CN111260498A - Process parameter detection method and device, electronic equipment and readable storage medium - Google Patents

Abstract

Embodiments of the present application provide a process parameter detection method, device, electronic device, and readable storage medium, which relate to the technical field of cloud computing. The method includes: acquiring a sample to be tested, the sample to be tested includes multiple parameter values of target process parameters; determining a distribution curve of the target process parameter in the sample to be tested according to the multiple parameter values; The difference between the distribution curve of the target process parameter in the to-be-detected sample and the historical distribution curve corresponding to the target process parameter determines whether the target process parameter in the to-be-detected sample is abnormal, and outputs the detection result. The method does not lose too much information when detecting process parameters, therefore, the accuracy of the detection results is greatly improved.

Description

Process parameter detection method, device, electronic device and readable storage medium

technical field

The embodiments of the present application relate to the field of cloud computing technologies, and in particular, to a process parameter detection method, apparatus, electronic device, and readable storage medium.

Background technique

In the process of industrial manufacturing, the process parameters such as temperature, pressure and power of the equipment directly determine whether the final product is qualified. If the abnormality of these process parameters can be found in time in the production process, and the early warning and measures can be taken in time when the process parameters are abnormal, the defective rate of the product can be greatly reduced. Therefore, how to detect whether the process parameters are abnormal is a problem worth studying.

In the prior art, whether the process parameters are abnormal is mainly detected based on one-dimensional process parameters. Specifically, in a production process, a parameter value is sampled for each process parameter of each sample for modeling, and whether the process parameter is abnormal is judged by a traditional one-dimensional abnormality detection algorithm. For example, the value of the process parameter sampled by the current test sample is compared with the average value of the process parameter in the historical sample, and whether the process parameter is abnormal is determined according to the difference value compared.

However, the methods in the prior art lose a lot of information, which may lead to inaccurate detection results.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a process parameter detection method, device, electronic device, and readable storage medium, which are used to solve the problem of inaccurate detection results caused by the loss of a large amount of information in process parameter detection in the prior art.

In the first aspect, the present application provides a process parameter detection method, comprising:

Obtaining a sample to be detected, the sample to be detected includes multiple parameter values of target process parameters;

determining the distribution curve of the target process parameter in the sample to be tested according to the plurality of parameter values;

According to the difference between the distribution curve of the target process parameter in the sample to be tested and the historical distribution curve corresponding to the target process parameter, it is determined whether the target process parameter in the sample to be tested is abnormal, and the historical distribution curve is determined. The curve is obtained based on the historical qualified samples; the detection result is output, and the detection result is used to indicate whether the target process parameter in the to-be-detected sample is abnormal.

As an optional implementation manner, according to the difference between the distribution curve of the target process parameter in the to-be-detected sample and the historical distribution curve corresponding to the target process parameter, determine the Before checking whether the target process parameters are abnormal, it also includes:

Obtaining a plurality of historically qualified samples, each of the historically qualified samples including a plurality of parameter values of the target process parameters;

According to a plurality of parameter values of the target process parameters in each of the historically qualified samples, respectively determine the distribution curve of the target process parameters in each of the historically qualified samples;

According to the distribution curve of the target process parameter in each of the historical qualified samples, the historical distribution curve corresponding to the target process parameter is determined.

As an optional implementation manner, determining the historical distribution curve corresponding to the target process parameter according to the distribution curve of the target process parameter in each of the historically qualified samples, including:

Determine the center distribution curve of the distribution curve of the target process parameter in each of the historical qualified samples, and use the center distribution curve as the historical distribution curve corresponding to the target process parameter.

As an optional implementation manner, according to the difference between the distribution curve of the target process parameter in the to-be-detected sample and the historical distribution curve corresponding to the target process parameter, determine the Whether the target process parameters are abnormal, including:

According to the difference between the distance between the distribution curve of the target process parameter in the sample to be tested and the historical distribution curve corresponding to the target process parameter and the target distance, determine whether the target process parameter in the sample to be tested is abnormal .

As an optional implementation manner, according to the difference between the distribution curve of the target process parameter in the to-be-detected sample and the historical distribution curve corresponding to the target process parameter, determine the Before checking whether the target process parameters are abnormal, it also includes:

The target distance is determined according to the distance between the distribution curve of the target process parameter in each of the historically qualified samples and the historical distribution curve corresponding to the target process parameter.

As an optional implementation manner, determining the target distance according to the distance between the distribution curve of the target process parameter in each of the historically qualified samples and the historical distribution curve corresponding to the target process parameter, including:

Respectively determine the distance between the distribution curve of the target process parameter in each historically qualified sample and the historical distribution curve corresponding to the target process parameter, and obtain a plurality of distances to be selected

The maximum distance among the plurality of candidate distances is used as the target distance.

