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

Abstract

The invention provides a fault diagnosis method and device based on charging data, a medium and equipment. The method comprises the following steps: collecting charging data in a charging process; static features and time sequence features in the charging data are extracted; inputting the static features into a support vector machine model to obtain a first fault probability; inputting the time sequence features into a long short-term memory network to obtain a second fault probability; based on the first fault probability and the second fault probability, performing weighted summation to obtain comprehensive credibility; the method comprises the following steps of: collecting charging data in real time in a charging process, extracting static characteristics and time sequence characteristics in the charging data, and respectively identifying the static characteristics and the time sequence characteristics by using a support vector machine model and a long short-term memory network to obtain a first fault probability and a second fault probability; and integrating the first fault probability and the second fault probability to obtain the credibility of the charging fault so as to improve the accuracy of fault prediction.

Description

Technical Field

[0001] The present application relates to the field of charging monitoring technology, and in particular to a fault diagnosis method, device, medium and equipment based on charging data. Background Art

[0002] Electric vehicles are becoming more and more popular due to their advantages of environmental protection, cleanliness and energy saving. As an important component in the promotion of electric vehicles, electric vehicle charging facilities are also developing rapidly. As the main charging equipment for electric vehicles, the number and frequency of use of charging piles are also increasing rapidly. However, during the charging process, charging failures may occur due to various reasons, resulting in abnormal charging, and even affecting charging safety in severe cases. Therefore, it is necessary to perform fault diagnosis on the charging process of electric vehicles.

[0003] The current charging process fault diagnosis technology mainly relies on static parameters collected by sensors or controllers during the charging process, such as charging current or charging voltage. However, in the actual charging process, if the charging current is too high, the temperature may rise rapidly, resulting in safety accidents, and it is difficult to predict the fault in advance through static parameters. Therefore, it is necessary to provide a method that can quickly and accurately predict charging faults. Summary of the invention

[0004] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a method, device, medium and equipment for fault diagnosis based on charging data.

[0005] According to one aspect of the present application, a fault diagnosis method based on charging data is provided, comprising: collecting charging data during the charging process; wherein the collection frequency of the charging data is related to the charge state of the rechargeable battery; extracting static features and time series features in the charging data; inputting the static features into a support vector machine model to obtain a first fault probability; inputting the time series features into a long short-term memory network to obtain a second fault probability; based on the first fault probability and the second fault probability, taking a weighted sum to obtain a comprehensive credibility; wherein the comprehensive credibility represents the credibility of the presence of a fault in the current charging state, the weight of the first fault probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second fault probability is positively correlated with the accuracy of the long short-term memory network.

[0006] In one embodiment, extracting the static features and time series features from the charging data includes: extracting a voltage-temperature coupling coefficient and a charging health index from the charging data; wherein the voltage-temperature coupling coefficient represents the dynamic correlation between the single cell voltage and temperature of the rechargeable battery, and the charging health index represents the similarity between the current charging curve and the historical benchmark charging curve.

[0007] In one embodiment, extracting the voltage-temperature coupling coefficient and the charging health index from the charging data includes: The calculation formula of the voltage-temperature coupling coefficient is: ; in, is the voltage-temperature coupling coefficient, For the The voltage change at each sampling point is For the The temperature change of each sampling point; The calculation formula of the charging health index is: ; in, For the charging health index, is the current charging curve, is the historical benchmark charging curve, Indicates the similarity distance between the current charging curve and the historical benchmark charging curve, It is the maximum length of the current charging curve and the historical benchmark charging curve.

[0008] In one embodiment, the fault diagnosis method based on charging data further includes: if the difference between the voltage-temperature coupling coefficient at the current moment and the voltage-temperature coupling coefficient at the previous moment is greater than a preset difference threshold, determining that there is a fault in the current charging state.

