WO2024128447A1

WO2024128447A1 - Method and electronic device for estimating state of health of a battery in an electronic device

Info

Publication number: WO2024128447A1
Application number: PCT/KR2023/010144
Authority: WO
Inventors: Subramanian Brahmadathan Swernath; Samarth Agarwal; Krishnan Seethalakshmy Hariharan; Sangheon Lee
Original assignee: Samsung Electronics Co., Ltd.
Priority date: 2022-12-12
Filing date: 2023-07-14
Publication date: 2024-06-20

Abstract

A method for estimating state-of-health (SOH) of a battery in an electronic device, is disclosed. The method includes obtaining a plurality of temperature values and a plurality of voltage values, during at least one of a charging and discharging cycle of the battery The method further includes determining an average temperature value for at least part of the plurality of temperature values corresponding a voltage range from among the plurality of voltage values The method further includes estimating a real-time SOH value of the battery based on the average temperature value and the voltage range using an artificial intelligence (AI) model. The AI model is trained to output a SOH value with a temperature value of the battery and a corresponding voltage range of the battery as inputs.

Description

METHOD AND ELECTRONIC DEVICE FOR ESTIMATING STATE OF HEALTH OF A BATTERY IN AN ELECTRONIC DEVICE

The present invention generally relates to a battery management system (BMS), and more specifically relates to a method and a system for estimating a state-of-health (SOH) of a battery in an electronic device.

In general, lithium-ion battery generally outperforms lead-acid battery in many ways. The lithium-ion battery is utilized extensively in a variety of applications, such as, electric vehicles (EVs) and smartphones. For instance, one of the most crucial requirements of a battery-powered electric car is range estimation (e.g., 100 kilometers) based on a state of charge (SoC) and state of health (SoH) of the lithium-ion battery. The lithium-ion battery is more lightweighted, more effective, charges very quickly, and lasts longer. However, some conditions can damage the lithium-ion battery. Further, the lithium-ion battery comprises a battery management system (BMS) to avoid these damaging conditions. The BMS is a group of circuits that controls and manages every aspect of battery's performance. The BMS is often constructed as a separate circuit board that is linked to the battery. Metal oxide field effect transistors (MOSFETs) or other solid-state switches, sensors, and a microcontroller are all components of the BMS. The BMS continuously assesses the lithium-ion battery's fundamental condition (e.g., cell voltage, cell temperature, etc.). Most crucially, the BMS prevents the lithium-ion battery from operating outside of safety parameters of the lithium-ion battery.

The state of charge (SoC) and state of health (SoH) are two important parameters for the lithium-ion battery. The BMS can prevent each cell in the battery from overcharging or over-discharging and extend life of the battery with precise estimates of the SoC and the SoH. As illustrated in Figure 1, the existing system estimates the SOH of the lithium-ion battery in response to measurement of the SoC of the battery, where the SOC is estimated and not directly measured. At a first block (Step-1), a model (such as a mathematical model, an AI model, a machine learning model, etc.) estimates the SOC based on input(s) received, as depicted below in equation 1:

SOC = f(

), error in "y or SOC" increases non-linearly; (1)

Where voltage (

) and current (

) re part of the input(s) that were received from the BMS. "V" indicates voltage and "

" indicates an error in the voltage or said fluctuation in the voltage. "I" indicates current and "

" indicates an error in the current or said fluctuation in the current. Due to the nonlinear nature of the current and voltage functions, as shown in the first graph of Figure 1, step 1 of the model results in an inaccurate measurement of the SoC. Additionally, as depicted in equation 2, the SoC is an integral of current with respect to time. As a result, the SOC may be dependent on previous measurements made at the time in question, which may lead to measurement error or inaccuracy.

SOC = SOC0 +

(2)

At a second block, a model (such as a mathematical model, an AI model, a machine learning model, etc.) estimates the SOH based on an input(s) received, as depicted in below equation 3:

SOH = g(SOC(I, V),

,

) (3)

where

and

are part of the input(s) that were received from the model of step-1. Where "

" indicates an error in the SOC or said fluctuation in the SOC. At the step-2, voltage (

) is directly received without any mathematical reformulation from step-1. As shown in the second graph of Figure 1, the estimated SOH contains an error or does not indicate real-time value because the measurement error or inaccuracy is present in the step-2 input. Further, the existing system may require estimation or knowledge of non-measurable variables or parameter tuning for estimating the SOH. Examples of the parameter include, but not limited to, hyperparameter (loss function/ optimizer) that is used for training the model or device-specific parameter. Thus, it is desired to address the above-mentioned disadvantages or other shortcomings or at least provide a better/more efficient alternative for the estimation of the SOH.

This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention. This summary is neither intended to identify key or essential inventive concepts of the invention nor is it intended for determining the scope of the invention.

According to one embodiment of the present disclosure, a method for estimating state-of-health (SOH) of a battery in an electronic device is disclosed. The method includes monitoring a plurality of temperature values and a plurality of voltage values at each SOH value, during at least one of a charging and discharging cycle of the battery. The method further includes determining, for each SOH value, an average temperature value of the plurality of temperature values across the plurality of voltage values. The method further includes generating an artificial intelligence (AI) model having a correlation of the determined average temperature, the plurality of voltage values, and the corresponding SOH values. The method further includes obtaining a real-time temperature value and a real-time voltage value associated with the battery. The method further includes estimating a real-time SOH value based on the real-time temperature value and the real-time voltage value of the battery based on the generated AI model.

According to one embodiment of the present disclosure, a method for estimating the SOH of the battery in the electronic device is disclosed. The method includes determining one or more parameters directly from a battery management system (BMS) of the battery, wherein the one or more parameters comprise one or more temperature values and one or more voltage values. The method further includes estimating the SOH of the battery based on the one or more determined parameters.