As an optional implementation manner, the determining the distribution curve of the target process parameter in the sample to be detected according to the plurality of parameter values includes:

determining the empirical distribution function of the target process parameter in the sample to be tested according to the plurality of parameter values;

Smoothing is performed on the empirical distribution function to obtain a distribution curve of the target process parameter in the sample to be detected.

In a second aspect, an embodiment of the present application provides a process parameter detection device, including:

an acquisition module, configured to acquire a sample to be detected, where the sample to be detected includes a plurality of parameter values of target process parameters;

a determination module, configured to determine the distribution curve of the target process parameter in the sample to be detected according to the plurality of parameter values; and, according to the distribution curve of the target process parameter in the sample to be detected and the target The difference between the historical distribution curves corresponding to the process parameters determines whether the target process parameters in the samples to be tested are abnormal, and the historical distribution curves are obtained based on historical qualified samples;

An output module, configured to output a detection result, where the detection result is used to indicate whether the target process parameter in the sample to be detected is abnormal.

As an optional implementation manner, the obtaining module is also used for:

Obtaining a plurality of historically qualified samples, each of the historically qualified samples including a plurality of parameter values of the target process parameters;

The determining module is further configured to: respectively determine the distribution curve of the target process parameter in each of the historically qualified samples according to a plurality of parameter values of the target process parameter in each of the historically qualified samples; and ,

According to the distribution curve of the target process parameter in each of the historical qualified samples, the historical distribution curve corresponding to the target process parameter is determined.

As an optional implementation manner, the determining module is specifically used for:

Determine the center distribution curve of the distribution curve of the target process parameter in each of the historical qualified samples, and use the center distribution curve as the historical distribution curve corresponding to the target process parameter.

As an optional implementation manner, the determining module is specifically used for:

According to the difference between the distance between the distribution curve of the target process parameter in the sample to be tested and the historical distribution curve corresponding to the target process parameter and the target distance, determine whether the target process parameter in the sample to be tested is abnormal .

As an optional implementation manner, the determining module is specifically used for:

The target distance is determined according to the distance between the distribution curve of the target process parameter in each of the historically qualified samples and the historical distribution curve corresponding to the target process parameter.

As an optional implementation manner, the determining module is specifically used for:

Respectively determine the distance between the distribution curve of the target process parameter in each historically qualified sample and the historical distribution curve corresponding to the target process parameter, and obtain a plurality of distances to be selected;

The maximum distance among the plurality of candidate distances is used as the target distance.

As an optional implementation manner, the determining module is specifically used for:

determining an empirical distribution function of the target process parameter in the sample to be tested according to the plurality of parameter values; and,

Smoothing is performed on the empirical distribution function to obtain a distribution curve of the target process parameter in the sample to be detected.

In a third aspect, an embodiment of the present application provides an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of the first aspect above.

In a fourth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause the computer to execute the method described in the first aspect.

In a fifth aspect, the embodiments of the present application provide a process parameter detection method, including:

Obtaining a sample to be detected, the sample to be detected includes multiple parameter values of target process parameters;

determining the distribution curve of the target process parameter in the sample to be tested according to the plurality of parameter values;

According to the distribution curve of the target process parameter in the to-be-detected sample and the historical distribution curve corresponding to the target process parameter, determine whether the target process parameter in the to-be-detected sample is abnormal, and the historical distribution curve is based on A qualified sample of history is obtained;

Output a detection result, which is used to indicate whether the target process parameter in the sample to be detected is abnormal

An embodiment in the above application has the following advantages or beneficial effects:

Based on multiple parameter values of the target process parameters in the sample to be tested, the distribution curve of the target process parameter is determined, and based on the difference between the distribution curve and the historical distribution curve corresponding to the target process parameter, it is determined whether the target process parameter in the sample to be tested is There is an exception. Since the distribution curve of the target process parameter is a curve obtained based on multiple parameter values, it can represent the complete information of the parameter value of the target process parameter changing with time. Therefore, when detecting the target process according to the curve and the historical distribution curve When a parameter is abnormal, it can be done based on the complete parameter value without losing too much information, so the accuracy of the detection result is greatly improved.

Other effects of the above-mentioned optional manners will be described below with reference to specific embodiments.