[0009] In one embodiment, the weighted sum based on the first failure probability and the second failure probability to obtain the comprehensive credibility includes: the calculation formula of the comprehensive credibility is: ; in, For comprehensive credibility, is the weight of the first failure probability, is the weight of the second failure probability, is the first failure probability, is the second failure probability; ， ， is the accuracy of the support vector machine model, is the accuracy of the long short-term memory network.

[0010] In one embodiment, the collecting of charging data during the charging process includes: acquiring charging battery data collected by the charging battery and charging pile data collected by the charging pile during the charging process; and matching the charging data based on the charging battery data and the charging pile data.

[0011] In one embodiment, collecting charging data during the charging process includes: if the voltage difference between the cells of the rechargeable battery is greater than a preset voltage threshold, increasing the frequency of collecting the charging data.

[0012] According to another aspect of the present application, a fault diagnosis device based on charging data is provided, comprising: a charging data acquisition module, used to collect charging data during the charging process; wherein the collection frequency of the charging data is related to the charge state of the rechargeable battery; a data feature extraction module, used to extract static features and time series features in the charging data; a first probability calculation module, used to input the static features into a support vector machine model to obtain a first fault probability; a second probability calculation module, used to input the time series features into a long short-term memory network to obtain a second fault probability; a credibility calculation module, used to obtain a comprehensive credibility based on a weighted sum of the first fault probability and the second fault probability; wherein the comprehensive credibility represents the credibility of the presence of a fault in the current charging state, the weight of the first fault probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second fault probability is positively correlated with the accuracy of the long short-term memory network.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute any of the above methods.

[0014] According to another aspect of the present application, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor is used to execute any of the above-described methods.

[0015] The present application provides a charging data-based fault diagnosis method, device, medium and equipment, which collect charging data during the charging process; wherein the charging data collection frequency is related to the charge state of the rechargeable battery; extract static features and time series features in the charging data; input the static features into a support vector machine model to obtain a first fault probability; input the time series features into a long short-term memory network to obtain a second fault probability; based on the first fault probability and the second fault probability, a weighted sum is performed to obtain a comprehensive credibility; wherein the comprehensive credibility represents the credibility of the existence of a fault in the current charging state, the weight of the first fault probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second fault probability is positively correlated with the accuracy of the long short-term memory network; that is, charging data is collected in real time during the charging process and static features and time series features therein are extracted, the support vector machine model and the long short-term memory network are used to respectively identify the static features and time series features to obtain the first fault probability and the second fault probability, and the credibility of the charging fault is obtained by combining the first fault probability and the second fault probability to improve the accuracy of fault prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 It is a flowchart of a fault diagnosis method based on charging data provided by an exemplary embodiment of the present application.

[0018] Figure 2 It is a structural schematic diagram of a fault diagnosis device based on charging data provided by an exemplary embodiment of the present application.

[0019] Figure 3 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0020] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0021] Figure 1 FIG. 1 is a flow chart of a fault diagnosis method based on charging data provided by an exemplary embodiment of the present application. Figure 1 As shown, the fault diagnosis method based on charging data includes the following steps: Step 110: Collect charging data during the charging process.

[0022] The frequency of collecting charging data is related to the state of charge of the rechargeable battery. The present application collects charging data of the rechargeable battery during the charging process to monitor the charging process of the rechargeable battery in real time. The frequency of collecting charging data is related to the state of charge (SOC) of the rechargeable battery. Specifically, when the SOC of the rechargeable battery is less than 20%, the collection frequency is 1Hz, when the SOC of the rechargeable battery is 20%-80%, the collection frequency is 10Hz, and when the SOC of the rechargeable battery is greater than 80%, the collection frequency is 1Hz, that is, when the SOC of the rechargeable battery is too low or high (at this time, the charging current is usually small), the charging data is collected at a lower collection frequency, and when the SOC is 20%-80% (at this time, the charging current is usually large), the charging data is collected at a higher collection frequency to improve the monitoring effect.

[0023] Step 120: Extract static features and time series features from the charging data.

