), chips defined as application specific integrated circuits (ASICs), and/or one or more microprocessors, or microcontrollers that execute program instructions (e.g., software). Program instructions may be instructions communicated to the edge controller 106 and/or the system controller 108 in the form of various individual settings (or program files), defining operational parameters for carrying out a particular process on or for a semiconductor wafer or to a system. The operational parameters may, in some embodiments, be part of a recipe defined by process engineers to accomplish one or more processing steps during the fabrication of one or more layers, materials, metals, oxides, silicon, silicon dioxide, surfaces, circuits, and/or dies of a wafer.

[0045] The edge controller 106 and/or the system controller 108, in some implementations, may be a part of or coupled to a computer that is integrated with, coupled to the system, otherwise networked to the system, or a combination thereof. For example, the system controller 108 may be in the “cloud” or all or a part of a fab host computer system, which can allow for remote access of the wafer processing. The computer may enable remote access to the system to monitor current progress of fabrication operations, examine a history of past fabrication operations, examine trends or performance metrics from a plurality of fabrication operations, to change parameters of current processing, to set processing steps to follow a current processing, or to start a new process. In some examples, a remote computer (e.g. a server) can provide process recipes to a system over a network, which may include a local network or the Internet. The remote computer may include a user interface that enables entry or programming of parameters and/or settings, which are then communicated to the system from the remote computer. In some examples, the edge controller 106 and/or the system controller 108 receives instructions in the form of data, which specify parameters for each of the processing steps to be performed during one or more operations. It should be understood that the parameters may be specific to the type of process to be performed and the type of tool that the edge controller 106 and/or the system controller 108 is configured to interface with or control. Thus as described above, the edge controller 106 and/or the system controller 108 may be distributed, such as by including one or more discrete controllers that are networked together and working towards a common purpose, such as the processes and controls described herein. An example of a distributed controller for such purposes would be one or more integrated circuits on a chamber in communication with one or more integrated circuits located remotely (such as at the platform level or as part of a remote computer) that combine to control a process on the chamber.

[0046] Without limitation, example systems may include a plasma etch chamber or module, a deposition chamber or module, a spin-rinse chamber or module, a metal plating chamber or module, a clean chamber or module, a bevel edge etch chamber or module, a physical vapor deposition (PVD) chamber or module, a chemical vapor deposition (CVD) chamber or module, an PEALD chamber or module, an atomic layer etch (ALE) chamber or module, an ion implantation chamber or module, a track chamber or module, and any other semiconductor processing systems that may be associated or used in the fabrication and/or manufacturing of semiconductor wafers.

[0047] As noted above, depending on the process step or steps to be performed by the tool, the edge controller 106 and/or the system controller 108 might communicate with one or more of other tool circuits or modules, other tool components, cluster tools, other tool interfaces, adjacent tools, neighboring tools, tools located throughout a factory, a main computer, another controller, or tools used in material transport that bring containers of wafers to and from tool locations and/or load ports in a semiconductor manufacturing factory.

[0048] It should be noted that FIG. 1 depicts merely one example of a multi-station process chamber that may be used in some embodiments of the techniques, systems, and methods described herein. In some implementations, a multi-station process chamber may include multiple chambers or reactors (e.g., two, four, six, eight, etc.), where the multiple chambers or reactors are modular in nature and are clustered. For example, the multiple chambers or reactors may be clustered around one or more shared components, such as one or more wafer handling systems, a system controller, etc. The multiple chambers or reactors may be under a common vacuum environment. In some embodiments, the vacuum environment, and the multiple modules it encloses, as well as the shared wafer handling resources, is collectively referred to as “a cluster tool.”

[0049] The techniques disclosed herein may utilize one or more IR cameras or sensors to obtain infrared data. The infrared data may be used to determine infrared temperature data, from which an actual temperature (e.g., of a component of the station, such as a pedestal) may be determined. Additionally or alternatively, the infrared data may be used to determine emissivity data from which thickness information indicating thickness of deposited materials on components of the process station or on a surface of a wafer undergoing processing may be determined. The temperature information (e.g., the actual temperature of a component of the station) and/or the thickness information may then be considered to determine if either the temperature information and/or the thickness information or out of specification. For example, temperature information being out of specification may involve at least a portion of a pedestal on which a substrate is to reside during processing is below a predetermined threshold. As another example, thickness information being out of specification may involve film deposition on a component of the station being greater than a predetermined threshold (e.g., indicating that a cleaning cycle should occur), and/or that film deposition on a substrate undergoing processing is outside of a predetermined thickness range (e.g., indicating an error or anomaly in a deposition process that is occurring). Responsive to identifying that either temperature information and/or thickness information is out of specification, the techniques disclosed herein may cause at least one action to occur. For example, the at least one action may include causing an alert to be presented, e.g., to a process engineer. As another example, the at least one action may include responsive changes to a fabrication process currently occurring, such as modifying gas flow rates, temperatures, etc. to counteract film deposition on a substrate that is outside of the specification. As yet another example, the at least one action may include identifying an error condition, such as a reduction in gas within an ampoule or mass flow controller, a failure in a valve that controls gas flow to the process station, or the like that causes a film deposition on a substrate to be below a target specification. As still another example, the at least one action may include causing a cleaning cycle to be initiated, e.g., responsive to a determination that deposition on components of the station (e.g., a surface or wall of the station) exceeds a predetermined threshold.

[0050] Note that IR cameras may have any suitable resolution. For example, an IR camera may be standard high definition (e.g., having a resolution of 1280x720 pixels), full high definition (e.g., having a resolution of 1920x1080 pixels), a 4K camera (e.g., having a resolution of approximately 4,000 horizontal pixels, such as 3840x2160 pixels or 4096x2160 pixels), or any other resolution. Different communication protocols may be used to communicate IR camera data, such as Universal Serial Bus (USB), Gigabit Ethernet (GigE), Gigabit Multimedia Serial Link (GMSL), or the like.