According to one embodiment of the present disclosure, a system for estimating the SOH of the battery in the electronic device is disclosed. The system includes a SOH estimator module coupled with a processor and a memory. The SOH estimator module is configured to monitor a plurality of temperature values and a plurality of voltage values at each SOH value, during at least one of a charging and discharging cycle of the battery. The SOH estimator module is further configured to determine, for each SOH value, an average temperature value of the plurality of temperature values across the plurality of voltage values. The SOH estimator module is further configured to generate an artificial intelligence (AI) model having a correlation of the determined average temperature, the plurality of voltage values, and the corresponding SOH values. The SOH estimator module is further configured to obtain a real-time temperature value and a real-time voltage value associated with the battery. The SOH estimator module is further configured to estimate a real-time SOH value based on the real-time temperature value and the real-time voltage value of the battery based on the generated AI model.

According to one embodiment of the present disclosure, a system for estimating the SOH of the battery in the electronic device is disclosed. The system includes a SOH estimator module coupled with a processor and a memory. The SOH estimator module is configured to determine one or more parameters directly from the BMS of the battery, wherein the one or more parameters comprise one or more temperature values and one or more voltage values. The SOH estimator module is configured to estimate the SOH of the battery based on the one or more determined parameters.

According to one embodiment of the present disclosure, a method for estimating state-of-health (SOH) of a battery in an electronic device is disclosed. The method includes obtaining a plurality of temperature values and a plurality of voltage values, during at least one of a charging and discharging cycle of the battery The method further includes determining an average temperature value for at least part of the plurality of temperature values corresponding a voltage range from among the plurality of voltage values The method further includes estimating a real-time SOH value of the battery based on the average temperature value and the voltage range using an artificial intelligence (AI) model. The AI model is trained to output a SOH value with a temperature value of the battery and a corresponding voltage range of the battery as inputs.

According to one embodiment of the present disclosure, an electronic device for estimating state-of-health (SOH) of a battery in the electronic device is disclosed. The electronic device includes a memory storing at least one instruction, and at least one processor configured to execute the at least one instruction. The at least one processor is configured to execute the at least one instruction to obtain a plurality of temperature values and a plurality of voltage values, during at least one of a charging and discharging cycle of the battery. The at least one processor is configured to execute the at least one instruction to determine an average temperature value for at least part of the plurality of temperature values corresponding a voltage range from among the plurality of voltage values. The at least one processor is configured to execute the at least one instruction to estimate a real-time SOH value of the battery based on the average temperature value and the voltage range using an artificial intelligence (AI) model. The AI model is trained to output a SOH value with a temperature value of the battery and a corresponding voltage range of the battery as inputs.

According to one embodiment of the present disclosure, a computer-readable recording medium having recorded thereon a program which is executable by a computer processor to perform the method.

To further clarify the advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail in the accompanying drawings.

These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

Figure 1 illustrates a problem scenario of certain existing systems for estimating a state of health (SOH) of a battery in an existing electronic device, according to prior art;

Figure 2 illustrates a block diagram of a disclosed model representing estimating the SOH of a battery in an electronic device, according to an embodiment as disclosed herein;

Figure 3 illustrates a block diagram of an electronic device for estimating the SOH of the battery in the electronic device, according to an embodiment as disclosed herein;

Figures 4A and 4B are flow diagrams illustrating a method for estimating the SOH of the battery in the electronic device, according to an embodiment as disclosed herein;

Figure 5 is a flow diagram illustrating a method for estimating the SOH of the battery in the electronic device, according to an embodiment as disclosed herein; and

Figure 6 illustrates an exemplary graphical representation of one or more parameters for estimating the SOH of the battery in the electronic device, according to an embodiment as disclosed herein.

For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates.

It will be understood by those skilled in the art that the foregoing general description and the following detailed description are explanatory of the invention and are not intended to be restrictive thereof.

Reference throughout this specification to "an aspect", "another aspect" or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrase "in an embodiment", "in one embodiment", "in another embodiment", and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

The terms "comprise", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by "comprises... a" does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.

The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments. The term "or" as used herein, refers to a non-exclusive or unless otherwise indicated. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those skilled in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

As is traditional in the field, embodiments may be described and illustrated in terms of blocks that carry out a described function or functions. These blocks, which may be referred to herein as units or modules or the like, are physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware and software. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The circuits constituting a block may be implemented by dedicated hardware, by a processor (e.g., one or more programmed microprocessors and associated circuitry), or by a combination of dedicated hardware to perform some functions of the block and a processor to perform other functions of the block. Each block of the embodiments may be physically separated into two or more interacting and discrete blocks without departing from the scope of the invention. Likewise, the blocks of the embodiments may be physically combined into more complex blocks without departing from the scope of the invention.

The accompanying drawings are used to help easily understand various technical features and it should be understood that the embodiments presented herein are not limited by the accompanying drawings. As such, the present disclosure should be construed to extend to any alterations, equivalents, and substitutes in addition to those which are particularly set out in the accompanying drawings. Although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.

Further, skilled artisans will appreciate those elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the methods in terms of the most prominent steps involved to help to improve understanding of aspects of the present invention. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

Referring now to the drawings, and more particularly to FIGS. 2 to 6, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments.

Figure 2 illustrates a block diagram of a disclosed model 200 (SOH estimator module of Figure 3) representing estimating the SOH of a battery in an electronic device, according to an embodiment as disclosed herein.

The disclosed model 200 directly monitors temperature and voltage from the BMS at a plurality of SOH values (e.g., SOH = 95.6%, SOH = 93.5%, etc.) during a charging cycle and/or a discharging cycle of the battery to estimate the SOH, as depicted below in equation 4:

SOH = f(

,

) (4)

Where temperature (

) and voltage (

) are part of the input(s) that were received from the BMS. "V" indicates voltage and "

" indicates an error in the voltage or said fluctuation in the voltage. "T" indicates temperature and "

" indicates an error in the temperature or said fluctuation in the temperature, as shown in graph of the Figure 2. The disclosed model 200 further calculates an average temperature across a plurality of voltage ranges for each of the SOH values. The disclosed model 200 further generates one or more models (e.g., AI model and/or function mapping) to correlate the average temperature, the plurality of voltage ranges, and corresponding SOH values. The disclosed model 200 further estimates the SOH for prevailing temperature and voltage in the battery using the generated AI model and/or function mapping (e.g., nonlinear response surface).

