Fault diagnosis method, apparatus, medium, and equipment based on charging data

Abstract

We provide fault diagnosis methods, devices, media, and equipment based on charging data. [Solution] By collecting charging data during the charging process, extracting static and time-series features from the charging data, inputting the static features into a support vector machine model to obtain a first failure probability, inputting the time-series features into a long short-term memory network to obtain a second failure probability, and performing weighted addition based on the first and second failure probabilities to obtain an overall reliability score, the accuracy of fault diagnosis is improved by collecting charging data in real time during the charging process, extracting static and time-series features therein, using a support vector machine model and a long short-term memory network to identify the static and time-series features respectively to obtain a first and second failure probability, and combining the first and second failure probabilities to obtain a reliability score for charging failures.

Description

TECHNICAL FIELD

[0001] The present invention relates to the field of charging monitoring technology, and more specifically, relates to a fault diagnosis method, apparatus, medium and device based on charging data.

BACKGROUND ART

[0002] Electric vehicles have rapidly become widespread in recent years due to the advantages of low environmental load, cleanness and energy saving. Along with this, charging facilities for electric vehicles, as important components in the popularization process, have developed rapidly. The number and usage frequency of charging piles, which are the main charging devices for electric vehicles, are also increasing rapidly. However, during the charging process, charging faults may occur for various reasons, causing charging abnormalities and further seriously affecting charging safety. Therefore, it is required to perform fault diagnosis on the charging process of electric vehicles.

PRIOR ART DOCUMENTS

PATENT DOCUMENTS

[0003]

PATENT DOCUMENT 1

NON-PATENT DOCUMENTS

[0004]

NON-PATENT DOCUMENT 1

SUMMARY OF THE INVENTION

PROBLEMS TO BE SOLVED BY THE INVENTION

[0005] Conventional fault diagnosis techniques for the charging process primarily determined the presence or absence of faults based on static parameters acquired during the charging process by sensors or controllers, such as charging current or charging voltage. However, in actual charging processes, excessive charging current can lead to a rapid temperature rise, potentially causing safety accidents. Furthermore, predicting faults in advance is difficult using only static parameters. Therefore, there is a need to provide a method that can predict charging faults quickly and accurately. [Means for solving the problem]

[0006] To solve the above technical problems, the present invention is proposed. Embodiments of the present invention provide a method, apparatus, medium, and device for diagnosing faults based on charging data.

[0007] According to one aspect of the present invention, a fault diagnosis method based on charging data is provided, which includes: collecting charging data during the charging process; extracting static features and time-series features from the charging data; inputting the static features into a support vector machine model to calculate a first failure probability; inputting the time-series features into a long short-term memory network to calculate a second failure probability; and obtaining an overall reliability score by performing weighted addition based on the first and second failure probabilities, wherein the frequency of collecting the charging data is set according to the charging state of the rechargeable battery, the overall reliability score indicates the reliability of the presence of a fault in the current charging state, the weight of the first failure probability has a positive correlation with the accuracy rate of the support vector machine model, and the weight of the second failure probability has a positive correlation with the accuracy rate of the long short-term memory network.

[0008] According to another aspect of the present invention, a fault diagnosis device based on charging data is provided. The fault diagnosis device comprises a charging data collection module for collecting charging data during the charging process; a data feature extraction module for extracting static features and time-series features from the charging data; a first probability calculation module for inputting the static features into a support vector machine model to calculate a first failure probability; a second probability calculation module for inputting the time-series features into a long short-term memory network to calculate a second failure probability; and a reliability calculation module for calculating an overall reliability score by performing weighted addition based on the first and second failure probabilities. The frequency of collecting the charging data is related to the charging state of the rechargeable battery, the overall reliability score indicates the reliability of the existence of a fault in the current charging state, the weight of the first failure probability has a positive correlation with the accuracy rate of the support vector machine model, and the weight of the second failure probability has a positive correlation with the accuracy rate of the long short-term memory network.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, and the computer program is used to perform any of the above methods.