[0051] FIG. 2 is a flowchart of an example process 200 for determining temperature and/or thickness information using IR data in accordance with some embodiments. In some implementations, blocks of process 200 may be executed by one or more processors of an edge controller and/or a system controller. Examples of an edge controller and/or a system controller are shown in and described above in connection with FIG. 1. In some embodiments, blocks of process 200 may be executed in an order other than what is shown in FIG. 2. In some embodiments, two or more blocks of process 200 may be executed substantially in parallel. In some embodiments, one or more blocks of process 200 may be omitted.

[0052] Process 200 can begin at 202 by receiving data from one or more infrared sensors (e.g., cameras) associated with one or more process stations. As shown in and described above in connection with FIG. 1 , an infrared sensor or camera may be disposed in a viewport of a station to obtain a view of at least a portion of the station. The viewport may be in a side wall of the station, a top portion of the station, or any other suitable location. One or more frames of infrared data may be obtained. In instances in which multiple frames are obtained, the frame rate may be, e.g., 1 frame per second, 10 frames per second, 20 frames per second, 30 frames per second, etc. Note that, in some embodiments, the data received from the one or more infrared sensors may be raw voltage data. The raw voltage data may be transmitted to an edge controller, e.g., as shown in and described above in connection with FIG. 1. [0053] At 204, process 200 can determine infrared temperature data and/or emissivity data based on the received data. For example, in some embodiments, process 200 may determine infrared temperature data from the raw voltage data obtained by the one or more infrared sensors by utilizing a calibration mapping to translate the raw voltage data to infrared temperature data. The infrared temperature data may be represented as, e.g., image data, where each pixel has a value that indicates an infrared temperature. The calibration may have been performed using a bare Silicon (Si) wafer that allows infrared energy to pass through. Note that, as used herein, “infrared temperature” may refer to a temperature inferred based on the data from the one or more infrared sensors, which may be dependent on the darkness (e.g., emissivity) of surfaces for which the infrared data is being obtained. In some implementations, process 200 may additionally or alternatively determine emissivity data for surfaces associated with the obtained infrared data. The emissivity data may be obtained by comparing a known temperature (e.g., from one or more thermocouples within the station) to the infrared temperature. For example, in an instance in which the known temperature for a particular component (e.g., a pedestal) is 100 degrees Celsius and the infrared temperature for the particular component based on the data for pixels corresponding to the component is 70 degrees Celsius, the emissivity data may represent an emissivity for the component required to cause the infrared temperature to be 30 degrees less than the known temperature.

[0054] Note that, to determine the infrared temperature and/or the emissivity data, process 200 may perform any suitable image processing techniques. For example, process 200 may perform edge detection, object detection, etc. to identify boundaries of components within an image associated with the received data. Based on the boundaries of the components, infrared temperature data and/or emissivity data may be obtained on a per-component basis. Note that, in some embodiments, edge detection may be performed on infrared data alone. Additionally or alternatively, in some embodiments, edge detection may be performed using infrared data and camera data from the visible spectrum. For example, infrared data and camera data from the visible spectrum may be combined to perform edge detection. In some embodiments, deep learning and/or other machine learning algorithms may be used to classify and/or segment features of importance.

[0055] At 206, process 200 can determine at least one of: 1) temperature information associated with one or more components of the process station; or 2) thickness information indicating a thickness of deposited materials on components of the process station or on a surface of a wafer undergoing processing in the process station. In some embodiments, in instances in which temperature information is determined, the temperature may be an actual temperature of one or more components. The one or more components may include, e.g., a pedestal in the process station, one or more walls of the station, or the like. In some embodiments, the temperature information may include actual temperatures at multiple points or areas of a component. For example, temperatures may be determined for multiple points or regions of a pedestal. In some embodiments, by determining temperatures for multiple points or regions of the pedestal, a dead zone of the pedestal that is cooler than expected may be identified, thereby identifying an error condition associated with a pedestal heater. In some embodiments, the temperature information may comprise two-dimensional information representing temperature variations across a component, such as temperature variations across the pedestal. In some embodiments, the temperature information may be determined based on the infrared temperature and/or the emissivity data as determined at block 204. For example, in some embodiments, determining the temperature information may involve providing the infrared temperature and/or the emissivity data to a trained machine learning model configured to output an actual temperature based on the infrared temperature and/or the emissivity data. As another example, in some embodiments, determining the temperature information may involve using a lookup table that associates infrared temperature, emissivity, and actual temperature, as described below in connection with FIG. 5. An example technique for determining temperatures associated with one or more components of a process station is shown in and described below in connection with FIG. 3.

[0056] In instances in which thickness information is determined, the thickness information may indicate a thickness of deposited film on a component of the process station, such as a wall surface, a pedestal surface, or any other surface. Additionally or alternatively, the thickness information may indicate a thickness of deposited film on a wafer undergoing a fabrication process in the station, such as a deposition process. In some embodiments the thickness information may be determined based on the infrared temperature and a known, or ground truth, temperature. The known or ground truth temperature may be obtained from one or more thermocouples disposed in the process station. In some embodiments, the thickness information may be determined by determining emissivity information for the wafer and/or the component of the process station for which thickness information is to be determined. The emissivity information may be determined based on the infrared temperature determined at block 204 and the known temperature, and/or based on a difference in the infrared temperature over time. For example, the emissivity information may be determined by providing the infrared temperature and the known temperature to a trained machine learning model configured to output the emissivity information. As another example, the emissivity information may be obtained from a lookup table that associates emissivity information, infrared temperature, and actual temperature.

[0057] It should be noted that, in some embodiments, changes in thickness or changes in emissivity may be used. For example, rather than determining an emissivity value or a thickness value, changes in emissivity or thickness over time may be used to, e.g., detect system drift. By way of example, different film thicknesses result in different emissivity values, and accordingly, changes in emissivity values may be correlated with changes in film thickness. Without directly calculating a film thickness, changes in emissivity values may be used to infer changes in film thickness values.

[0058] At 208, process 200 can determine whether the temperature information and/or the thickness information is out of specification. For example, in an instance in which the temperature information comprises actual temperatures of one or more components of the process station, process 200 can determine whether the temperature is outside of an acceptable temperature range for the one or more components. As a more particular example, in some embodiments, process 200 can determine whether one or more regions of a pedestal have a temperature that is below a temperature threshold. In some embodiments, process 200 can determine whether temperature variation (e.g., a two-dimensional temperature profile) of a component is outside of an acceptable variability range, e.g., to identify a dead-zone of a pedestal.