Unlike the existing system, a disclosed method comprises a direct single-step accurate method to estimate the SOH of the battery by mapping change in temperature of the battery in a fixed voltage window, as described in conjunction with Figure 3 to Figure 6. The disclosed method uses measured outputs from the BMS during a standard charging or discharging cycle/process and there are no estimated quantities (e.g., SOC) present in the disclosed method. As a result, the accuracy of SOH estimation improves because the disclosed method is based on a direct mapping/function/model. Further, as the disclosed method estimates the SOH in a real-time with a minimal memory requirement of an electronic device using one or more models (e.g., function mapping and/or a direct mapping and/or a lightweight neural network (AI model)) In other words, the disclosed approach does not require the exclusive usage of AI/ML models in order to estimate the SOH in real-time.

Figure 3 illustrates a block diagram of an electronic device 300 for estimating the SOH of the battery 350 in the electronic device 300, according to an embodiment as disclosed herein. Examples of the electronic device 300 may include, but not limited to, a smartphone, a tablet computer, a Personal Digital Assistance (PDA), an Internet of Things (IoT) device, a wearable device, and any other such device including a battery/BMS as discussed throughout the disclosure.

In an embodiment, the electronic device 300 comprises a system 301. The system 301 may include a memory 310, a processor 320, a communicator 330, a SOH estimator module 340, and a battery 350.

In an embodiment, the system 301 may be outside the electronic device 300, and/or various hardware components of the electronic device 300 may be located in one or more electronic devices.

The memory 310 stores instructions to be executed by the processor 320 for estimating the SOH of the battery 350 in the electronic device 300, as discussed throughout the disclosure. The memory 310 may include non-volatile storage elements. Examples of such non-volatile storage elements may include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In addition, the memory 310 may, in some examples, be considered a non-transitory storage medium. The term "non-transitory" may indicate that the storage medium is not embodied in a carrier wave or a propagated signal. However, the term "non-transitory" should not be interpreted that the memory 310 is non-movable. In some examples, the memory 310 can be configured to store larger amounts of information than the memory 310. In certain examples, a non-transitory storage medium may store data that can, over time, change (e.g., in Random Access Memory (RAM) or cache). The memory 310 can be an internal storage unit, or it can be an external storage unit of the electronic device 300, a cloud storage, or any other type of external storage.

The processor 320 communicates with the memory 310, the communicator 330, and the SOH estimator module 340. The processor 320 is configured to execute instructions stored in the memory 310 and to perform various processes to estimate the SOH of the battery 350 in the electronic device 300, as discussed throughout the disclosure. The processor 320 may include one or a plurality of processors, maybe a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and/or an Artificial intelligence (AI) dedicated processor such as a neural processing unit (NPU).

The communicator 330 is configured for communicating internally between internal hardware components and with external devices (e.g., server) via one or more networks (e.g., Radio technology). The communicator 330 includes an electronic circuit specific to a standard that enables wired or wireless communication.

The SOH estimator module 340 is implemented by processing circuitry such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like.

In an embodiment, the SOH estimator module 340 includes a detector module 341, a profile module 342, a smoothing filter module 343, a correlator module 344, and a SOH indicator module 345. In an embodiment, the memory 310 may include the SOH estimator module 340. The processor 320 may executes at least one instruction stored in the memory 310. The at least one instruction may be corresponding to functions of the SOH estimator module 340.

In one embodiment, the detector module 341 monitors a plurality of temperature values and a plurality of voltage values at each SOH value, during at least one of a charging and discharging cycle of the battery 350. The detector module 341 directly measures the plurality of temperature values and the plurality of voltage values from a battery management system (BMS) of the battery. In one embodiment, the detector module 341 determines, for each SOH value, an average temperature value of the plurality of temperature values across the plurality of voltage values. Based on the average temperature value of the plurality of temperature values across the plurality of voltage values, the profile module 342 generates a temperature-voltage profile prior to the determination of the average temperature value across the plurality of voltage values using a filter (e.g., smoothing filter module 343).

In one embodiment, the detector module 341 obtains a plurality of temperature values and a plurality of voltage values, during at least one of a charging and discharging cycle of the battery. In one embodiment, the detector module 341 determines an average temperature value for at least part of the plurality of temperature values corresponding a voltage range from among the plurality of voltage values.

In one embodiment, the correlator module 344 generates an artificial intelligence (AI) model having a correlation of the determined average temperature, the plurality of voltage values, and the corresponding SOH values. In one embodiment, the detector module 341 obtains a real-time temperature value and a real-time voltage value associated with the battery using the generated AI model. Based on the obtained real-time temperature value and the obtained real-time voltage, the SOH indicator module 345 estimates a real-time SOH value based on the real-time temperature value and the real-time voltage value of the battery based on the generated AI model.

In one embodiment, the SOH indicator module 345 estimates a real-time SOH value of the battery based on the average temperature value and the voltage range using an artificial intelligence (AI) model.

In one embodiment, the detector module 341 determines one or more temperature values and one or more voltage values during one or more charging/ discharging cycles of the battery 350 at each SOH value of the battery 350 from a battery management system (BMS) of the battery 350, as shown in Figure 6. Based on the determined one or more temperature values and one or more voltage values, the detector module 341 determines one or more average temperature values of the one or more temperature values across a plurality of voltage values associated with the one or more voltage values for each SOH value to estimate the SOH of the battery 350. The detector module 341 sends the determined data (i.e., temperature value(s), voltage value(s), and average temperature value(s)) to the profile module 342 for further processing associated with the estimation of the SOH of the battery 350 in the electronic device 300.