[0010] According to another aspect of the present invention, an electronic device is provided, comprising a processor and a memory for storing instructions that the processor can execute, wherein the processor is configured to perform any of the above methods. [Effects of the Invention]

[0011] The present invention provides a fault diagnosis method, apparatus, medium, and device based on charging data. It collects charging data during the charging process, sets the frequency of charging data collection according to the charging state of the rechargeable battery, extracts static and time-series features from the charging data, inputs the static features into a support vector machine model to obtain a first failure probability, inputs the time-series features into a long short-term memory network to obtain a second failure probability, performs weighted addition based on the first and second failure probabilities to calculate the overall reliability, and by calculating the overall reliability, the failure rate in the current charging state can be evaluated with high accuracy. The weight of the first failure probability has a positive correlation with the accuracy of the support vector machine model, and the weight of the second failure probability has a positive correlation with the accuracy of the long short-term memory network. Specifically, charging data is collected in real time during the charging process, static and time-series features are extracted, and a support vector machine model and a long short-term memory network are used to identify the static and time-series features, respectively, and calculate the first and second failure probabilities. By combining the first and second failure probabilities, the reliability of the charging failure is obtained, thereby improving the accuracy of fault diagnosis. [Brief explanation of the drawing]

[0012] The above and other objects, features and advantages of the present invention will become clearer by describing embodiments of the invention in more detail with reference to the drawings. The drawings are used to provide a further understanding of embodiments of the present invention, constitute part of the specification, and are used to interpret the invention together with the embodiments of the invention, and do not limit the invention. In the drawings, the same reference numerals usually indicate the same or corresponding members or steps. [Figure 1] This is a flowchart of a fault diagnosis method based on charging data according to an exemplary embodiment of the present invention. [Figure 2] This is a schematic diagram illustrating the configuration of a fault diagnosis device based on charging data according to one exemplary embodiment of the present invention. [Figure 3] This is a configuration diagram of an electronic device according to one exemplary embodiment of the present invention. [Modes for carrying out the invention]

[0013] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the drawings. Those skilled in the art will understand that the embodiments described are only a selection of embodiments of the present invention, not all embodiments, and that the present invention is not limited to the exemplary embodiments described herein.

[0014] Figure 1 is a flowchart of a fault diagnosis method based on charge data according to an exemplary embodiment of the present invention. As shown in Figure 1, the fault diagnosis method based on charge data of this embodiment includes the following steps: In step 110, charging data is collected during the charging process.

[0015] Here, the frequency of collecting charging data is set according to the charge state of the rechargeable battery. In this invention, the charging process of a rechargeable battery is monitored in real time by collecting charging data during the charging process of the rechargeable battery. Here, the frequency of collecting charging data is related to the charge state (SOC) of the rechargeable battery. Specifically, when the SOC of the rechargeable battery is less than 20%, the collection frequency is 1 Hz; when the SOC of the rechargeable battery is between 20% and 80%, the collection frequency is 10 Hz; and when the SOC of the rechargeable battery is greater than 80%, the collection frequency is 1 Hz. In other words, when the SOC of the rechargeable battery is too low or too high (in which case the charging current is usually small), charging data is collected at a low collection frequency, but when the SOC is in the range of 20% to 80% (in which case the charging current is usually large), charging data is collected at a high frequency, thereby improving the monitoring effect.

[0016] In step 120, static and time-series features are extracted from the charging data.

[0017] In this invention, after collecting charging data, static features (e.g., average voltage, extreme temperature, etc.) and time-series features (e.g., voltage fluctuation curve, temperature change trend, etc.) are extracted from the charging data, and based on these features, it is determined whether or not a fault exists in the charging process.

[0018] In step 130, the extracted static features are input into a support vector machine model to calculate a first failure probability.

[0019] In the present invention, the support vector machine model is trained with a plurality of sample data, and the first failure probability can be obtained by inputting the extracted static features.

[0020] In step 140, the extracted time-series features are input into a long short-term memory network (LSTM) to calculate a second failure probability.