[0059] In some embodiments, process 200 may determine whether the thickness information is out of specification. For example, if the thickness information is associated with surfaces of one or more components, process 200 may determine that the thickness information is out of specification if the thickness is greater than a predetermined threshold. This may indicate that a clean cycle is to be initiated. As another example, if the thickness information is associated with a surface of a wafer undergoing processing, process 200 may determine whether the deposited thickness is outside of a predetermined range. For example, process 200 may determine that a greater than expected thickness of film has deposited on a wafer and may determine, e.g., that various process controls are to be adjusted to control thickness of the film as a fabrication process (e.g., a deposition process) continues. Conversely, process 200 may determine that less than an expected thickness of film has deposited on the wafer, and may identify one or more anomalies or error conditions that may have caused the reduced thickness. For example, process 200 may identify a reduction in gas within an ampoule or mass flow controller, or a failure in a valve that controls gas flow to the process station, thereby causing less gas within the process station and in turn a reduced film thickness on the wafer. [0060] If, at 208, process 200 determines that the temperature information and/or the thickness information is out of specification (“yes” at 208), process 200 can proceed to 210 and can take at least one action. For example, process 200 can cause an alert to be presented, e.g., to a process engineer. The alert may be presented via a user interface on a system controller or other user device operatively coupled to the process station or a process chamber associated with the process station. As another example, in some embodiments, process 200 can cause a fabrication process to be stopped and/or paused. As yet another example, in some embodiments, process 200 can cause a recovery process to be initiated (e.g., a cleaning cycle and/or a precoat cycle may be initiated, for example, responsive to determining that film thickness on surfaces of the station exceed a predetermined threshold). As still another example, in some embodiments, process 200 can modify parameters of a fabrication process occurring in the station to correct for deposited film thickness being outside of an expected range, e.g., by modifying gas flow, modifying RF power, or the like.

[0061] In general, the action may be one that provides real-time process control and/or real-time predictive maintenance during performance of a fabrication process. For example, temperature information of a pedestal being outside of specification may allow detection of a developing failure in the pedestal heater(s), because process 200 may detect a dead-zone developing before complete failure. As another example, process 200 may detect an imminent or impending valve failure or drop in ampoule or mass flow controller precursor levels by detecting any deviation in film deposition thickness on a wafer relative to an expected thickness. By detecting deviations in temperature and/or film thickness in situ (e.g., while a fabrication process is occurring), control may be performed during the fabrication process.

[0062] Regardless of whether or not at least one action is taken at 210 (e.g., including if the temperature information and/or thickness information is determined to he within specification at 208, or “yes” at 208), process 200 can determine, at 212, if the process has completed. Responsive to determining that the process has not completed at 212 (“no” at 212), process 200 can loop back to block 202 and can receive additional data from the one or more infrared sensors. Conversely, if at 212 process 200 determines the process has completed (“yes” at 212), process 200 can end.

[0063] In some embodiments, infrared temperature (e.g., a temperature inferred based on infrared data), actual temperature (e.g., a ground truth temperature of a component or element), and emissivity may be related. For example, knowing two parameters of infrared temperature, actual temperature, and emissivity may allow the third parameter to be determined based on a relationship between the three parameters. Note that, in some embodiments, data from additional sensors (e.g., one or more additional thermocouples) may additionally be used. In some implementations, the relationship between infrared temperature, actual temperature, and emissivity may be learned using a machine learning model. In some embodiments, the machine learning model may be trained using a training set that includes measured values of infrared temperature, actual temperature (e.g., as measured by a thermocouple) and emissivity information. In some embodiments, the emissivity information may be based on known material properties. In some embodiments, a trained machine learning model may be particular to a given material, e.g., silicon, ceramic such as that used for a pedestal, or the like. In some embodiments, the trained machine learning model may be used to determine, based on input of two parameters of infrared temperature, actual temperature and emissivity, an output corresponding to a value of the third parameter. In some embodiments, the trained machine learning model may be utilized directly as part of an inference stage. Alternatively, in some embodiments, the trained machine learning model may be used to construct a look up table that associates values of the three parameters of infrared temperature, actual temperature, and emissivity. Note that a graph that illustrates an example relationship between these three parameters is shown in and described in FIG. 5. As illustrated, at a given actual temperature, with increasing emissivity (e.g., with increasing darkness of the surface or material), the corresponding infrared temperature decreases. In other words, for a given actual temperature (or ground truth temperature), emissivity and infrared temperature are inversely related. The exact relationship between actual temperature, emissivity, and infrared temperature may be material dependent and may be learned by a machine learning model based on experimental data.

[0064] As described above in connection with FIG. 2, in some embodiments, temperature information associated with one or more components of a station or of a wafer undergoing processing may be obtained. Note that the temperature information may be represented as temperatures for each pixel of an image representing a viewpoint of an IR camera used to obtain infrared data from which the temperature information was determined. Accordingly, temperature information may be determined for hundreds of pixels, corresponding to hundreds of points for the one or more components or the wafer, rather than one or two temperature measurements obtained from corresponding physical thermocouples disposed in a process station.