Based on one or more average temperature values across the plurality of voltage values, the profile module 342 generates temperature-voltage data (e.g., graph) for the one or more cycles (i.e., charging/discharging cycle) of the battery 350 at each SOH value of the battery 350 based on the one or more average temperature values across the plurality of voltage values, as described in conjunction with Figure 6. In one or more embodiments, the AI model scales the one or more determined temperature values based on an ambient condition and maps one or more scaled temperature values to corresponding one or more determined voltage values. The produced temperature-voltage data contains noise. To remove the noise, the profile module 342 sends the generated temperature-voltage data to the smoothing filter module 343. The smoothing filter module 343 uses a filter (e.g., moving average filter or equivalent), function mapping (e.g., non-linear regression model or AI model or a surface fitting), and/or a smoothing mechanism (any variation of finite impulse response (FIR) filter (e.g., Savgol filter)), to remove the noise from the generated temperature-voltage data and generates smooth temperature-voltage data. The smoothing filter module 343 sends the smooth temperature-voltage data to the correlator module 344 for further processing associated with the estimation of the SOH of the battery 350 in the electronic device 300.

Upon receiving the smooth temperature-voltage data, the correlator module 344 splits the smooth temperature-voltage data into multiple segments of one or more fixed voltage values and the one or more average temperature values. The correlator module 344 then passes multiple segments into one or more models (e.g., an artificial intelligence (AI) model, a function mapping, and a machine learning (ML) model) of the electronic device 300 to correlate the one or more average temperature values, the plurality of voltage values, and corresponding SOH values, as described in conjunction with Figure 6. The correlator module 344 then sends data associated with correlation to the SOH indicator module 345 for further processing associated with the estimation of the SOH of the battery 350 in the electronic device 300.

Based on the correlation data, the SOH indicator module 345 estimates the SOH of the battery 350. The SOH indicator module 345 displays the estimated SOH on a display of the electronic device 300. The display can accept user　inputs and may include a Liquid Crystal Display (LCD), a Light Emitting Diode (LED), an Organic Light Emitting Diode (OLED), or another type of display.

In one embodiment, the electronic device 300 sends the one or more determined parameters to at least one server (not shown in Figure 3), wherein the at least one server utilizes one or more models (e.g., AI model/ function mapping/ ML model) to estimate the SOH of the battery 350. Then, the electronic device 300 receives the estimated SOH from the at least one server, wherein the estimated SOH is displayed on a screen of the electronic device 300.

A function associated with the various components of the electronic device 300 may be performed through the non-volatile memory, the volatile memory, and the processor 320. One or a plurality of processors controls processing of input data in accordance with a predefined operating rule or AI model stored in the non-volatile memory and/or the volatile memory. The predefined operating rule or AI model may be provided through training or learning. Here, being provided through learning means that, by applying a learning algorithm to a plurality of learning data, a predefined operating rule or AI model of the desired characteristic is determined. The learning may be performed in a device itself in which AI according to an embodiment is performed, and/or may be implemented through a separate server/system. The learning algorithm is a method for training a predetermined target device (for example, a robot) using the plurality of learning data to cause, allow, or control the target device to decide or predict. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

The AI model may consist of a plurality of neural network layers. Each layer has a plurality of weight values and performs a layer operation through a calculation of a previous layer and an operation of a plurality of weights. Examples of neural networks include, but are not limited to, convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), restricted Boltzmann Machine (RBM), deep belief network (DBN), bidirectional recurrent deep neural network (BRDNN), generative adversarial networks (GAN), and deep Q-networks.

Although Figure 3 shows various hardware components of the electronic device 300, but it is to be understood that other embodiments are not limited thereon. In other embodiments, the electronic device 300 may include less or more number of components. Further, labels or names of the components are used only for illustrative purpose and does not limit the scope of the invention. One or more components can be combined to perform the same or substantially similar functions to estimate the SOH of the battery 350 in the electronic device 300.

Figures 4A and 4B are flow

diagrams illustrating methods

400, 450 for estimating the SOH of the battery 350 in the electronic device 300, according to an embodiment as disclosed herein.

Referring to Figure 4A, at step 401, the method 400 includes monitoring a plurality of temperature values and a plurality of voltage values at each SOH value, during at least one of a charging and discharging cycle of the battery 350, as described in conjunction with Figure 6. In one embodiment, the monitoring comprises directly measuring the plurality of temperature values and the plurality of voltage values from the BMS of the battery 350.

At step 402, the method 400 includes determining, for each SOH value, an average temperature value of the plurality of temperature values across the plurality of voltage values. In one embodiment, determining an average temperature value across the plurality of voltage values for each SOH value comprises generating a temperature-voltage profile prior to the determination of the average temperature value across the plurality of voltage values using a filter, as described in conjunction with Figure 6.

At step 403, the method 400 includes generating an artificial intelligence (AI) model having a correlation of the determined average temperature, the plurality of voltage values, and the corresponding SOH values, as described in conjunction with Figure 6.

At step 404, the method 400 includes obtaining a real-time temperature value and a real-time voltage value associated with the battery 350.

At step 405, the method 400 includes estimating a real-time SOH value based on the real-time temperature value and the real-time voltage value of the battery 350 based on the generated AI model.

Referring to Figure 4B, at step 451, the method 450 includes obtaining a plurality of temperature values and a plurality of voltage values, during at least one of a charging and discharging cycle of the battery 350, as described in conjunction with Figure 6. In one embodiment, the obtaining comprises directly measuring the plurality of temperature values and the plurality of voltage values from the BMS of the battery 350.

At step 452, the method 450 includes determining an average temperature value for at least part of the plurality of temperature values corresponding a voltage range from among the plurality of voltage values. In one embodiment, determining the average temperature value comprises generating a temperature-voltage profile using a filter prior to the determination of the average temperature value, as described in conjunction with Figure 6.