[0021] In the present invention, the long short-term memory network is similarly trained with a plurality of sample data, and the second failure probability is obtained by inputting the time-series features.

[0022] In step 150, weighted summation is performed based on the first failure probability and the second failure probability to calculate a comprehensive reliability.

[0023] Here, the comprehensive reliability is an index indicating the reliability that a failure exists in the current charging state. The weight of the first failure probability has a positive correlation with the accuracy rate of the support vector machine model, and the weight of the second failure probability has a positive correlation with the accuracy rate of the long short-term memory network. According to the present invention, the support vector machine model and the long short-term memory network respectively determine the probability that a failure exists in the charging process, the first failure probability and the second failure probability are subjected to weighted summation to obtain the final failure probability (i.e., the comprehensive reliability), the advantages of the two models are complementarily utilized, and the accuracy of failure determination can be improved.

[0024] The fault diagnosis method based on charging data provided by the present invention involves collecting charging data during the charging process, setting the frequency of charging data collection according to the charging state of the rechargeable battery, extracting static and time-series features from the charging data, inputting the static features into a support vector machine model to calculate a first failure probability, inputting the time-series features into a long short-term memory network to calculate a second failure probability, calculating an overall reliability score by weighted addition based on the first and second failure probabilities, the overall reliability score indicates the reliability of failure occurrence in the current charging state, the weight of the first failure probability has a positive correlation with the accuracy rate of the support vector machine model, and the weight of the second failure probability has a positive correlation with the accuracy rate of the long short-term memory network. In other words, the accuracy of fault diagnosis is improved by collecting charging data in real time during the charging process, extracting static and time-series features therein, identifying the static and time-series features using a support vector machine model and a long short-term memory network, calculating the first and second failure probabilities, and obtaining the reliability of charging failures by combining the first and second failure probabilities.

[0025] In one embodiment, the specific implementation method of step 120 may be as follows: The voltage-temperature coupling coefficient and the charge health index are extracted from the charging data. The voltage-temperature coupling coefficient indicates the dynamic relationship between the cell voltage and temperature of the rechargeable battery, and the charge health index indicates the similarity between the current charging curve and the historical reference charging curve.

[0026] This invention provides an index for determining whether or not a fault exists during the charging process by extracting the voltage-temperature coupling coefficient and the charge health index. The voltage-temperature coupling coefficient indicates the dynamic correlation between cell voltage and temperature, while the charge health index represents the similarity between the current charge curve and the hysteretic reference charge curve.

[0027] In one embodiment, the specific implementation method of step 120 described above may be as follows. The formula for calculating the voltage-temperature coupling coefficient is given by the following equation (1). The formula for calculating the charging health index is given by the following equation (2). JPEG2026170837000003.jpg51157

[0028] The present invention calculates the voltage-temperature coupling coefficient and the charge health index, respectively, using the above formula. Here, the range of the voltage-temperature coupling coefficient is [-1, 1]. The voltage-temperature coupling coefficient is used to identify the risk of thermal runaway in a rechargeable battery, and the charge health index is an indicator for evaluating the health of the rechargeable battery. If the charge health index continuously falls below a set threshold, it indicates a degradation in the capacity of the rechargeable battery or an increase in its internal resistance. In such cases, further diagnosis is necessary to determine whether there is a fault in the charging process.

[0029] In one embodiment, the fault diagnosis method based on the charging data described above may further include determining that a fault exists in the current charging state if the difference between the voltage-temperature coupling coefficient at the current time and the voltage-temperature coupling coefficient at the previous time exceeds a preset difference threshold.

[0030] The present invention allows for the extraction of the voltage-temperature coupling coefficient and, based on the change in the coefficient, determining whether there is a risk of thermal runaway in the rechargeable battery. Specifically, it calculates the difference between the voltage-temperature coupling coefficient at the current time and the voltage-temperature coupling coefficient at the previous time. If this difference exceeds a preset difference threshold (i.e., if the voltage-temperature coupling coefficient increases rapidly), it is determined that abnormal heat generation is occurring inside the rechargeable battery, and it is desirable to issue an immediate alarm to avoid a safety accident.