[0065] As described above, in some embodiments, for a given pixel or point, temperature information may comprise actual temperature that is determined based on an infrared temperature and an emissivity for that pixel or point. For example, the infrared temperature and the emissivity may be provided to a trained machine learning model to determine the corresponding actual temperature. As another example, the infrared temperature and the emissivity may be used as keys to a lookup table to determine the corresponding actual temperature. Note that a lookup table may be generated using a trained machine learning model. In instances in which a trained machine learning model is utilized, the model may be trained using experimental training data in which actual temperature is measured using one or more thermocouples, thermistors, or the like, and infrared temperature is measured using one or more infrared sensors. In some embodiments, emissivity may be determined using known material properties and/or spectral or wavelength information. For example, emissivity of a bare silicon wafer may be determined based on known properties of silicon. As another example, known properties of silicon oxide, which may form during a fabrication process, may be used to determine emissivity information during a fabrication process. Note that, in some embodiments, emissivity may be a global emissivity where the same emissivity value is applied to all pixels or regions. Conversely, in some embodiments, emissivity may be a local emissivity where emissivity is dependent on an angle of the infrared sensors or cameras. For example, emissivity may vary for shallow camera angles relative to increased camera angles (e.g., a viewpoint that is closer to top-down). In some embodiments, correction for infrared camera or sensor angle may be based on experimental data obtained using infrared sensors or cameras disposed at a particular angle and measurements of actual or ground truth temperatures. The actual temperatures may be used to determine the effect of the angle on emissivity at different regions or pixels. Note that relationships between emissivity and camera angle, distance, material properties, spectral/wavelength information, etc. may be determined experimentally, in conjunction with a trained machine learning model, and/or using a physicsbased model that simulates various chamber conditions.

[0066] Note that, in some embodiments, various image processing techniques may be used to determine temperatures for specific components in a process station and/or for a wafer in the process station. For example, edge detection and/or object detection may be employed to segment an image such that a cluster of pixels is identified as corresponding to a particular component or to the wafer. Temperature information for the component or the wafer may then be determined based on the infrared temperatures and/or emissivity information for the corresponding cluster of pixels.

[0067] FIG. 3 is a flowchart of an example process 300 for determining temperature information for one or more components of a process station and/or for a wafer residing in the process station in accordance with some embodiments. In some embodiments, blocks of process 300 may be executed by an edge controller and/or a system controller (e.g., as shown in and described above in connection with FIG. 1). In some embodiments, blocks of process 300 may be executed in an order other than what is shown in FIG. 3. In some embodiments, two or more blocks of process 300 may be executed substantially in parallel. In some embodiments, one or more blocks of process 300 may be omitted.

[0068] Process 300 can begin at 302 by receiving data from one or more infrared sensors (or cameras) associated with a process station. The data may be obtained during performance of a fabrication process. The data may be obtained from a viewport of the process station that provides any suitable view (e.g., a side view, a top-down view, etc.) of a region of the process station.

[0069] In some embodiments, the data obtained by the one or more infrared sensors may be raw voltage data. Process 300 may transform the raw voltage data to infrared temperature data. The infrared temperature data may be obtained using calibration data that transforms the raw voltage data to infrared temperature. The infrared temperature data may be two-dimensional data that represents the region captured by the infrared sensor(s) as pixels in two dimensions, where each pixel is associated with an infrared temperature.

[0070] In some embodiments, process 300 may perform image processing techniques such that one or more components or elements may be identified within an infrared temperature image. Accordingly, the infrared temperature data may be associated with particular components or elements (e.g., a pedestal, a wafer residing in the process station, etc.).

[0071] At 304, process 300 can determine emissivity data. The emissivity data may be determined based on known material properties of components of the station and/or of the wafer at a particular point of the fabrication process. For example, during a fabrication process, emissivity associated with the wafer may be determined based on known properties of silicon oxide, which may develop within the process station as a result of a fabrication process. As described above, the emissivity data may be global emissivity data that applies the same emissivity to the entire infrared image, or local emissivity data which corrects for the angle of the infrared sensor(s) or cameras at different regions of the infrared temperature image.

[0072] At 306, process 300 can predict actual temperature information based on the received data from the one or more infrared sensors and the emissivity data. The actual temperature information may be for one or more components of the process station, such as predicted temperature of a pedestal. In some embodiments, the actual temperature information may be for a surface of a wafer undergoing processing. The actual temperature information may be two-dimensional temperature information that can indicate temperature variations across a region (e.g., across a spatial region). For example, temperature variations across a pedestal may be utilized to identify a dead zone or a relatively cool zone of the pedestal that is below a temperature specification.

[0073] As described above, the actual temperature information may be determined based on the infrared temperature (determined from the data from the one or more infrared sensors) and the emissivity data. For example, the infrared temperature and the emissivity data may be provided to a machine learning model that provides the actual temperature as output. As another example, the infrared temperature and the emissivity data may be used as keys to a lookup table to identify the corresponding actual temperature. In some embodiments, actual temperature may be determined on a pixel-by-pixel basis for a two-dimensional image representing infrared temperatures. For example, for a given pixel, the infrared temperature and the emissivity value corresponding to the pixel may be used to determine the actual temperature.

[0074] In some implementations, thickness of deposited film may be estimated based on infrared data. For example, in some embodiments, infrared data and ground truth temperature data may be used to determine emissivity information for a particular surface (e.g., a surface of a component in the process station and/or a wafer surface of wafer undergoing processing). The emissivity information may be determined based on a difference between an infrared temperature determined based on the data from the infrared sensor(s) or camera(s) and the ground truth temperature (which may be obtained by one or more thermocouples or other physical temperature measuring elements disposed in the process station). By way of example, in an instance in which a fabrication process begins in the station, a ground truth temperature and an infrared temperature may be determined for a wafer undergoing fabrication. At the beginning of the process, the infrared temperature and the ground truth temperature may not differ by much. As the fabrication process continues and film is deposited, the infrared temperature may begin to deviate more from the ground truth temperature (which may be measured by a thermocouple disposed in the pedestal, or the like). The deviation in the infrared temperature may be due to the changing emissivity of the wafer due to the deposited film. Accordingly, the emissivity may be determined based on the difference between the infrared temperature and the ground truth temperature. For example, the infrared temperature and the ground truth temperature may be provided as input to a trained machine learning model configured to provide the corresponding emissivity as an output. As another example, the infrared temperature and the ground truth temperature may be used as keys to a lookup table to identify the corresponding emissivity. Note that emissivity may be determined on a pixel- by-pixel basis for an image representing infrared temperatures for a region, and ground truth temperature may be determined based on values of one or more thermocouples. Note that the same ground truth temperature may be applied to multiple pixels, e.g., due to having only one, two, three, etc. thermocouples from which to determine ground truth temperature.