Description of drawings

The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present application. in:

Fig. 1 is a schematic diagram of temperature process parameters in a certain rubber compound production process;

Fig. 2 is a schematic diagram of power process parameters in a certain rubber compound production process;

3 is a schematic flowchart of a process parameter detection method provided by an embodiment of the present application;

4 is a schematic flowchart of a process parameter detection method provided by an embodiment of the present application;

5 is a schematic flowchart of a process parameter detection method provided by an embodiment of the present application;

Fig. 6 is an example diagram of distribution curve distance;

7 is a schematic flowchart of a process parameter detection method provided by an embodiment of the present application;

8 is a schematic diagram of the principle of a process parameter detection method provided by an embodiment of the present application;

FIG. 9 is a module structure diagram of a process parameter detection device 900 provided by an embodiment of the present application;

FIG. 10 is a block diagram of an electronic device for a process parameter detection method according to an embodiment of the present application.

Detailed ways

Exemplary embodiments of the present application are described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

In the prior art, a parameter value is sampled for each process parameter of each sample in a production process for modeling, and whether the process parameter is abnormal is judged by a traditional one-dimensional abnormality detection algorithm. For example, the value of the process parameter sampled by the current test sample is compared with the average value of the process parameter in the historical sample, and whether the process parameter is abnormal is determined according to the difference value compared. This method only uses part of the parameter values of the process parameters as the benchmark for detection, so a large number of process parameter values will be lost during detection, which may lead to inaccurate detection results.

Considering the problem in the prior art that using a one-dimensional anomaly detection algorithm to detect process parameters will lose a large number of process parameter values and may cause inaccurate detection results, the embodiment of the present application performs detection based on the distribution curve of the process parameters, so that the detection is based on a complete Process parameter values are carried out without losing a large number of process parameter values, which can greatly improve the accuracy of the detection results.

The embodiments of the present application can be applied to various industrial manufacturing and production projects, such as a rubber compound production process, a plastic injection molding process, and the like. Taking a rubber compound processing process as an example, a variety of process parameters may need to be detected in a production process, such as temperature, rotational speed, pressure, power, and energy. At each stage in the entire production process, the parameter values of each process parameter can be collected. A sample can be formed by counting the parameter values of each process parameter in each stage of a production process or the parameter values of some stages in a production process.

The following table 1 is an example of a sample formed during the processing of a rubber compound. As shown in table 1, the sample numbered 1 includes five process parameters of temperature, pressure, energy, power, and rotational speed. Each process parameter Include multiple parameter values.

Table 1

Figure 1 is a schematic diagram of the temperature process parameters in the production process of a certain compound. As shown in Figure 1, the horizontal axis represents the sample number, and the vertical axis represents the temperature value. The distribution of all parameter values of the temperature process parameters in each sample is determined by the corresponding The box diagram is shown.

Figure 2 is a schematic diagram of the power process parameters in the production process of a rubber compound. As shown in Figure 2, the horizontal axis represents the sample number, and the vertical axis represents the power value. The distribution of all parameter values of the power process parameters in each sample passes through the corresponding Box diagram shown.

FIG. 3 is a schematic flowchart of a process parameter detection method provided by an embodiment of the present application. The execution body of the method may be an electronic device with computing processing capability. As shown in FIG. 3 , the method includes:

S301. Obtain a sample to be detected, where the sample to be detected includes multiple parameter values of target process parameters.

Optionally, the above-mentioned sample to be detected is a sample obtained by statistics of parameter values of process parameters of each stage or part of the stage in a production process. The sample to be tested may include multiple parameter values of one process parameter, or may include multiple process parameters, and each process parameter corresponds to multiple parameter values. If the sample to be tested includes multiple process parameters, the above-mentioned target process parameter may refer to any one of the multiple process parameters. For each process parameter, it can be detected whether there is any abnormality in the manner of the following embodiments.

Optionally, the form of the above-mentioned sample to be detected can be in the form of the data set exemplified in the aforementioned Table 1, or can also be in the form of the box diagram exemplified in the above-mentioned FIG. 1 or FIG. 2, or can also be other It can represent the form of all parameter values, which is not specifically limited in this embodiment of the present application.

S302. Determine the distribution curve of the target process parameter in the sample to be detected according to the above-mentioned multiple parameter values.

Optionally, based on the above-mentioned multiple parameter values, a distribution curve of the target process parameter can be obtained, and the distribution curve of the target process parameter can represent the information of the multiple parameter values, and specifically, the parameter value that can represent the process parameter changes with time. Information.

Optionally, in this embodiment of the present application, the distribution curve of the target process parameter may be represented by a distribution function.