[0031] In one embodiment, the specific implementation method of step 150 described above may be as follows. The formula for calculating the overall reliability is expressed by the following formula (3). JPEG2026170837000004.jpg59156

[0032] This invention integrates the diagnostic results of the support vector machine model and the long short-term memory network by calculating the overall reliability using the above formula, thereby obtaining the final fault diagnosis result, i.e., the final failure probability. A higher overall reliability indicates a higher probability of a fault occurring during the charging process. This invention can further improve the accuracy of fault diagnosis by determining the weights of the two models based on the accuracy rates of the support vector machine model and the long short-term memory network (obtained from the validation dataset).

[0033] The present invention can perform actions based on alarm measures corresponding to a preset failure probability after calculating the overall reliability. For example, the alarm mechanism in the present invention can be designed in five stages: if the overall reliability is less than 30%, no operation is triggered; if the overall reliability is between 30% and 50%, a notification is triggered; if the overall reliability is between 50% and 70%, current limiting charging is triggered; if the overall reliability is between 70% and 90%, power reduction charging is triggered; and if the overall reliability exceeds 90%, a power cut-off operation is triggered.

[0034] In one embodiment, the specific implementation method of step 110 may be as follows: During the charging process, battery data collected by the rechargeable battery and charge pile data collected by the charge pile are acquired, and charging data is generated by matching these data.

[0035] This invention simultaneously collects battery data and charging pile data during the charging process using both a rechargeable battery (e.g., a BMS) and a charging pile, and introduces a data consistency check mechanism. Specifically, it mutually verifies the battery data and charging pile data to confirm that they are within an appropriate range, and performs mutual inspection using the battery data and charging pile data to fill in missing data and remove abnormal values ​​and noise. This improves the reliability of the data. If a discrepancy is found between the battery data and charging pile data during the verification process, it can trigger data recollection or an alarm notification.

[0036] In one embodiment, the specific implementation method of step 110 may be as follows: When the inter-cell voltage difference of the rechargeable battery exceeds a preset voltage threshold, the frequency of collecting charging data is increased.

[0037] This invention collects cell voltages from a rechargeable battery to obtain cell status information. When the voltage difference between cells exceeds a preset voltage threshold, it indicates a large difference in the charge state between cells. In this case, the frequency of charge data collection can be increased (for example, up to 100Hz), thereby improving charging safety.

[0038] Figure 2 is a schematic diagram of the configuration of a fault diagnosis device based on charging data according to an exemplary embodiment of the present invention. As shown in Figure 2, the fault diagnosis device 20 based on charging data comprises a charging data collection module 21 that collects charging data during the charging process, a data feature extraction module 22 that extracts static features and time-series features from the charging data, a first probability calculation module 23 that inputs static features into a support vector machine model to calculate a first failure probability, a second probability calculation module 24 that inputs time-series features into a long short-term memory network to calculate a second failure probability, and a reliability calculation module 25 that calculates an overall reliability score by performing weighted addition based on the first and second failure probabilities. The frequency of charging data collection is set according to the charging state of the rechargeable battery, the overall reliability score indicates the reliability of failure occurrence in the current charging state, the weight of the first failure probability has a positive correlation with the accuracy rate of the support vector machine model, and the weight of the second failure probability has a positive correlation with the accuracy rate of the long short-term memory network.