[0075] Based on the emissivity information, thickness of deposited film may be determined. The thickness may be determined by providing the emissivity information to a trained machine learning model configured to predict film thickness based on the emissivity and the ground truth temperature. The model may have been trained using a training set that includes experimental data. For example, a training sample may include measured emissivity and ground truth temperature, as well as a measured corresponding film thickness. The model may be specific to a material or component. For example, a different model may be used to determine film thickness for a wafer than for film thickness on a station wall.

[0076] FIG. 4 is a flowchart of an example process 400 for determining thickness information associated with deposited film on one or more surfaces and/or on a wafer surface in accordance with some embodiments. In some embodiments, blocks of process 400 may be executed by an edge controller and/or a system controller (e.g., as shown in and described above in connection with FIG. 1). In some embodiments, blocks of process 400 may be executed in an order other than what is shown in FIG. 4. In some embodiments, two or more blocks of process 400 may be executed substantially in parallel. In some embodiments, one or more blocks of process 400 may be omitted.

[0077] Process 400 can begin at 402 by receiving data from one or more infrared sensors (or cameras) associated with a process station. The data may be obtained during performance of a fabrication process. The data may be obtained from a viewport of the process station that provides any suitable view (e.g., a side view, a top-down view, etc.) of a region of the process station.

[0078] In some embodiments, the data obtained by the one or more infrared sensors may be raw voltage data. Process 400 may transform the raw voltage data to infrared temperature data. The infrared temperature data may be obtained using calibration data that transforms the raw voltage data to infrared temperature. The infrared temperature data may be two-dimensional data that represents the region captured by the infrared sensor(s) as pixels in two dimensions, where each pixel is associated with an infrared temperature.

[0079] In some embodiments, process 400 may perform image processing techniques such that one or more components or elements may be identified within an infrared temperature image. Accordingly, the infrared temperature data may be associated with particular components or elements (e.g., a pedestal, a wafer residing in the process station, etc.).

[0080] At 404, process 400 can receive ground truth temperature information from one or more thermocouples associated with the process station. For example, the ground truth temperature information may be obtained from one or more thermocouples disposed in a pedestal of the process station.

[0081] At 406, process 400 can determine emissivity information associated with a wafer undergoing processing and/or one or more components of the process station based on the data from the one or more infrared sensors and the ground truth temperature information. For example, emissivity information may be determined using infrared temperature and ground truth temperature. For example, an infrared temperature and a ground truth temperature may be provided to a trained machine learning model to determine the corresponding emissivity. As another example, the infrared temperature and the ground truth temperature may be provided as keys to a look up table to determine the corresponding emissivity. Note that emissivity may be determined on a pixel-by-pixel basis for an image representing infrared temperature for a two-dimensional spatial region constructed using the data from the one or more infrared sensors.

[0082] At 408, process 400 can determine a deposition thickness of a film deposited on the wafer undergoing processing and/or a surface within the process station based on the emissivity information. For example, process 400 can provide the emissivity information to a trained machine learning model to obtain the corresponding deposition thickness. As another example, process 400 can utilize the emissivity information as a key to a look up table to obtain the corresponding deposition thickness. Note that deposition thickness may be determined on a pixel-by pixel basis based on the corresponding emissivity for the pixel. Accordingly, two- dimensional variations in thickness may be identified, either across a surface within the process station (e.g., a station wall) or across a wafer undergoing processing. This may allow nonuniformities in deposition to be detected on a wafer while the wafer is undergoing processing in situ, which may allow for process control to correct non-uniformities during the fabrication process.

[0083] Note that, in some embodiments, process 400 may be performed in a loop, e.g., during a fabrication process, for example, to monitor deposition thickness on a wafer during the fabrication process. In some embodiments, process 400 may be utilized prior to initiation of a fabrication process or after performance of a fabrication process to determine whether a station or chamber cleaning cycle is to be initiated. In some embodiments, a quality of an undercoat and/or a pre-coat of a wafer may be analyzed by determining uniformity of a deposition of the undercoat and/or the pre-coat, or the thickness of the undercoat or the pre-coat.

CONTEXT FOR DISCLOSED COMPUTATIONAL EMBODIMENTS

[0084] Systems including fabrication tools as described herein may include logic for utilizing infrared data, e.g., for determining temperature information and/or thickness information.

[0085] The analysis logic may be designed and implemented in any of various ways. For example, the logic can be implemented in hardware and/or software. Examples are presented in the controller section herein. Hardware-implemented control logic may be provided in any of a variety of forms, including hard coded logic in digital signal processors, applicationspecific integrated circuits, and other devices that have algorithms implemented as hardware. Analysis logic may also be implemented as software or firmware instructions configured to be executed on a general-purpose processor. System control software may be provided by “programming” in a computer readable programming language.

[0086] The computer program code for controlling processes in a process sequence can be written in any conventional computer readable programming language: for example, assembly language, C, C++, Pascal, Fortran, or others. Compiled object code or script is executed by the processor to perform the tasks identified in the program. Also as indicated, the program code may be hard coded.

[0087] Integrated circuits used in logic may include chips in the form of firmware that store program instructions, digital signal processors (DSPs), chips defined as application specific integrated circuits (ASICs), and/or one or more microprocessors, or microcontrollers that execute program instructions (e.g., software). Program instructions may be instructions communicated in the form of various individual settings (or program files), defining operational parameters for carrying out a particular analysis or image analysis application.

[0088] In some implementations, the image analysis logic is resident (and executes) on a computational resource on or closely associated with a fabrication tool from which camera images are captured. In some implementations, the image analysis logic is remote from a fabrication tool from which camera images are captured. For example, the analysis logic may be executable on cloud-based resources.

[0089] FIG. 6 is a block diagram of an example of the computing device 600 suitable for use in implementing some embodiments of the present disclosure. For example, device 600 may be suitable for implementing some or all functions of image analysis logic disclosed herein. [0090] Computing device 600 may include a bus 602 that directly or indirectly couples the following devices: memory 604, one or more central processing units (CPUs) 606, one or more graphics processing units (GPUs) 608, a communication interface 1310, input/output (I/O) ports 612, input/output components 614, a power supply 616, and one or more presentation components 618 (e.g., display(s)). In addition to CPU 606 and GPU 608, computing device 600 may include additional logic devices that are not shown in FIG. 6, such as but not limited to an image signal processor (ISP), a digital signal processor (DSP), an ASIC, an FPGA, or the like.