[0024] After collecting the charging data, this application extracts static features (such as voltage mean, temperature extremes, etc.) and time series features (such as voltage fluctuation curve, temperature change trend, etc.) from the charging data to determine whether there is a fault in the charging process.

[0025] Step 130: Input the static features into the support vector machine model to obtain a first failure probability.

[0026] The present application inputs the extracted static features into a support vector machine model (SVM) to obtain a first fault probability, wherein the support vector machine model can be obtained by training multiple samples.

[0027] Step 140: Input the time series features into the long short-term memory network to obtain a second failure probability.

[0028] The present application inputs the extracted time series features into a long short-term memory network (LSTM) to obtain a second failure probability, wherein the long short-term memory network can be obtained by training multiple samples.

[0029] Step 150: Based on the first failure probability and the second failure probability, perform weighted summation to obtain a comprehensive credibility.

[0030] Among them, the comprehensive credibility indicates the credibility of the fault in the current charging state, the weight of the first fault probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second fault probability is positively correlated with the accuracy of the long short-term memory network. This application uses the support vector machine model and the long short-term memory network to respectively judge the probability of a fault in the charging process, and weightedly sums the first fault probability and the second fault probability to obtain the final fault probability (i.e., comprehensive credibility) to combine the advantages of the two models and improve the accuracy of fault judgment.

[0031] The present application provides a fault diagnosis method based on charging data, which collects charging data during the charging process; wherein the collection frequency of the charging data is related to the charge state of the rechargeable battery; extracts static features and time series features in the charging data; inputs the static features into a support vector machine model to obtain a first fault probability; inputs the time series features into a long short-term memory network to obtain a second fault probability; based on the first fault probability and the second fault probability, a weighted sum is taken to obtain a comprehensive credibility; wherein the comprehensive credibility represents the credibility of the existence of a fault in the current charging state, the weight of the first fault probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second fault probability is positively correlated with the accuracy of the long short-term memory network; that is, charging data is collected in real time during the charging process and static features and time series features therein are extracted, the support vector machine model and the long short-term memory network are used to respectively identify the static features and time series features to obtain the first fault probability and the second fault probability, and the credibility of the charging fault is obtained by combining the first fault probability and the second fault probability to improve the accuracy of fault prediction.

[0032] In one embodiment, the specific implementation method of the above step 120 can be: extracting the voltage-temperature coupling coefficient and the charging health index in the charging data; wherein the voltage-temperature coupling coefficient represents the dynamic correlation between the single cell voltage and temperature of the rechargeable battery, and the charging health index represents the similarity between the current charging curve and the historical benchmark charging curve.

[0033] The present application obtains a judgment indicator for determining whether there is a fault during the charging process by extracting the voltage-temperature coupling coefficient, a dynamic correlation parameter of the single cell voltage and temperature of the rechargeable battery, and the charging health index, a similarity parameter between the current charging curve and the historical benchmark charging curve.

[0034] In one embodiment, the specific implementation of step 120 may be: The voltage-temperature coupling coefficient is calculated as: ; in, is the voltage-temperature coupling coefficient, For the The voltage change at the sampling point (compared to the i -1 sampling point), For the The temperature change of each sampling point (compared with the i -1 sampling point); The calculation formula of charging health index is: ; in, For the charging health index, is the current charging curve, is the historical benchmark charging curve, Indicates the similarity distance between the current charging curve and the historical benchmark charging curve, It is the maximum length of the current charging curve and the historical benchmark charging curve.

[0035] The present application calculates the voltage-temperature coupling coefficient and the charging health index respectively through the above formula, wherein the value range of the voltage-temperature coupling coefficient is [-1,1]. The voltage-temperature coupling coefficient is used to identify the thermal runaway risk of the rechargeable battery. The charging health index is used to evaluate the health status of the rechargeable battery. When the charging health index is continuously lower than a set threshold, it indicates that the capacity of the rechargeable battery is attenuated or the internal resistance is increased. At this time, it is necessary to further diagnose whether there is a fault in the charging process.