[0039] The fault diagnosis device based on charging data provided by the present invention collects charging data during the charging process using a charging data collection module 21, where the frequency of charging data collection is set according to the charging state of the rechargeable battery. A data feature extraction module 22 extracts static features and time-series features from the charging data. A first probability calculation module 23 inputs the static features into a support vector machine model to calculate the first failure probability, and a second probability calculation module 24 inputs the time-series features into a long-term short-term memory network to calculate the second failure probability. A reliability calculation module 25 calculates the overall reliability by performing weighted addition based on these first and second failure probabilities. Here, the overall reliability indicates the reliability of failure in the current charging state, the weight of the first failure probability has a positive correlation with the accuracy of the support vector machine model, and the weight of the second failure probability has a positive correlation with the accuracy of the long short-term memory network. In other words, according to the present invention, charging data is collected in real time during the charging process, its static and time-series features are extracted and analyzed, and the static and time-series features are identified using the support vector machine model and the long short-term memory network, respectively, thereby obtaining and combining the first and second failure probabilities, and thereby improving the accuracy of fault diagnosis.

[0040] In one embodiment, the data feature extraction module 22 may be further configured as follows: It extracts the voltage-temperature coupling coefficient and the charge health index from the charging data, where the voltage-temperature coupling coefficient indicates the dynamic relationship between the cell voltage and temperature of the rechargeable battery, and the charge health index indicates the similarity between the current charging curve and the historical reference charging curve.

[0041] In one embodiment, the data feature extraction module 22 may be further arranged as follows. The formula for calculating the voltage-temperature coupling coefficient is given by equation (1) below. JPEG2026170837000005.jpg149159

[0042] In one embodiment, the fault diagnosis device 20 based on the above charging data may be further configured as follows: If the difference between the voltage-temperature coupling coefficient at the current time and the voltage-temperature coupling coefficient at the previous time exceeds a preset difference threshold, it is determined that a fault exists in the current charging state.

[0043] In one embodiment, the confidence calculation module 25 may be further arranged as follows. The formula for calculating the overall confidence is expressed by the following formula (3). JPEG2026170837000006.jpg55154

[0044] In one embodiment, the charging data collection module 21 may be further configured as follows: It acquires charging battery data collected by the charging battery and charging pile data collected by the charging pile during the charging process, and matches these data to generate charging data.

[0045] In one embodiment, the charging data collection module 21 may be further configured as follows: When the voltage difference between the cells of the rechargeable battery exceeds a preset voltage threshold, the frequency of charging data collection is increased.

[0046] The electronic device of an embodiment according to the present invention will be described below with reference to Figure 3. The electronic device may be either one or both of the first and second devices, or a standalone device independent of them, and the standalone device can communicate with the first and second devices and receive input signals collected from them.

[0047] Figure 3 shows a block diagram of an electronic device in an embodiment of the present invention.

[0048] As shown in Figure 3, the electronic device 10 comprises one or more processors 11 and memory 12.

[0049] The processor 11 may be a central processing unit (CPU), or another type of processing unit having data processing capability and / or instruction execution capability, and further, it may be capable of controlling other components in the electronic device 10 to perform a desired function.

[0050] The memory 12 can store one or more computer program products, and the computer program products may include various types of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache). The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored in the computer-readable storage media, and the processor 11 will implement the methods and / or other desired functions according to each embodiment of the present invention described above by executing the program instructions. The computer-readable storage media may also store various other contents, such as input signals, signal components, and noise components.

[0051] In one embodiment, the electronic device 10 may further include an input device 13 and an output device 14, and these components are connected to each other via a bus by a system and / or other connection mechanism (not shown).

[0052] If the electronic device is a standalone device, the input device 13 may be a communication network connector for receiving input signals collected from the first and second devices.

[0053] The input device 13 may further include, for example, a keyboard, a mouse, and the like.

[0054] The output device 14 can output various information to the outside, including specified distance information, direction information, and so on. The output device 14 may include, for example, a display, a speaker, a printer, a communication network, and a remote output device connected thereto.

[0055] Naturally, for the sake of simplification, Figure 3 shows only some of the components of the electronic device 10 related to the present invention, and components such as buses and input / output interfaces are omitted. Furthermore, depending on the specific application, the electronic device 10 may optionally include other appropriate components.

[0056] In addition to the above-described methods and apparatus, embodiments of the present invention may also be computer program products including computer program instructions, where the computer program instructions are executed by a processor, causing the processor to perform steps of the various embodiments of the present invention described in the “Exemplary Methods” section of this specification.