[0091] Although the various blocks of FIG. 6 are shown as connected via the bus 602 with lines, this is not intended to be limiting and is for clarity only. For example, in some embodiments, a presentation component 618, such as a display device, may be considered an VO component 614 (e.g., if the display is a touch screen). As another example, CPUs 606 and/or GPUs 608 may include memory (e.g., the memory 604 may be representative of a storage device in addition to the memory of the GPUs 608, the CPUs 606, and/or other components). In other words, the computing device of FIG. 6 is merely illustrative. Distinction is not made between such categories as “workstation,” “server,” “laptop,” “desktop,” “tablet,” “client device,” “mobile device,” “hand-held device,” “electronic control unit (ECU),” “virtual reality system,” and/or other device or system types, as all are contemplated within the scope of the computing device of FIG. 6.

[0092] Bus 602 may represent one or more busses, such as an address bus, a data bus, a control bus, or a combination thereof. The bus 602 may include one or more bus types, such as an industry standard architecture (ISA) bus, an extended industry standard architecture (EISA) bus, a video electronics standards association (VESA) bus, a peripheral component interconnect (PCI) bus, a peripheral component interconnect express (PCIe) bus, and/or another type of bus.

[0093] Memory 604 may include any of a variety of computer-readable media. The computer- readable media may be any available media that can be accessed by the computing device 600. The computer-readable media may include both volatile and nonvolatile media, and removable and non-removable media. By way of example, and not limitation, the computer-readable media may comprise computer-storage media and/or communication media.

[0094] The computer-storage media may include both volatile and nonvolatile media and/or removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, and/or other data types. For example, memory 604 may store computer-readable instructions (e.g., that represent a program(s) and/or a program element(s), such as an operating system. Computer-storage media may include, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by computing device 600. As used herein, computer storage media does not comprise signals per se.

[0095] The communication media may embody computer-readable instructions, data structures, program modules, and/or other data types in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” may refer to a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, the communication media may include wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media. Combinations of any of the above should also be included within the scope of computer- readable media.

[0096] CPU(s) 606 may be configured to execute the computer-readable instructions to control one or more components of the computing device 600 to perform one or more of the methods and/or processes described herein. CPU(s) 606 may each include one or more cores (e.g., one, two, four, eight, twenty-eight, seventy-two, etc.) that are capable of handling a multitude of software threads simultaneously. CPU(s) 606 may include any type of processor and may include different types of processors depending on the type of computing device 600 implemented (e.g., processors with fewer cores for mobile devices and processors with more cores for servers). For example, depending on the type of computing device 600, the processor may be an ARM processor implemented using Reduced Instruction Set Computing (RISC) or an x86 processor implemented using Complex Instruction Set Computing (CISC). Computing device 600 may include one or more CPUs 1306 in addition to one or more microprocessors or supplementary co-processors, such as math co-processors.

[0097] GPU(s) 608 may be used by computing device 600 to render graphics (e.g., 3D graphics). GPU(s) 608 may include many (e.g., tens, hundreds, or thousands) of cores that are capable of handling many software threads simultaneously. GPU(s) 608 may generate pixel data for output images in response to rendering commands (e.g., rendering commands from CPU(s) 606 received via a host interface). GPU(s) 608 may include graphics memory, such as display memory, for storing pixel data. The display memory may be included as part of memory 604. GPU(s) 608 may include two or more GPUs operating in parallel (e.g., via a link). When combined, each GPU 608 can generate pixel data for different portions of an output image or for different output images (e.g., a first GPU for a first image and a second GPU for a second image). Each GPU can include its own memory or can share memory with other GPUs.

[0098] In examples where the computing device 600 does not include the GPU(s) 608, the CPU(s) 606 may be used to render graphics.

[0099] Communication interface 610 may include one or more receivers, transmitters, and/or transceivers that enable computing device 600 to communicate with other computing devices via an electronic communication network, included wired and/or wireless communications. Communication interface 610 may include components and functionality to enable communication over any of a number of different networks, such as wireless networks (e.g., Wi-Fi, Z-Wave, Bluetooth, Bluetooth LE, ZigBee, etc.), wired networks (e.g., communicating over Ethernet), low-power wide-area networks (e.g., LoRaWAN, SigFox, etc.), and/or the internet.

[0100] I/O ports 612 may enable the computing device 1300 to be logically coupled to other devices including I/O components 614, presentation component(s) 618, and/or other components, some of which may be built in to (e.g., integrated in) computing device 600. Illustrative I/O components 614 include a microphone, mouse, keyboard, joystick, track pad, satellite dish, scanner, printer, wireless device, etc. I/O components 614 may provide a natural user interface (NUI) that processes air gestures, voice, or other physiological inputs generated by a user. In some instances, inputs may be transmitted to an appropriate network element for further processing. An NUI may implement any combination of speech recognition, stylus recognition, facial recognition, biometric recognition, gesture recognition both on screen and adjacent to the screen, air gestures, head and eye tracking, and touch recognition (as described in more detail below) associated with a display of computing device 600. Computing device 600 may be include depth cameras, such as stereoscopic camera systems, infrared camera systems, RGB camera systems, touchscreen technology, and combinations of these, for gesture detection and recognition. Additionally, computing device 600 may include accelerometers or gyroscopes (e.g., as part of an inertia measurement unit (IMU)) that enable detection of motion. In some examples, the output of the accelerometers or gyroscopes may be used by computing device 600 to render immersive augmented reality or virtual reality.

[0101] Power supply 616 may include a hard-wired power supply, a battery power supply, or a combination thereof. Power supply 616 may provide power to computing device 600 to enable the components of computing device 600 to operate. [0102] Presentation component(s) 618 may include a display (e.g., a monitor, a touch screen, a television screen, a heads-up-display (HUD), other display types, or a combination thereof), speakers, and/or other presentation components. Presentation component(s) 618 may receive data from other components (e.g., GPU(s) 608, CPU(s) 606, etc.), and output the data (e.g., as an image, video, sound, etc.).