S303 , according to the difference between the distribution curve of the target process parameter in the sample to be tested and the historical distribution curve corresponding to the target process parameter, determine whether the target process parameter in the sample to be tested is abnormal.

Wherein, the historical distribution curve is obtained based on historical qualified samples.

Optionally, the above-mentioned historical distribution curve may refer to the distribution curve obtained by the qualified samples in the samples detected before the samples to be detected are detected, that is, the historical distribution curve represents the characteristics of the qualified samples.

Corresponding to the samples to be tested, the historical qualified samples may include a variety of process parameters, or may include one process parameter. In the embodiment of the present application, the historical distribution curve refers to the distribution curve corresponding to the target process parameter.

The process of obtaining the above historical distribution curve will be described in detail in the following embodiments.

On the basis of obtaining the historical distribution curve, it is possible to compare the distribution curve of the target process parameter in the sample to be tested with the historical distribution curve, and determine whether the target process parameter is abnormal according to the difference between the curves.

S304 , outputting a detection result, where the detection result is used to indicate whether the above-mentioned target process parameter in the above-mentioned to-be-detected sample is abnormal.

Optionally, the above detection result may be text information or information combining text and images.

Taking the information combining text and images as an example, for example, "the temperature parameter in this sample is abnormal" can be output, and at the same time, an image of the distribution curve of the temperature in the sample to be detected over time can be output, or the temperature in the sample to be detected can be output. Time-varying distribution curves and comparison images of historical distribution curves, etc.

In this embodiment, the distribution curve of the target process parameter is determined based on multiple parameter values of the target process parameter in the sample to be detected, and based on the difference between the distribution curve and the historical distribution curve corresponding to the target process parameter, the sample to be detected is determined. Whether the target process parameters are abnormal. Since the distribution curve of the target process parameter is a curve obtained based on multiple parameter values, it can represent the complete information of the parameter value of the target process parameter changing with time. Therefore, when detecting the target process according to the curve and the historical distribution curve When a parameter is abnormal, it can be done based on the complete parameter value without losing too much information, so the accuracy of the detection result is greatly improved.

When the distribution curve of the target process parameter is determined in the above step S302, an optional embodiment adopts an empirical distribution function to represent the distribution curve of the target process parameter. Specifically, if the empirical distribution curve of the target process parameter is represented by the distribution function _Fn (x), the distribution function _Fn (x) can be directly used to form the distribution function of the target process parameter in the above step S302. F _n (x) can be represented by the following formula (1).

Among them, x is the independent variable of the function, xi represents the ith parameter value of the target process parameter fitting the empirical distribution curve, n represents the number of parameter values of the target process parameter fitting the empirical distribution curve, and I represents the indicative function , the value of the indicative function is 0 or 1. Specifically, when x _i ≤x, I takes a value of 1, and when x _i >x, I takes a value of 0.

In a specific implementation process, since the parameter values of the target process parameters may vary greatly, the distribution curve represented by F _n (x) may not be smooth enough. Based on this consideration, as another optional implementation manner, the distribution curve of the smoothed F _n (x) is used as the distribution curve of the target process parameter in the embodiment of the present application.

4 is a schematic flowchart of a process parameter detection method provided by an embodiment of the present application. As shown in FIG. 4 , an optional method for determining the distribution curve of the target process parameter in the above step S302 includes:

S401. Determine an empirical distribution function of the target process parameter in the to-be-detected sample according to the plurality of parameter values.

The empirical distribution function may be the above-mentioned F _n (x).

S402 , performing smoothing processing on the above-mentioned empirical distribution function to obtain a distribution curve of the target process parameter in the above-mentioned sample to be detected.

In one example, the Bernstein distribution function estimator may be used to smooth F _n (x) to obtain a distribution curve B _mn (x) of the target process parameter, as shown in the following formulas (2) and (3).

Wherein, k is the number of types of process parameters in the sample to be tested (or the historical qualified sample hereinafter), and m represents the order of the polynomial.

The distribution curve of the target process parameters obtained through the above steps S401-S402 has better smoothness and better boundary properties. Therefore, when the subsequent curve difference comparison is performed based on the distribution curve, a more accurate comparison can be obtained. result.

As mentioned above, the above historical distribution curve is obtained based on historical qualified samples. The process of obtaining the historical distribution curve is performed before the above step S303. When obtaining the historical distribution curve based on the historical qualified samples, any one of the following methods can be used.

In the first optional manner, a qualified sample can be randomly selected from a plurality of historical qualified samples, and a distribution curve of the target process parameters in the qualified sample is established, and the curve is used as the above-mentioned historical distribution curve.