[0057] The computer program product can generate program code that performs operations according to embodiments of the present invention using any combination of one or more programming languages, and the programming languages ​​include object-oriented programming languages ​​such as Java® and C++. It also includes conventional procedural programming languages ​​such as the C language or similar programming languages. The program code may run entirely on a user computing device, partially on a user computing device, as a single independent software package, partially on a user computing device, partially on a remote computing device, or entirely on a remote computing device or server.

[0058] In addition, the embodiments of the present invention may be computer-readable storage media in which computer program instructions are stored, and when these computer program instructions are executed by a processor, the processor performs the steps of the various embodiments of the present invention described in the "Exemplary Methods" section of this specification.

[0059] The computer-readable storage medium may consist of any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any combination thereof. More specific examples (non-exclusive list) of readable storage media include electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0060] The basic principles of the present invention have been explained above with reference to specific examples, but the advantages, superiority, and effects mentioned in the present invention are merely illustrative examples and not limitations. These advantages, superiority, and effects should not be considered essential to each embodiment of the present invention. Furthermore, the specific details disclosed above are merely illustrative and for ease of understanding, and are not limiting, nor do they limit the fact that the present invention must be realized by adopting the above specific details.

[0061] The block diagrams of the devices, apparatus, equipment, and systems according to the present invention are illustrative examples only and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatus, equipment, and systems may be connected, arranged, and configured in any way. As those skilled in the art will recognize, these devices, apparatus, equipment, and systems may be connected, arranged, and configured in any way. Terms such as “equipment,” “includes,” and “have” are open terms meaning “includes, but not limited to,” and can be used interchangeably. The terms “or” and “and” as used herein mean the terms “and / or,” and can be used interchangeably unless explicitly indicated in the context. The term “for example” as used herein means “for example, but not limited to,” and can be used interchangeably.

[0062] Furthermore, in the apparatus, equipment, and method of the present invention, each component or each step can be disassembled and / or reassembled. These disassembly and / or reassembly should be considered equivalent solutions to the present invention.

[0063] The foregoing description of the disclosed embodiments is provided to enable those skilled in the art to create or use this disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the invention. Accordingly, the invention is not limited to the embodiments shown herein, and the broadest scope should be given that is consistent with the principles and novel features disclosed herein.

[0064] The foregoing description is presented for illustrative and explanatory purposes. Furthermore, this description is not intended to limit the embodiments of the present invention to those disclosed herein. While several exemplary embodiments and examples have been described above, those skilled in the art will recognize certain variations, modifications, changes, additions, and subcombinations thereof.

Claims

1. A fault diagnosis method based on charging data performed by a processor, The process of collecting charging data during the charging process, A step of extracting static features and time-series features from the aforementioned charging data, The process involves inputting the aforementioned static features into a support vector machine model to calculate the first failure probability, The process involves inputting the aforementioned time-series features into a long-term short-term memory network to calculate the probability of a second failure, The process includes a step of calculating the overall reliability by performing weighted addition based on the first failure probability and the second failure probability, The frequency of collecting the charging data is related to the charging state of the rechargeable battery, the overall reliability indicates the reliability of the presence of a fault in the current charging state, the weight of the first failure probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second failure probability is positively correlated with the accuracy of the long short-term memory network. The step of extracting static and time-series features from the charging data includes the step of extracting the voltage-temperature coupling coefficient and the charging health index from the charging data, wherein the voltage-temperature coupling coefficient indicates the dynamic relationship between the cell voltage and temperature of the rechargeable battery, and the charging health index indicates the similarity between the current charging curve and the historical reference charging curve. The formula for calculating the voltage-temperature coupling coefficient is expressed by the following formula (1): Here, C ｖｔ This represents the voltage-temperature coupling coefficient, ΔV ｉ ΔT is the voltage change at the i-th sampling point. ｉ This is the temperature change at the i-th sampling point. The formula for calculating the aforementioned charge health index is expressed by the following formula (2): Here, CHI indicates the charge health index, D current This is the current charging curve, D baseline This shows the hysteresis reference charging curve, DTW(D current , D baseline A fault diagnosis method based on charging data, characterized in that ) indicates the similarity distance between the current charging curve and the historical reference charging curve, and MaxLength indicates the maximum length of those curves.