At step 453, the method 450 includes estimating a real-time SOH value of the battery 350 based on the average temperature value and the voltage range using an artificial intelligence (AI) model. In one embodiment, the AI model may be trained to output a SOH value with a temperature value of the battery (350) and a corresponding voltage range of the battery (350) as inputs.

Figure 5 is a flow diagram illustrating a method 500 for estimating the SOH of the battery 350 in the electronic device 300, according to another embodiment as disclosed herein.

At step 501, the method 500 includes determining one or more parameters directly from the BMS of the battery 350, wherein the one or more parameters comprise one or more temperature values and one or more voltage values, which relates to step 401 of Figure 4A and step 451 of Figure 4B.

In one embodiment, determining the one or more parameters directly from the BMS at step 501 comprises determining one or more temperature values during one or more cycles of the battery 350 at each SOH value of the battery 350, wherein the one or more cycles comprise a charging cycle and a discharging cycle, and the one or more temperature values are associated with the one or more parameters that are directly determined from the BMS, which also relates to step 401 of Figure 4A and step 451 of Figure 4B. Further, the step 501 may include determining one or more voltage values during one or more cycles of the battery 350 at each SOH value of the battery 350, wherein the one or more cycles comprise the charging cycle and the discharging cycle, and the one or more voltage values are associated with the one or more parameters that are directly determined from the BMS, which also relates to step 401 of Figure 4A and step 451 of Figure 4B. Furthermore, the step 501 may include determining one or more average temperature values of the one or more temperature values across the plurality of voltage values associated with the one or more voltage values for each SOH value to estimate the SOH of the battery 350, which also relates to step 402 of Figure 4A and step 452 of Figure 4B.

Additionally, the step 501 may include determining the real-time temperature value and the real-time voltage value associated with the battery 350 based on the one or more temperature values, the one or more voltage values, and the one or more average temperature values for each SOH value to estimate the SOH of the battery 350, which also relates to step 404 of Figure 4A and step 452 of Figure 4B.

Additionally, the step 501 may include generating temperature-voltage data for the one or more cycles of the battery 350 at each SOH value of the battery 350 based on the one or more average temperature values across the plurality of voltage values, which relates to step 402 of Figure 4A and step 452 of Figure 4B.

Additionally, the step 501 may include generating smooth temperature-voltage data for the one or more cycles of the battery 350 at each SOH value of the battery 350 based on the one or more average temperature values across the plurality of voltage values using the filter, wherein the smooth temperature-voltage data is split into multiple segments of one or more fixed voltage values and the one or more average temperature values, which relates to step 402 of Figure 4A and step 452 of Figure 4B.

At step 502, the method 500 includes estimating the SOH of the battery 350 based on the one or more determined parameters, which relates to step 405 of Figure 4A and step 453 of Figure 4B.

In one embodiment, the method 500 includes correlating the one or more average temperature values, the plurality of voltage values, and corresponding SOH values by utilizing one or more models of the electronic device 300 to estimate the SOH of the battery 350, wherein the one or more models of the electronic device 300 comprise the artificial intelligence (AI) model, the function mapping, and the machine learning (ML) model, which relates to step 403 of Figure 4A and step 453 of Figure 4B.

Additionally, the step 502 may include receiving multiple segments of one or more fixed voltage values and the one or more average temperature values, which relates to step 403 of Figure 4A and step 453 of Figure 4B.

Additionally, the step 502 may include passing the received multiple segments into the one or more models of the electronic device 300 to estimate one or more SOH values of the battery 350, which relates to step 403 of Figure 4A and step 453 of Figure 4B.

Additionally, the step 502 may include averaging the estimated one or more SOH values to estimate the SOH of the battery 350, which relates to step 403 of Figure 4A and step 453 of Figure 4B.

Additionally, the step 502 may include estimating the SOH of the battery 350 based on the correlation of current temperature and voltage in the battery 350, which relates to step 405 of Figure 4A and step 453 of Figure 4B.

Additionally, the step 502 may include estimating the SOH is independent of a state of charge (SOC) of the battery 350, which relates to step 405 of Figure 4A and step 453 of Figure 4B.

Additionally, the step 502 may include estimating the SOH is independent of a partial charging condition, a partial discharging condition, an initial charging condition, a full charging condition, an ambient condition, a form factor of the battery 350, an abnormal temperature variation during charging, and an extension of the battery 350, which relates to step 405 of Figure 4A and step 453 of Figure 4B.

Additionally, the step 502 may include scaling the one or more determined temperature values based on an ambient condition, which relates to step 405 of Figure 4A and step 453 of Figure 4B. The method 500 further includes mapping the one or more scaled temperature values to corresponding one or more determined voltage values by utilizing one or more models of the electronic device to estimate the SOH of the battery 350, which relates to step 405 of Figure 4A and step 453 of Figure 4B. The one or more models of the electronic device 300 comprise the AI model, the function mapping, and the ML model.

Additionally, the step 502 may include sending the one or more determined parameters to at least one server, wherein the at least one server utilizes one or more models to estimate the SOH of the battery 350 and wherein the one or more models comprise an artificial intelligence (AI) model, a function mapping, and a machine learning (ML) model. The method 500 further includes receiving the estimated SOH from the at least one server, wherein the estimated SOH is displayed on a screen of the electronic device, which relates to step 405 of Figure 4A and step 453 of Figure 4B.

Figure 6 illustrates an exemplary graphical representation of one or more parameters for estimating the SOH of the battery 350 in the electronic device 300, according to an embodiment as disclosed herein.