[0036] In one embodiment, the above-mentioned fault diagnosis method based on charging data may further include: if the difference between the voltage-temperature coupling coefficient at the current moment and the voltage-temperature coupling coefficient at the previous moment is greater than a preset difference threshold, determining that there is a fault in the current charging state.

[0037] After extracting the voltage-temperature coupling coefficient, the present application can determine whether the rechargeable battery has a risk of thermal runaway based on the voltage-temperature coupling coefficient. Specifically, by calculating the difference between the voltage-temperature coupling coefficient at the current moment and the voltage-temperature coupling coefficient at the previous moment, if the difference is greater than the preset difference threshold (that is, the voltage-temperature coupling coefficient suddenly increases), it is determined that abnormal heating has occurred inside the rechargeable battery. At this time, timely warning is required to avoid safety accidents.

[0038] In one embodiment, the specific implementation of the above step 150 may be: the calculation formula of the comprehensive credibility is: ; in, For comprehensive credibility, is the weight of the first failure probability, is the weight of the second failure probability, is the first failure probability, is the second failure probability; ， ， is the accuracy of the support vector machine model, is the accuracy of the long short-term memory network.

[0039] The present application calculates the comprehensive credibility through the above formula, that is, the comprehensive support vector machine model and the long short-term memory network diagnosis results, to obtain the final fault diagnosis result, that is, the final fault probability. The higher the comprehensive credibility, the higher the possibility of a fault in the charging process. The present application determines the weights of the two models based on the accuracy of the support vector machine model and the long short-term memory network (which can be verified using a validation set) to further improve the accuracy of fault diagnosis.

[0040] After obtaining the comprehensive credibility, the present application can be executed based on the early warning measures corresponding to the preset fault probability. For example, the present application can design the early warning mechanism into five levels. When the comprehensive credibility is lower than 30%, no operation is triggered. When the comprehensive credibility is between 30% and 50%, notification is triggered. When the comprehensive credibility is between 50% and 70%, current limiting charging is triggered. When the comprehensive credibility is between 70% and 90%, power reduction charging is triggered. When the comprehensive credibility is greater than 90%, power-off operation is triggered.

[0041] In one embodiment, the specific implementation method of the above step 110 can be: obtaining charging battery data collected by the charging battery during the charging process and charging pile data collected by the charging pile; and matching to obtain charging data based on the charging battery data and the charging pile data.

[0042] This application can use rechargeable batteries (such as BMS) and charging piles to collect charging battery data and charging pile data during the charging process, and introduce a data consistency check mechanism, that is, to check the charging battery data and charging pile data against each other, and use the charging battery data and charging pile data to check each other while checking whether the charging battery data and charging pile data are within a reasonable range, so as to fill in missing data and remove outliers and noise, so as to improve data reliability. If the charging battery data and charging pile data are found to be inconsistent during the verification process, data re-collection or an alarm prompt can be triggered.

[0043] In one embodiment, the specific implementation of the above step 110 may be: if the voltage difference between the cells of the rechargeable battery is greater than a preset voltage threshold, then increasing the frequency of collecting charging data.

[0044] The present application collects the voltage of the rechargeable battery cells to obtain the status information of the cells. If the voltage difference between the cells is greater than the preset voltage threshold, it means that the charging status difference between the cells is large. At this time, the charging data collection frequency can be increased (for example, to 100Hz) to improve charging safety.

[0045] Figure 2 FIG. 1 is a schematic diagram of a fault diagnosis device based on charging data provided by an exemplary embodiment of the present application. Figure 2As shown, the fault diagnosis device 20 based on charging data includes: a charging data acquisition module 21, which is used to collect charging data during the charging process; wherein the acquisition frequency of the charging data is related to the charge state of the rechargeable battery; a data feature extraction module 22, which is used to extract static features and time series features in the charging data; a first probability calculation module 23, which is used to input the static features into the support vector machine model to obtain a first fault probability; a second probability calculation module 24, which is used to input the time series features into the long short-term memory network to obtain a second fault probability; a credibility calculation module 25, which is used to obtain a comprehensive credibility based on the weighted sum of the first fault probability and the second fault probability; wherein the comprehensive credibility represents the credibility of the existence of a fault in the current charging state, the weight of the first fault probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second fault probability is positively correlated with the accuracy of the long short-term memory network.