2. The fault diagnosis method based on the aforementioned charging data further, A fault diagnosis method based on charging data according to claim 1, characterized in that it includes determining that a fault exists in the current charging state if the difference between the voltage-temperature coupling coefficient at the current time and the voltage-temperature coupling coefficient at the previous time exceeds a preset difference threshold.

3. The process of calculating the overall reliability by performing weighted addition based on the first and second failure probabilities is as follows: The calculation of the overall reliability, expressed by the following formula (3), Here, m(A) represents the overall reliability, ω ＳＶＭ is the weight of the first failure probability, ω ＬＳＴＭ is the weight of the second failure probability, SVM ｐｒｏｂ is the first failure probability, LSTM ｐｒｏｂ represents the second failure probability, Ａｃｃ SVM stands for the accuracy of a Support Vector Machine model. Ａｃｃ The fault diagnosis method based on charging data according to claim 1, characterized in that LSTM indicates the accuracy rate of the long-term short-term memory network.

4. The step of collecting charging data during the aforementioned charging process is: A step of acquiring battery data collected by the rechargeable battery and charge pile data collected by the charge pile during the charging process, A fault diagnosis method based on charging data according to claim 1, characterized by including a step of matching and acquiring charging data based on the charging battery data and the charging pile data.

5. The step of collecting charging data during the aforementioned charging process is: The fault diagnosis method based on charging data according to claim 1, characterized in that when the voltage difference between cells of the rechargeable battery exceeds a preset voltage threshold, the frequency of collecting the charging data is increased.

6. A fault diagnosis device based on charging data, A charging data collection module that collects charging data during the charging process, A data feature extraction module that extracts static features and time-series features from the aforementioned charging data, A first probability calculation module that inputs the aforementioned static features into a support vector machine model to calculate a first failure probability, A second probability calculation module that inputs the aforementioned time-series features into a long-term short-term memory network to calculate the second failure probability, Includes a reliability calculation module that performs weighted addition based on the first failure probability and the second failure probability to obtain an overall reliability score, The frequency of collecting the aforementioned charging data is set according to the charge status of the rechargeable battery. The aforementioned overall reliability indicates the reliability of the presence of a fault in the current charging state, the weight of the first failure probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second failure probability is positively correlated with the accuracy of the long short-term memory network. The data feature extraction module is further configured to extract the voltage-temperature coupling coefficient and the charge health index in the charge data. The voltage-temperature coupling coefficient indicates the dynamic relationship between the cell voltage and temperature of the rechargeable battery, and the charge health index indicates the similarity between the current charge curve and the historical reference charge curve. The formula for calculating the voltage-temperature coupling coefficient is expressed by the following formula (1): Here, C ｖｔ This represents the voltage-temperature coupling coefficient, ΔV ｉ ΔT is the voltage change at the i-th sampling point. ｉ This is the temperature change at the i-th sampling point. The formula for calculating the aforementioned charge health index is expressed by the following formula (2): Here, CHI indicates the charge health index, D current This is the current charging curve, D baseline This shows the hysteresis reference charging curve, DTW(D current , D baseline A fault diagnosis device based on charging data, characterized in that ) indicates the similarity distance between the current charging curve and the historical reference charging curve, and MaxLength indicates the maximum length of those curves.

7. A computer-readable storage medium, A computer-readable storage medium characterized in that a computer program is stored in the storage medium, and the computer program is used to perform the method according to any one of claims 1 to 5.

8. It is an electronic device, Processor and The processor comprises a memory that stores executable instructions, The electronic device is characterized in that the processor is used to perform the method described in any one of claims 1 to 5.

Images