At first graph 601, the electronic device 300 determines one or more temperature values and one or more voltage values during one or more cycles of the battery 350 at each SOH value of the battery 350, which relates to step 401 of Figure 4A and step 451 of Figure 4B. The electronic device 300 further determines one or more average temperature values of the one or more temperature values across the plurality of voltage values associated with the one or more voltage values for each SOH value to estimate the SOH of the battery 350, which relates to step 402 of Figure 4A and step 452 of Figure 4B. For example, the one or more average temperature values (

T) represented on x-axis of the graph 601 and the plurality of voltage values represented on y-axis of the graph 601. The graph 601 includes a "first curve 601a", which represents average temperature-voltage data for the battery's first SOH value (98.4%) at 100 charging/discharging cycles, a "second curve 601b", which represents average temperature-voltage data for the battery's second SOH value (95.6%) at 200 charging/discharging cycles, and a "third curve 601c", which represents average temperature-voltage data for the battery's third SOH value (93.5%) at 400 charging/discharging cycles. The electronic device 300 further generates smooth temperature-voltage data for the one or more cycles of the battery 350 at each SOH value of the battery 350 based on the one or more average temperature values across the plurality of voltage values using the filter, wherein the smooth temperature-voltage data is split into multiple segments of one or more fixed voltage values and the one or more average temperature values. In a fixed voltage range, for example, 4.18 to 4.2 V, the electronic device 300 determines one or more average temperature values for the first curve 601a/second curve 601b/third curve 601c, where each curve corresponds to a different SOH. The determined/learned values are generated in a subsequent voltage window, for example, 4.2 to 4.22 V at multiple SOH values corresponding to the three curves, in a manner similar to the preceding step.

At second graph 602, the electronic device 300 utilizes one or more models of the electronic device 300, which relates to step 403 of Figure 4A and step 453 of Figure 4B, to receive the multiple segments of one or more fixed voltage values and the one or more average temperature values. Upon receiving the multiple segments, the electronic device 300 passes the received multiple segments into the one or more models of the electronic device 300 to correlate the one or more average temperature values, the plurality of voltage values, and corresponding SOH values. In this case, the data is represented by a contour three-dimensional (3D) plot (i.e., temperature, voltage, and SOH). The electronic device 300 continuously monitors the data, for example, every cycle plotting a line(s) and ideally getting a surface 602a or said multiple lines when combined become the surface 602a that indicates various correlations. Where the surface 602a correlates with the interdependence of the SOH vs temperature vs voltage.

At step-603, based upon correlation, the electronic device 300 estimates one or more SOH values, which relates to step 405 of Figure 4A and step 453 of Figure 4B. The electronic device 300 then takes the average of the estimated one or more SOH values from the multiple segments of one or more fixed voltage values and the one or more average temperature values. The electronic device 300 then notifies the current SOH/ real-time SOH value on a display of the electronic device 300.

In one embodiment, the disclosed method is applicable regardless of the ambient conditions. Consider a scenario where SOH estimation from battery 350 charging at various ambient conditions. For example, the battery 350 charged inside an air conditioning (AC) room versus an ambient condition in a hot/cold environment. Existing systems use SOC estimation (derived/calculated quantity) training or do not account for external variations to estimate the SOH, while the disclosed method/system explicitly incorporates an ambient temperature and thus can predict the SOH regardless of external conditions.

In one embodiment, the disclosed method is applicable across various electronic devices. For example, each mobile device has a unique operating current, voltage, and so on. Certain existing systems must be re-trained and re-parameterized using the specific data to estimate the SOH. While the disclosed method/system works across devices by incorporating previously known effect of the battery 350 form factor (surface area & volume) to estimate the SOH. The disclosed method/system does not require re-training depending on the shape/ size of the battery 350 as a form factor is incorporated in a training stage itself and universal across batteries with the same chemical composition.

In one embodiment, the disclosed method is applicable to identify abnormalities of the battery 350. Consider a scenario in which the temperature varies abnormally during charging. For example, degradation causes a change in resistance, which causes the temperature to rise or fall. In this scenario, certain existing systems are incapable of detecting abuse/misuse. While the disclosed method/system directly measures temperature and uses it in SOH estimation, it can detect abnormalities without delay, thereby improving safety. Because it is a real-time SOH estimation, the disclosed method/system can also be extended to change charging profiles.

In one embodiment, the disclosed method is applicable during extension of the battery pack. Consider a scenario in which EVs operate in more demanding conditions than mobile phones/smartphones. Because of its location within the pack, each cell in a multi-cell pack used in the EV may have different degradation and external temperature. External factors, for example, can change the temperature of individual cells in a pack during charging and discharging. The disclosed method/system accurately estimates the SOH in the fourth scenario because external variations have been considered in the

T vs

V training at each SOH value.

In one embodiment, the disclosed method consists of a parameterized model, as shown in equation 4, that can be used in conjunction with the surface 602a to predict temperature profile based on any charging or discharging protocol. Furthermore, the surface in 602 can be extended to a scaled temperature, which aids in the prediction of SOH for any ambient conditions.

Several advantages of the disclosed method, for example, are listed below.

Estimating the SOH for any external condition (e.g., ambient conditions).

Increasing accuracy in comparison to certain existing systems. As previously stated, certain existing systems use the SOC to estimate the battery's SOH. Where SOC is an estimated quantity or is not directly measured, and SOC0 is unknown and potentially erroneous (e.g., 1%). The disclosed method/system, on the other hand, uses the voltage and temperature directly from the BMS to generate a SOH value that maps between different voltages and temperatures. Input to the function mapping and/or AI/ML model (artificial neural networks (ANN)), for example, has a minimal measurement error of less than mV and 0.30C. Temperature measurement error is less than 0.30C and voltage measurement error is less than mV.

Raising safety concerns immediately if a significant deviation from the expected is observed.

Estimating the SOH in both cycles (e.g., charging or discharging).

Utilizing input features (e.g., T, V) to trigger changes to other aspects e.g., charging.

Reducing computational load due to direct mapping of measured states; no on-device estimation algorithms are required.

In one embodiment, the disclosed method performs abnormal temperature measurements, that can be used to warn of a probable failure, as per the following equation 4.

Where, Ploss = f (Resistance, Current) and Ploss = I2R. resistance growth is a direct measure of SOH, Temperature rises as the battery ages, and

are material properties and form factors. Once a mapping of SOH to temperature vs Voltage curve has been generated, it can be extended to any battery. The disclosed method does not necessitate re-parameterization.