In the second alternative, a qualified sample that is closest to the production time of the sample to be tested can be selected, and a distribution curve of the target process parameters in the qualified sample can be established, and the curve can be used as the above-mentioned historical distribution curve.

In the third optional manner, the above-mentioned historical distribution curve may be obtained by processing the qualified samples of the plurality of histories based on the qualified samples of the plurality of histories. The third optional manner will be described in detail below.

5 is a schematic flowchart of a process parameter detection method provided by an embodiment of the present application. As shown in FIG. 4 , the process of obtaining the above-mentioned historical distribution curve based on a plurality of historical format samples includes:

S501. Acquire a plurality of historically qualified samples, and each historically qualified sample includes a plurality of parameter values of the above-mentioned target process parameters.

Exemplarily, the above-mentioned multiple historical qualified samples may be qualified samples within a preset period before the time when the above-mentioned samples to be tested are produced, and the preset period may be, for example, one month, three months, or half a year.

S502 , according to the multiple parameter values of the target process parameters in each historically qualified sample, respectively determine the distribution curve of the target process parameter in each historically qualified sample.

Optionally, the method for determining the distribution curve of the target process parameter in the historically qualified samples may be the same as the method for determining the distribution curve of the target process parameter in the sample to be tested in the foregoing embodiment. Repeat.

S503: Determine a historical distribution curve corresponding to the target process parameter according to the distribution curve of the target process parameter in each historically qualified sample.

As an optional embodiment, the center distribution curve of the distribution curve of the target process parameter in each historical qualified sample may be determined, and the center distribution curve is used as the historical distribution curve corresponding to the target process parameter.

The above-mentioned central distribution curve can represent the common characteristics of the target process parameters in multiple historical samples. Therefore, using the central distribution curve as the historical distribution curve compared with the samples to be detected can make the comparison result more accurate.

The following describes the process of determining whether the target process parameter of the sample to be tested is abnormal in the above step S303.

As an optional implementation manner, the embodiment of the present application measures the difference between the distribution curves based on the distance between the distribution curves.

和

则两个分布曲线的距离为图6中双箭头线的长度，该长度可以通过如下公式(4)表示。Figure 6 is an example diagram of the distribution curve distance. As shown in Figure 6, it is assumed that there are two distribution curves

and

Then the distance between the two distribution curves is the length of the double-arrow line in FIG. 6 , and the length can be expressed by the following formula (4).

In a specific implementation process, as an example, Monte Carlo integral calculation can be used. Specific steps are as follows:

First, generate samples Y ₁ , Y ₂ ,...,Y _N that obey a uniform distribution.

分布的样本X₁,X₁,…,X_N。Secondly, based on Y ₁ , Y ₂ ,...,Y _N , generate obedience

Distribution of samples X ₁ ,X ₁ ,…,X _N .

Then, calculate the integral

In the above step S303, to determine whether the target process parameters of the sample to be tested are abnormal, the method shown in FIG.

Further, the above distance is judged, and according to the difference between the distance between the distribution curve of the target process parameter in the sample to be tested and the historical distribution curve corresponding to the target process parameter and the target distance, it is determined whether the target process parameter in the sample to be tested is abnormal.

Wherein, the above-mentioned difference may be a difference value or a ratio value or the like.

In an optional manner, the above-mentioned target distance may be a preset empirical value.

In another optional manner, the above target distance may be obtained according to historical qualified samples.

Specifically, in this optional manner, the target distance may be determined according to the distance between the distribution curve of the target process parameter in each historically qualified sample and the historical distribution curve corresponding to the target process parameter.

As described above in steps S501-S503, the distribution curve of the target process parameters in each historically qualified sample, and the historical distribution curve corresponding to the target process parameters can be obtained. Calculate the distance between the historical distribution curve and the distribution curve corresponding to each historical qualified sample, so as to obtain a plurality of candidate distances. On the basis of obtaining a plurality of candidate distances, one candidate distance may be selected as the target distance, or the above target distance may be obtained by performing averaging and other processing on the plurality of candidate distances. The following FIG. 7 takes one form as an example for description.

FIG. 7 is a schematic flowchart of a process parameter detection method provided by an embodiment of the present application. As shown in FIG. 7 , an example of determining the target distance includes:

S701, respectively determining the distance between the distribution curve of the target process parameter in each historical qualified sample and the historical distribution curve corresponding to the target process parameter, to obtain a plurality of distances to be selected.

S702. Use the maximum distance among the above-mentioned multiple candidate distances as the above-mentioned target distance.

It should be noted that if the sample to be tested includes multiple target process parameters, the above target distance is calculated for each target process parameter, or the above target distance can be calculated by combining various target process parameters.