[0046] The present application provides a fault diagnosis device based on charging data, which collects charging data during the charging process through a charging data collection module 21; wherein the collection frequency of the charging data is related to the charge state of the rechargeable battery; the data feature extraction module 22 extracts static features and time series features in the charging data; the first probability calculation module 23 inputs the static features into a support vector machine model to obtain a first fault probability; the second probability calculation module 24 inputs the time series features into a long short-term memory network to obtain a second fault probability; the credibility calculation module 25 obtains a comprehensive credibility by weighted summation based on the first fault probability and the second fault probability; wherein the comprehensive credibility represents the credibility of the existence of a fault in the current charging state, the weight of the first fault probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second fault probability is positively correlated with the accuracy of the long short-term memory network; that is, the charging data is collected in real time during the charging process and the static features and time series features therein are extracted, the support vector machine model and the long short-term memory network are used to identify the static features and time series features respectively to obtain the first fault probability and the second fault probability, and the credibility of the charging fault is obtained by combining the first fault probability and the second fault probability to improve the accuracy of fault prediction.

[0047] In one embodiment, the data feature extraction module 22 can be further configured to extract the voltage-temperature coupling coefficient and the charging health index in the charging data; wherein the voltage-temperature coupling coefficient represents the dynamic correlation between the single cell voltage and temperature of the rechargeable battery, and the charging health index represents the similarity between the current charging curve and the historical benchmark charging curve.

[0048] In one embodiment, the data feature extraction module 22 may be further configured as follows: The voltage-temperature coupling coefficient is calculated as: ; in, is the voltage-temperature coupling coefficient, For the The voltage change at each sampling point is For the The temperature change of each sampling point; The calculation formula of charging health index is: ; in, For the charging health index, is the current charging curve, is the historical benchmark charging curve, Indicates the similarity distance between the current charging curve and the historical benchmark charging curve, It is the maximum length of the current charging curve and the historical benchmark charging curve.

[0049] In one embodiment, the above-mentioned fault diagnosis device 20 based on charging data can be further configured as follows: if the difference between the voltage-temperature coupling coefficient at the current moment and the voltage-temperature coupling coefficient at the previous moment is greater than a preset difference threshold, it is determined that there is a fault in the current charging state.

[0050] In one embodiment, the above credibility calculation module 25 can be further configured as follows: the calculation formula of the comprehensive credibility is: ; in, For comprehensive credibility, is the weight of the first failure probability, is the weight of the second failure probability, is the first failure probability, is the second failure probability; ， ， is the accuracy of the support vector machine model, is the accuracy of the long short-term memory network.

[0051] In one embodiment, the charging data collection module 21 may be further configured to: obtain charging battery data collected by the charging battery during the charging process and charging pile data collected by the charging pile; and obtain charging data by matching the charging battery data and the charging pile data.

[0052] In one embodiment, the charging data collection module 21 may be further configured to increase the collection frequency of the charging data if the voltage difference between the cells of the rechargeable battery is greater than a preset voltage threshold.

[0053] Below, reference Figure 3The electronic device according to the embodiment of the present application is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signal from them.

[0054] Figure 3 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0055] like Figure 3 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0056] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0057] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the methods of the various embodiments of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0058] In one example, the electronic device 10 may further include: an input device 13 and an output device 14 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0059] When the electronic device is a stand-alone device, the input device 13 may be a communication network connector, which is used to receive the collected input signals from the first device and the second device.

[0060] In addition, the input device 13 may also include, for example, a keyboard, a mouse, and the like.