In one embodiment of the present disclosure, a method for estimating state-of-health (SOH) of a battery in an electronic device is disclosed. The method includes obtaining a plurality of temperature values and a plurality of voltage values, during at least one of a charging and discharging cycle of the battery The method further includes determining an average temperature value for at least part of the plurality of temperature values corresponding a voltage range from among the plurality of voltage values The method further includes estimating a real-time SOH value of the battery based on the average temperature value and the voltage range using an artificial intelligence (AI) model. The AI model is trained to output a SOH value with a temperature value of the battery and a corresponding voltage range of the battery as inputs.

In one embodiment of the present disclosure, the obtaining comprises directly measuring the plurality of temperature values and the plurality of voltage values from a battery management system (BMS) of the battery.

In one embodiment of the present disclosure, the determining the average temperature value comprises generating a temperature-voltage profile using a filter prior to the determination of the average temperature value.

In one embodiment of the present disclosure, a method for estimating the SOH of the battery in the electronic device is disclosed. The method includes determining one or more parameters directly from a battery management system (BMS) of the battery, wherein the one or more parameters comprise one or more temperature values and one or more voltage values. The method further includes estimating the SOH of the battery based on the one or more determined parameters.

In one embodiment of the present disclosure, determining the one or more parameters directly from the BMS comprises determining one or more temperature values during one or more cycles of the battery, wherein the one or more cycles comprise a charging cycle and a discharging cycle, and the one or more temperature values are associated with the one or more parameters that are directly determined from the BMS. The determining the one or more parameters directly from the BMS comprises determining one or more voltage values during one or more cycles of the battery, wherein the one or more cycles comprise the charging cycle and the discharging cycle, and the one or more voltage values are associated with the one or more parameters that are directly determined from the BMS. The determining the one or more parameters directly from the BMS comprises determining one or more average temperature values of the one or more temperature values corresponding to one or more voltage ranges from among the one or more voltage values to estimate the SOH of the battery.

In one embodiment of the present disclosure, determining the one or more parameters directly from the BMS comprises generating temperature-voltage data for the one or more cycles of the battery based on the one or more average temperature values corresponding to the one or more voltage ranges. The determining the one or more parameters directly from the BMS comprises generating smooth temperature-voltage data for the one or more cycles of the battery using a filter based on the one or more average temperature values, wherein the smooth temperature-voltage data is split into multiple segments of one or more fixed voltage ranges and the one or more average temperature values.

In one embodiment of the present disclosure, estimating the SOH of the battery comprises correlating the one or more average temperature values, the one or more voltage ranges, and corresponding SOH values by utilizing one or more models of the electronic device to estimate the SOH of the battery, wherein the one or more models of the electronic device comprise an artificial intelligence (AI) model, a function mapping, and a machine learning (ML) model. The estimating the SOH of the battery comprises estimating the SOH of the battery based on the correlation of current temperature and voltage in the battery.

In one embodiment of the present disclosure, utilizing one or more models of the electronic device to estimate the SOH of the battery comprises receiving the multiple segments of one or more fixed voltage ranges and the one or more average temperature values. The utilizing one or more models of the electronic device to estimate the SOH of the battery comprises passing the received multiple segments into the one or more models of the electronic device to estimate one or more SOH values of the battery. The utilizing one or more models of the electronic device to estimate the SOH of the battery comprises averaging the estimated one or more SOH values to estimate the SOH of the battery.

In one embodiment of the present disclosure, estimating the SOH is independent of a state of charge (SOC) of the battery.

In one embodiment of the present disclosure, estimating (502) the SOH is independent of a partial charging condition, a partial discharging condition, an initial charging condition, a full charging condition, an ambient condition, a form factor of the battery, an abnormal temperature variation during charging, and an extension of the battery.

In one embodiment of the present disclosure, the method comprises scaling the one or more determined temperature values based on an ambient condition. The method comprises mapping the one or more scaled temperature values to corresponding one or more determined voltage values by utilizing one or more models of the electronic device (300) to estimate the SOH of the battery (350) The one or more models of the electronic device (300) comprise an artificial intelligence (AI) model, a function mapping, and a machine learning (ML) model.

In one embodiment of the present disclosure, the method comprises sending the one or more determined parameters to at least one server, wherein the at least one server utilizes one or more models to estimate the SOH of the battery 350 and wherein the one or more models comprise an artificial intelligence (AI) model, a function mapping, and a machine learning (ML) model. The method comprises receiving the estimated SOH from the at least one server, wherein the estimated SOH is displayed on a screen of the electronic device.

In one embodiment of the present disclosure, an electronic device for estimating state-of-health (SOH) of a battery in the electronic device is disclosed. The electronic device includes a memory storing at least one instruction, and at least one processor configured to execute the at least one instruction. The at least one processor is configured to execute the at least one instruction to obtain a plurality of temperature values and a plurality of voltage values, during at least one of a charging and discharging cycle of the battery. The at least one processor is configured to execute the at least one instruction to determine an average temperature value for at least part of the plurality of temperature values corresponding a voltage range from among the plurality of voltage values. The at least one processor is configured to execute the at least one instruction to estimate a real-time SOH value of the battery based on the average temperature value and the voltage range using an artificial intelligence (AI) model. The AI model is trained to output a SOH value with a temperature value of the battery and a corresponding voltage range of the battery as inputs.

The various actions, acts, blocks, steps, or the like in the flow diagrams may be performed in the order presented, in a different order, or simultaneously. Further, in some embodiments, some of the actions, acts, blocks, steps, or the like may be omitted, added, modified, skipped, or the like without departing from the scope of the invention.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one ordinary skilled in the art to which this invention belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.

While specific language has been used to describe the present subject matter, any limitations arising on account thereto, are not intended. As would be apparent to a person in the art, various working modifications may be made to the method to implement the inventive concept as taught herein. The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment.