An example of a comprehensive calculation is as follows.

基于所有历史合格样本，得到各目标工艺参数的中心分布曲线

使用下述公式(5)计算出最大距离。Assuming that a certain sample i in the historical qualified samples includes k kinds of target process parameters, the distribution curve of these target process parameters is

Based on all historical qualified samples, the center distribution curve of each target process parameter is obtained

The maximum distance is calculated using the following formula (5).

where s is the sample size.

The maximum distance calculated by the above formula (5) is the comprehensive distance of all process parameters in the sample. Therefore, the distance between the distribution curve of the target process parameter in the sample to be detected and the historical distribution curve corresponding to the target process parameter corresponds to the distance to be detected. The combined distance of all process parameters in the sample.

As an example, it is assumed that the distance between the distribution curve of the target process parameter in the sample to be tested and the historical distribution curve corresponding to the target process parameter is D', if D'>2*D _max , the target process in the sample to be tested can be determined The parameter is abnormal, that is, the sample to be tested is an unqualified sample.

FIG. 8 is a schematic diagram of the principle of the process parameter detection method provided by the embodiment of the present application. As shown in FIG. 8 , a distribution curve of each target process parameter of each sample is obtained based on historical qualified samples, and for each process parameter, the calculation center distribution curve. Based on the distribution curve and the center distribution curve of each historical qualified sample, the maximum distance (ie, the aforementioned target distance) D _max can be calculated, and based on the distribution curve and the center distribution curve of the sample to be detected, D' can be calculated, and by comparing D' and D _max , that is, whether the target process parameters of the sample to be tested are abnormal can be obtained.

FIG. 9 is a block diagram of a process parameter detection device 900 provided by an embodiment of the present application. As shown in FIG. 9 , the device includes:

The obtaining module 901 is configured to obtain a sample to be detected, wherein the sample to be detected includes a plurality of parameter values of target process parameters.

A determination module 902, configured to determine the distribution curve of the target process parameter in the sample to be detected according to the plurality of parameter values; and, according to the distribution curve of the target process parameter in the sample to be detected and the The difference between the historical distribution curves corresponding to the target process parameters determines whether the target process parameters in the samples to be tested are abnormal, and the historical distribution curves are obtained based on historical qualified samples.

The output module 903 is configured to output a detection result, where the detection result is used to indicate whether the target process parameter in the sample to be detected is abnormal.

As an optional implementation manner, the obtaining module 901 is also used for:

A plurality of historically qualified samples are obtained, and each of the historically qualified samples includes a plurality of parameter values of the target process parameters.

The determination module 902 is further configured to: respectively determine the distribution curve of the target process parameter in each of the historically qualified samples according to a plurality of parameter values of the target process parameter in each of the historically qualified samples; and, According to the distribution curve of the target process parameter in each of the historical qualified samples, the historical distribution curve corresponding to the target process parameter is determined.

As an optional implementation manner, the determining module 902 is specifically configured to:

Determine the center distribution curve of the distribution curve of the target process parameter in each of the historical qualified samples, and use the center distribution curve as the historical distribution curve corresponding to the target process parameter.

As an optional implementation manner, the determining module 902 is specifically configured to:

According to the difference between the distance between the distribution curve of the target process parameter in the sample to be tested and the historical distribution curve corresponding to the target process parameter and the target distance, determine whether the target process parameter in the sample to be tested is abnormal .

As an optional implementation manner, the determining module 902 is specifically configured to:

The target distance is determined according to the distance between the distribution curve of the target process parameter in each of the historically qualified samples and the historical distribution curve corresponding to the target process parameter.

As an optional implementation manner, the determining module 902 is specifically configured to:

Determine the distance between the distribution curve of the target process parameter in each historical qualified sample and the historical distribution curve corresponding to the target process parameter, obtain a plurality of candidate distances, and use the maximum distance in the plurality of candidate distances as the distance. the target distance.

As an optional implementation manner, the determining module 902 is specifically configured to:

Determine an empirical distribution function of the target process parameter in the sample to be tested according to the plurality of parameter values; and perform smoothing on the empirical distribution function to obtain an empirical distribution function of the target process parameter in the sample to be tested distribution curve.

According to the embodiments of the present application, the present application further provides an electronic device and a readable storage medium.

As shown in FIG. 10 , it is a block diagram of an electronic device of the method for detecting a process parameter according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the application described and/or claimed herein.