[0103] The disclosure may be described in the general context of computer code or machine- useable instructions, including computer-executable instructions such as program modules, being executed by a computer or other machine, such as a personal data assistant or other handheld device. Generally, program modules including routines, programs, objects, components, data structures, etc., refer to code that perform particular tasks or implement particular abstract data types. The disclosure may be practiced in a variety of system configurations, including hand-held devices, consumer electronics, general-purpose computers, more specialty computing devices, etc. The disclosure may also be practiced in distributed computing environments where tasks are performed by remote-processing devices that are linked through a communications network.

Additional Considerations

[0104] Without limitation, example systems may include a plasma etch chamber or module, a plasma-assisted deposition chamber or module such as a plasma-assisted chemical vapor deposition (PECVD) chamber or module or a plasma-assisted atomic layer deposition (PEALD) chamber or module, an atomic layer etch (ALE) chamber or module, a clean chamber or module, a physical vapor deposition (PVD) chamber or module, an ion implantation chamber or module, and any other plasma-assisted semiconductor processing systems that may be associated or used in the fabrication and/or manufacturing of semiconductor wafers.

[0105] Unless otherwise specified, the plasma power levels and associated parameters provided herein are appropriate for processing a 300 mm wafer substrate. One of ordinary skill in the art would appreciate that these parameters may be adjusted as necessary for substrates of other sizes.

[0106] The apparatus/process described herein may be used in conjunction with lithographic patterning tools or processes, for example, for the fabrication or manufacture of electronic devices including semiconductor devices, displays, LEDs, photovoltaic panels and the like. Typically, though not necessarily, such tools/processes will be used or conducted together in a common fabrication facility. Lithographic patterning of a film typically includes some or all of the following operations, each operation enabled with a number of possible tools: (1) application of photoresist on a workpiece, i.e., substrate, using a spin-on or spray-on tool; (2) curing of photoresist using a hot plate or furnace or UV curing tool; (3) exposing the photoresist to visible or UV or x-ray light with a tool such as a wafer stepper; (4) developing the resist so as to selectively remove resist and thereby pattern it using a tool such as a wet bench; (5) transferring the resist pattern into an underlying film or workpiece by using a dry or plasma- assisted etching tool; and (6) removing the resist using a tool such as an RF or microwave plasma resist stripper.

[0107] As used in this specification and appended claims, the singular forms “a”, “an”, and “the” include plural referents unless the content and context dictates otherwise. For example, reference to “a cell” includes a combination of two or more such cells. Unless indicated otherwise, an “or” conjunction is used in its correct sense as a Boolean logical operator, encompassing both the selection of features in the alternative (A or B, where the selection of A is mutually exclusive from B) and the selection of features in conjunction (A or B, where both A and B are selected).

[0108] It is to be understood that the phrases “for each <item> of the one or more <items>,” “each <item> of the one or more <items>,” or the like, if used herein, are inclusive of both a single-item group and multiple-item groups, i.e., the phrase “for . . . each” is used in the sense that it is used in programming languages to refer to each item of whatever population of items is referenced. For example, if the population of items referenced is a single item, then “each” would refer to only that single item (despite the fact that dictionary definitions of “each” frequently define the term to refer to “every one of two or more things”) and would not imply that there must be at least two of those items. Similarly, the term “set” or “subset” should not be viewed, in itself, as necessarily encompassing a plurality of items — it will be understood that a set or a subset can encompass only one member or multiple members (unless the context indicates otherwise).

[0109] The use, if any, of ordinal indicators, e.g., (a), (b), (c). . . or the like, in this disclosure and claims is to be understood as not conveying any particular order or sequence, except to the extent that such an order or sequence is explicitly indicated. For example, if there are three steps labeled (i), (ii), and (iii), it is to be understood that these steps may be performed in any order (or even concurrently, if not otherwise contraindicated) unless indicated otherwise. For example, if step (ii) involves the handling of an element that is created in step (i), then step (ii) may be viewed as happening at some point after step (i). Similarly, if step (i) involves the handling of an element that is created in step (ii), the reverse is to be understood. It is also to be understood that use of the ordinal indicator “first” herein, e.g., “a first item,” should not be read as suggesting, implicitly or inherently, that there is necessarily a “second” instance, e.g., “a second item.”

[0110] Various computational elements including processors, memory, instructions, routines, models, or other components may be described or claimed as “configured to” perform a task or tasks. In such contexts, the phrase “configured to” is used to connote structure by indicating that the component includes structure (e.g., stored instructions, circuitry, etc.) that performs the task or tasks during operation. As such, the unit/circuit/component can be said to be configured to perform the task even when the specified component is not necessarily currently operational (e.g., is not on).

[0111] The components used with the “configured to” language may refer to hardware — for example, circuits, memory storing program instructions executable to implement the operation, etc. Additionally, “configured to” can refer to generic structure (e.g., generic circuitry) that is manipulated by software and/or firmware (e.g., an FPGA or a general -purpose processor executing software) to operate in manner that is capable of performing the recited task(s). Additionally, “configured to” can refer to one or more memories or memory elements storing computer executable instructions for performing the recited task(s). Such memory elements may include memory on a computer chip having processing logic. In some contexts, “configured to” may also include adapting a manufacturing process (e.g., a semiconductor fabrication facility) to fabricate devices (e.g., integrated circuits) that are adapted to implement or perform one or more tasks.

[0112] Although the foregoing embodiments have been described in some detail for purposes of clarity of understanding, it will be apparent that certain changes and modifications may be practiced within the scope of the appended claims. It should be noted that there are many alternative ways of implementing the processes, systems, and apparatus of the present embodiments. Accordingly, the present embodiments are to be considered as illustrative and not restrictive, and the embodiments are not to be limited to the details given herein.