The embodiments disclosed herein can be implemented using at least one hardware device and performing network management functions to control the elements.

The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope of the embodiments as described herein.

Claims

A method 450 for estimating state-of-health (SOH) of a battery 350 in an electronic device 300, the method 450 comprising:

obtaining (451) a plurality of temperature values and a plurality of voltage values, during at least one of a charging and discharging cycle of the battery 350;

determining (452) an average temperature value for at least part of the plurality of temperature values corresponding a voltage range from among the plurality of voltage values; and

estimating (453) a real-time SOH value of the battery 350 based on the average temperature value and the voltage range using an artificial intelligence (AI) model, the AI model trained to output a SOH value with a temperature value of the battery 350 and a corresponding voltage range of the battery 350 as inputs.
The method 450 as claimed in claim 1, wherein the obtaining (451) comprises directly measuring the plurality of temperature values and the plurality of voltage values from a battery management system (BMS) of the battery 350.
The method 450 as claimed in any one of claims 1 and 2, wherein the determining (452) the average temperature value comprises:

generating a temperature-voltage profile using a filter prior to the determination of the average temperature value.
A method 500 for estimating state-of-health (SOH) of a battery 350 in an electronic device 300, the method 500 comprising:

determining (501) one or more parameters directly from a battery management system (BMS) of the battery 350, wherein the one or more parameters comprise one or more temperature values and one or more voltage values; and

estimating (502) the SOH of the battery 350 based on the one or more determined parameters.
The method 500 as claimed in claim 4, wherein determining (501) the one or more parameters directly from the BMS comprises:

determining one or more temperature values during one or more cycles of the battery 350, wherein the one or more cycles comprise a charging cycle and a discharging cycle, and the one or more temperature values are associated with the one or more parameters that are directly determined from the BMS;

determining one or more voltage values during one or more cycles of the battery 350, wherein the one or more cycles comprise the charging cycle and the discharging cycle, and the one or more voltage values are associated with the one or more parameters that are directly determined from the BMS; and

determining one or more average temperature values of the one or more temperature values corresponding to one or more voltage ranges from among the one or more voltage values to estimate the SOH of the battery 350.
The method 500 as claimed in claim 5, wherein determining (501) the one or more parameters directly from the BMS comprises:

generating temperature-voltage data for the one or more cycles of the battery 350 based on the one or more average temperature values corresponding to the one or more voltage ranges; and

generating smooth temperature-voltage data for the one or more cycles of the battery 350 using a filter based on the one or more average temperature values, wherein the smooth temperature-voltage data is split into multiple segments of one or more fixed voltage ranges and the one or more average temperature values.
The method 500 as claimed in any one of claims 5 and 6, wherein estimating (502) the SOH of the battery 350 comprises:

correlating the one or more average temperature values, the one or more voltage ranges, and corresponding SOH values by utilizing one or more models of the electronic device 300 to estimate the SOH of the battery 350, wherein the one or more models of the electronic device 300 comprise an artificial intelligence (AI) model, a function mapping, and a machine learning (ML) model; and

estimating the SOH of the battery 350 based on the correlation of current temperature and voltage in the battery 350.
The method 500 as claimed in claim 7, wherein utilizing one or more models of the electronic device 300 to estimate the SOH of the battery 350 comprises:

receiving the multiple segments of one or more fixed voltage ranges and the one or more average temperature values;

passing the received multiple segments into the one or more models of the electronic device 300 to estimate one or more SOH values of the battery 350; and

averaging the estimated one or more SOH values to estimate the SOH of the battery 350.
The method 500 as claimed in any one of claims 4 to 8, wherein estimating (502) the SOH is independent of a state of charge (SOC) of the battery 350.
The method 500 as claimed in any one of claims 4 to 9, wherein estimating (502) the SOH is independent of a partial charging condition, a partial discharging condition, an initial charging condition, a full charging condition, an ambient condition, a form factor of the battery 350, an abnormal temperature variation during charging, and an extension of the battery 350.
The method 500 as claimed in any one of claims 5 to 8, comprising:

scaling the one or more determined temperature values based on an ambient condition; and

mapping the one or more scaled temperature values to corresponding one or more determined voltage values by utilizing one or more models of the electronic device 300 to estimate the SOH of the battery 350, wherein the one or more models of the electronic device 300 comprise an artificial intelligence (AI) model, a function mapping, and a machine learning (ML) model.
The method 500 as claimed in any one of claims 4 to 11, comprising:

sending the one or more determined parameters to at least one server, wherein the at least one server utilizes one or more models to estimate the SOH of the battery 350 and wherein the one or more models comprise an artificial intelligence (AI) model, a function mapping, and a machine learning (ML) model; and

receiving the estimated SOH from the at least one server, wherein the estimated SOH is displayed on a screen of the electronic device 300.
An electronic device 300 for estimating state-of-health (SOH) of a battery 350 in the electronic device 300, the electronic device 300 comprising:

a memory 310 storing at least one instruction; and

at least one processor 320 configured to execute the at least one instruction to:

obtain a plurality of temperature values and a plurality of voltage values, during at least one of a charging and discharging cycle of the battery 350;

determine an average temperature value for at least part of the plurality of temperature values corresponding a voltage range from among the plurality of voltage values; and

estimate a real-time SOH value of the battery 350 based on the average temperature value and the voltage range using an artificial intelligence (AI) model, the AI model trained to output a SOH value with a temperature value of the battery 350 and a corresponding voltage range of the battery 350 as inputs.
The electronic device 300 as claimed in claim 13, wherein to obtain, at least one processor 320 is configured to execute the at least one instruction to directly measure the plurality of temperature values and the plurality of voltage values from a battery management system (BMS) of the battery 350.
The electronic device 300 as claimed in any one of claims 13 and 14, wherein to determine the average temperature value, the at least one processor 320 is configured to execute the at least one instruction to:

generate a temperature-voltage profile using a filter prior to the determination of the average temperature value.