As shown in FIG. 10, the electronic device includes: one or more processors 1001, a memory 1002, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or otherwise as desired. The processor may process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used with multiple memories and multiple memories, if desired. Likewise, multiple electronic devices may be connected, each providing some of the necessary operations (eg, as a server array, a group of blade servers, or a multiprocessor system). In FIG. 10, a processor 1001 is used as an example.

The memory 1002 is the non-transitory computer-readable storage medium provided by the present application. Wherein, the memory stores instructions executable by at least one processor, so that the at least one processor executes the process parameter detection method provided by the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, and the computer instructions are used to cause the computer to execute the process parameter detection method provided by the present application.

As a non-transitory computer-readable storage medium, the memory 1002 can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules corresponding to the process parameter detection method in the embodiments of the present application (for example, The acquisition module 1001, the determination module 1002 and the output module 1003 shown in FIG. 10). The processor 1001 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions and modules stored in the memory 1002, that is, implementing the process parameter detection method in the above method embodiments.

The memory 1002 can include a stored program area and a stored data area, wherein the stored program area can store an operating system, an application program required by at least one function; the stored data area can store data created according to the use of electronic equipment detected by process parameters, etc. . Additionally, memory 1002 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 1002 may optionally include memory located remotely relative to the processor 1001, and these remote memories may be connected to the electronic device for process parameter detection via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The electronic device for process parameter detection may further include: an input device 1003 and an output device 1004 . The processor 1001 , the memory 1002 , the input device 1003 and the output device 1004 may be connected by a bus or in other ways, and the connection by a bus is taken as an example in FIG. 10 .

The input device 1003 can receive input numerical or character information, and generate key signal input related to user settings and function control of electronic equipment for process parameter detection, such as touch screen, keypad, mouse, trackpad, touchpad, pointing stick, One or more input devices such as mouse buttons, trackballs, joysticks, etc. Output devices 1004 may include display devices, auxiliary lighting devices (eg, LEDs), haptic feedback devices (eg, vibration motors), and the like. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

These computational programs (also referred to as programs, software, software applications, or codes) include machine instructions for programmable processors, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages calculation program. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or apparatus for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.

According to the technical solutions of the embodiments of the present application, a method for detecting process parameters is also provided, including:

A sample to be detected is obtained, and the sample to be detected includes multiple parameter values of the target process parameter.

According to the plurality of parameter values, a distribution curve of the target process parameter in the sample to be detected is determined.

According to the distribution curve of the target process parameter in the to-be-detected sample and the historical distribution curve corresponding to the target process parameter, determine whether the target process parameter in the to-be-detected sample is abnormal, and the historical distribution curve is based on A qualified sample of history is obtained.

A detection result is output, where the detection result is used to indicate whether the target process parameter in the sample to be detected is abnormal.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present application can be performed in parallel, sequentially or in different orders, and as long as the desired results of the technical solutions disclosed in the present application can be achieved, no limitation is imposed herein.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims (17)

1. A process parameter detection method is characterized by comprising the following steps:

obtaining a sample to be detected, wherein the sample to be detected comprises a plurality of parameter values of target process parameters;

determining a distribution curve of the target process parameters in the sample to be detected according to the plurality of parameter values;

determining whether the target process parameters in the sample to be detected are abnormal or not according to the difference between the distribution curve of the target process parameters in the sample to be detected and the historical distribution curve corresponding to the target process parameters, wherein the historical distribution curve is obtained based on historical qualified samples;

and outputting a detection result, wherein the detection result is used for indicating whether the target process parameters in the sample to be detected are abnormal or not.

2. The method according to claim 1, wherein before determining whether the target process parameter in the sample to be detected is abnormal according to the difference between the distribution curve of the target process parameter in the sample to be detected and the historical distribution curve corresponding to the target process parameter, the method further comprises:

obtaining a plurality of historical qualified samples, wherein each historical qualified sample comprises a plurality of parameter values of the target process parameter;

respectively determining a distribution curve of the target process parameter in each historical qualified sample according to a plurality of parameter values of the target process parameter in each historical qualified sample;

and determining a historical distribution curve corresponding to the target process parameter according to the distribution curve of the target process parameter in each historical qualified sample.

3. The method of claim 2, wherein said determining a historical profile of the target process parameter from the profile of the target process parameter in each of the historically qualified samples comprises:

and determining a central distribution curve of the target process parameter in each historical qualified sample, and taking the central distribution curve as a historical distribution curve corresponding to the target process parameter.