Claims

CLAIMS What is claimed is:

1. A method for utilizing infrared data in conjunction with semiconductor fabrication processes, the method comprising: receiving data from one or more infrared sensors associated with a process station of a semiconductor fabrication process chamber; determining infrared temperature data and/or emissivity data based on the received data; determining at least one of: 1) temperature information associated with one or more components of the process station; or 2) thickness information indicating a thickness of deposited materials on components of the process station or on a surface of a substrate undergoing processing in the process station using the infrared temperature data and/or the emissivity data; determining whether the temperature information and/or the thickness information is out of a target specification; and in response to determining that the temperature information and/or the thickness information is out of the target specification, taking at least one corrective action.

2. The method of claim 1, wherein determining the temperature information associated with the one or more components of the process station comprises predicting an actual temperature of the one or more components based on the infrared temperature data and the emissivity data.

3. The method of claim 2, wherein determining the actual temperature comprises providing the infrared temperature data and the emissivity data to a trained machine learning model configured to predict an actual temperature associated with a given infrared temperature and emissivity.

4. The method of claim 3, wherein the trained machine learning model is trained using data from known material emissivities.

5. The method of claim 1, wherein the temperature information associated with the one or more components of the process station comprises temperature information associated with a pedestal.

6. The method of claim 5, wherein the temperature information comprises two- dimensional information representing temperature variations across the pedestal.

7. The method of claim 6, further comprising detecting a heater dead zone region of the pedestal based on the two-dimensional information, and wherein the at least one corrective action comprises causing an alert to be generated indicative of the heater dead zone region.

8. The method of any one of claims 1-7, wherein determining the thickness information comprises determining an emissivity of a surface of the components of the process station or the surface of the substrate undergoing processing based on ground truth temperature information and the infrared temperature data.

9. The method of claim 8, wherein the thickness information is determined based on the emissivity of the surface and known material properties of the surface of the components or the surface of the substrate undergoing processing.

10. The method of any one of claims 1-7, wherein determining whether the thickness information is out of the target specification comprises determining whether a thickness of deposited layers on the surface of the substrate is out of the target specification.

11. The method of claim 10, further comprising identifying an error in a deposition process occurring in the process station based on the thickness information being out of the target specification.

12. The method of claim 11, wherein identifying the error in the deposition process comprises identifying at least one of: a reduction in gas within an ampoule or mass flow controller, or a failure in a valve that controls gas flow to the process station.

13. The method of any one of claims 1-7, wherein the determining whether the temperature information and/or the thickness information is out of a target specification occurs during performance of a fabrication process.

14. The method of any one of claims 1-7, wherein determining whether the thickness information is out of the target specification comprises determining whether deposited material on components of the process station exceeds a threshold value.

15. The method of claim 14, wherein the at least one corrective action comprises initiating a cleaning cycle based on the determination that the deposited material exceeds the threshold value.

16. The method of any one of claims 1-7, wherein the emissivity data comprises global emissivity data applicable to an entire surface of a material of a particular type.

17. The method of any one of claims 1-7, wherein the emissivity data comprises local emissivity data, and where the method further comprises determining global emissivity data that varies across the surface of the material based on the local emissivity data.

18. A system for utilizing infrared data in conjunction with semiconductor fabrication processes, the system comprising: one or more processors configured to: receive data from one or more infrared sensors associated with a process station of a semiconductor fabrication process chamber; determine infrared temperature data and/or emissivity data based on the received data; determine at least one of: 1) temperature information associated with one or more components of the process station; or 2) thickness information indicating a thickness of deposited materials on components of the process station or on a surface of a substrate undergoing processing in the process station using the infrared temperature data and/or the emissivity data; determine whether the temperature information and/or the thickness information is out of a target specification; and in response to determining that the temperature information and/or the thickness information is out of the target specification, take at least one corrective action.

19. The system of claim 18, wherein determining the temperature information associated with the one or more components of the process station comprises predicting an actual temperature of the one or more components based on the infrared temperature data and the emissivity data.

20. The system of claim 19, wherein determining the actual temperature comprises providing the infrared temperature data and the emissivity data to a trained machine learning model configured to predict an actual temperature associated with a given infrared temperature and emissivity.

21. The system of claim 20 wherein the trained machine learning model is trained using data from known material emissivities.

22. The system of claim 18, wherein the temperature information associated with the one or more components of the process station comprises temperature information associated with a pedestal.

23. The system of claim 22, wherein the temperature information comprises two- dimensional information representing temperature variations across the pedestal.

24. The system of claim 23, wherein the one or more processors are further configured to detect a heater dead zone region of the pedestal based on the two- dimensional information, and wherein the at least one corrective action comprises causing an alert to be generated indicative of the heater dead zone region.

25. The system of any one of claims 18-24, wherein determining the thickness information comprises determining an emissivity of a surface of the components of the process station or the surface of the substrate undergoing processing based on ground truth temperature information and the infrared temperature data.

26. The system of claim 25, wherein the thickness information is determined based on the emissivity of the surface and known material properties of the surface of the components or the surface of the substrate undergoing processing.

27. The system of any one of claims 18-24, wherein determining whether the thickness information is out of the target specification comprises determining whether a thickness of deposited layers on the surface of the substrate is out of the target specification.

28. The system of claim 27, wherein the one or more processors are further configured to identify an error in a deposition process occurring in the process station based on the thickness information being out of the target specification.

29. The system of claim 28, wherein identifying the error in the deposition process comprises identifying at least one of: a reduction in gas within an ampoule or mass flow controller, or a failure in a valve that controls gas flow to the process station.

30. The system of any one of claims 18-24, wherein the determining whether the temperature information and/or the thickness information is out of a target specification occurs during performance of a fabrication process.

31. The system of any one of claims 18-24, wherein determining whether the thickness information is out of the target specification comprises determining whether deposited material on components of the process station exceeds a threshold value.

32. The system of claim 31 , wherein the at least one corrective action comprises initiating a cleaning cycle based on the determination that the deposited material exceeds the threshold value.

33. The system any one of claims 18-24, wherein the emissivity data comprises global emissivity data applicable to an entire surface of a material of a particular type.

34. The system of any one of claims 18-24, wherein the emissivity data comprises local emissivity data, and where the method further comprises determining global emissivity data that varies across the surface of the material based on the local emissivity data.