[0061] The output device 14 can output various information to the outside, including the determined distance information, direction information, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0062] Of course, to simplify, Figure 3Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0063] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0064] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0065] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0066] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0067] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0068] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0069] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0070] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0071] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A fault diagnosis method based on charging data, characterized in that: include: Collecting charging data during the charging process; wherein the charging data collection frequency is related to the charge state of the rechargeable battery; Extracting static features and time series features from the charging data; Inputting the static features into a support vector machine model to obtain a first fault probability; Inputting the time series features into a long short-term memory network to obtain a second failure probability; Based on the first fault probability and the second fault probability, a weighted sum is taken to obtain a comprehensive credibility; wherein the comprehensive credibility indicates the credibility of a fault in the current charging state, the weight of the first fault probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second fault probability is positively correlated with the accuracy of the long short-term memory network.

2. The fault diagnosis method based on charging data according to claim 1, characterized in that: The extracting of static features and time series features from the charging data comprises: Extracting a voltage-temperature coupling coefficient and a charging health index from the charging data; wherein the voltage-temperature coupling coefficient represents a dynamic correlation between a single cell voltage and a temperature of the rechargeable battery, and the charging health index represents a similarity between a current charging curve and a historical benchmark charging curve.

3. The fault diagnosis method based on charging data according to claim 2, characterized in that: The extracting the voltage-temperature coupling coefficient and the charging health index from the charging data comprises: The calculation formula of the voltage-temperature coupling coefficient is: ； in, is the voltage-temperature coupling coefficient, For the The voltage change at each sampling point is For the The temperature change of each sampling point; The calculation formula of the charging health index is: ； in, For the charging health index, is the current charging curve, is the historical benchmark charging curve, Indicates the similarity distance between the current charging curve and the historical benchmark charging curve, It is the maximum length of the current charging curve and the historical benchmark charging curve.

4. The fault diagnosis method based on charging data according to claim 2, characterized in that: The fault diagnosis method based on charging data also includes: If the difference between the voltage-temperature coupling coefficient at the current moment and the voltage-temperature coupling coefficient at the previous moment is greater than a preset difference threshold, it is determined that there is a fault in the current charging state.

5. The fault diagnosis method based on charging data according to claim 1, characterized in that: The weighted summing up of the first failure probability and the second failure probability to obtain the comprehensive credibility includes: The calculation formula of the comprehensive credibility is: ； in, For comprehensive credibility, is the weight of the first failure probability, is the weight of the second failure probability, is the first failure probability, is the second failure probability; ， , is the accuracy of the support vector machine model, is the accuracy of the long short-term memory network.

6. The fault diagnosis method based on charging data according to claim 1, characterized in that: The charging data collected during the charging process includes: Acquire the charging battery data collected by the charging battery and the charging pile data collected by the charging pile during the charging process; The charging data is obtained by matching the charging battery data and the charging pile data.

7. The fault diagnosis method based on charging data according to claim 1, characterized in that: The charging data collected during the charging process includes: If the voltage difference between the cells of the rechargeable battery is greater than a preset voltage threshold, the collection frequency of the charging data is increased.

8. A fault diagnosis device based on charging data, characterized in that: include: A charging data acquisition module, used to acquire charging data during the charging process; wherein the acquisition frequency of the charging data is related to the charge state of the rechargeable battery; A data feature extraction module, used to extract static features and time series features from the charging data; A first probability calculation module, used for inputting the static features into a support vector machine model to obtain a first fault probability; A second probability calculation module, used for inputting the time series feature into a long short-term memory network to obtain a second fault probability; A credibility calculation module is used to obtain a comprehensive credibility based on the weighted sum of the first fault probability and the second fault probability; wherein the comprehensive credibility represents the credibility of the presence of a fault in the current charging state, the weight of the first fault probability is positively correlated with the accuracy of the support vector machine model, and the weight of the second fault probability is positively correlated with the accuracy of the long short-term memory network.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the method described in any one of claims 1 to 7.

Images