4. The method according to claim 2 or 3, wherein the determining whether the target process parameter in the sample to be detected is abnormal according to the difference between the distribution curve of the target process parameter in the sample to be detected and the historical distribution curve corresponding to the target process parameter comprises:

and determining whether the target process parameters in the sample to be detected are abnormal or not according to the difference between the target distance and the distance between the distribution curve of the target process parameters in the sample to be detected and the historical distribution curve corresponding to the target process parameters.

5. The method according to claim 4, wherein before determining whether the target process parameter in the sample to be detected is abnormal according to the difference between the distribution curve of the target process parameter in the sample to be detected and the historical distribution curve corresponding to the target process parameter, the method further comprises:

and determining the target distance according to the distance between the distribution curve of the target process parameter in each historical qualified sample and the historical distribution curve corresponding to the target process parameter.

6. The method of claim 5, wherein said determining the target distance based on the distance between the profile of the target process parameter in each of the historically qualified samples and the historical profile corresponding to the target process parameter comprises:

respectively determining the distance between the distribution curve of the target process parameter in each historical qualified sample and the historical distribution curve corresponding to the target process parameter to obtain a plurality of candidate distances;

and taking the maximum distance in the plurality of candidate distances as the target distance.

7. The method according to any one of claims 1 to 6, wherein said determining a profile of said target process parameter in said sample to be tested based on said plurality of parameter values comprises:

determining an empirical distribution function of the target process parameters in the sample to be detected according to the plurality of parameter values;

and smoothing the empirical distribution function to obtain a distribution curve of the target process parameters in the sample to be detected.

8. A process parameter detection device is characterized by comprising:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a sample to be detected, and the sample to be detected comprises a plurality of parameter values of target process parameters;

the determining module is used for determining a distribution curve of the target process parameters in the sample to be detected according to the plurality of parameter values; and the number of the first and second groups,

determining whether the target process parameters in the sample to be detected are abnormal or not according to the difference between the distribution curve of the target process parameters in the sample to be detected and the historical distribution curve corresponding to the target process parameters, wherein the historical distribution curve is obtained based on historical qualified samples;

and the output module is used for outputting a detection result, and the detection result is used for indicating whether the target process parameters in the sample to be detected are abnormal or not.

9. The apparatus of claim 8, wherein the obtaining module is further configured to:

obtaining a plurality of historical qualified samples, wherein each historical qualified sample comprises a plurality of parameter values of the target process parameter;

the determining module is further configured to: respectively determining a distribution curve of the target process parameter in each historical qualified sample according to a plurality of parameter values of the target process parameter in each historical qualified sample; and the number of the first and second groups,

and determining a historical distribution curve corresponding to the target process parameter according to the distribution curve of the target process parameter in each historical qualified sample.

10. The apparatus of claim 9, wherein the determining module is specifically configured to:

and determining a central distribution curve of the target process parameter in each historical qualified sample, and taking the central distribution curve as a historical distribution curve corresponding to the target process parameter.

11. The apparatus according to claim 9 or 10, wherein the determining module is specifically configured to:

and determining whether the target process parameters in the sample to be detected are abnormal or not according to the difference between the target distance and the distance between the distribution curve of the target process parameters in the sample to be detected and the historical distribution curve corresponding to the target process parameters.

12. The apparatus of claim 11, wherein the determining module is specifically configured to:

and determining the target distance according to the distance between the distribution curve of the target process parameter in each historical qualified sample and the historical distribution curve corresponding to the target process parameter.

13. The apparatus of claim 12, wherein the determining module is specifically configured to:

respectively determining the distance between the distribution curve of the target process parameter in each historical qualified sample and the historical distribution curve corresponding to the target process parameter to obtain a plurality of candidate distances; and the number of the first and second groups,

and taking the maximum distance in the plurality of candidate distances as the target distance.

14. The apparatus according to any one of claims 8 to 13, wherein the determining module is specifically configured to:

determining an empirical distribution function of the target process parameters in the sample to be detected according to the plurality of parameter values; and the number of the first and second groups,

and smoothing the empirical distribution function to obtain a distribution curve of the target process parameters in the sample to be detected.

15. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-4.

17. A process parameter detection method is characterized by comprising the following steps:

obtaining a sample to be detected, wherein the sample to be detected comprises a plurality of parameter values of target process parameters;

determining a distribution curve of the target process parameters in the sample to be detected according to the plurality of parameter values;

determining whether the target process parameters in the sample to be detected are abnormal or not according to the distribution curve of the target process parameters in the sample to be detected and a historical distribution curve corresponding to the target process parameters, wherein the historical distribution curve is obtained based on historical qualified samples;

and outputting a detection result, wherein the detection result is used for indicating whether the target process parameters in the sample to be detected are abnormal or not.

Images