Classification and identification method and system of energy storage battery, electronic equipment and storage medium

Abstract

The invention discloses an energy storage battery classification and identification method and system, electronic equipment and a storage medium, and the method comprises the steps: carrying out the charging and discharging test of different energy storage batteries, collecting the charging and discharging data of different energy storage batteries, extracting the transient characteristics of the charging and discharging data, and enabling the transient characteristics to better represent the charging and discharging characteristics of each energy storage battery; then, principal component analysis processing is carried out on the transient characteristics of each energy storage battery, a plurality of main characteristic characteristics are extracted, and the characteristic dimension is effectively reduced; then, constructing a training data set and an energy storage battery identification model, and training the energy storage battery identification model by using the training data set until the model converges; and finally, obtaining the charging and discharging data of the energy storage battery to be identified, obtaining the characteristics of the energy storage battery, inputting the characteristics into the trained energy storage battery identification model, and outputting the classification result of the energy storage battery, so that different types of energy storage batteries can be adaptively and accurately identified, and the applicability and robustness of the algorithm are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery classification and identification, and in particular, to a classification and identification method and system for energy storage batteries, electronic equipment, and a computer-readable storage medium. Background Art

[0002] With the growing demand for energy, energy storage batteries play an increasingly important role in power systems, electric vehicles and other fields. Different energy storage batteries have different chemical compositions and electrochemical characteristics. In order to optimize battery performance and extend service life, different energy storage batteries need to be managed in a differentiated manner. Therefore, it is necessary to accurately identify the type of energy storage batteries. Traditional battery type identification methods often rely on fixed identification models, which are difficult to adapt to the dynamic changes of different battery types and cannot accurately identify battery types. Summary of the invention

[0003] The present invention provides a classification and identification method and system for energy storage batteries, electronic equipment, and a computer-readable storage medium, which can adaptively and accurately identify different types of energy storage batteries, thereby improving the applicability and robustness of the algorithm.

[0004] According to one aspect of the present invention, a method for classifying and identifying energy storage batteries is provided, comprising the following contents:

[0005] Carry out charge and discharge tests on different energy storage batteries, collect charge and discharge data of different energy storage batteries and extract transient characteristics of charge and discharge data;

[0006] The transient characteristics of each energy storage battery are processed by principal component analysis to obtain multiple characteristic features;

[0007] Construct a feature vector based on multiple characteristic features of each energy storage battery, and construct a training data set;

[0008] An energy storage battery identification model is constructed based on the Hebb neural network model, and the energy storage battery identification model is trained using the training data set until the model converges;

[0009] Obtain the charging and discharging data of the energy storage battery to be identified and obtain its characteristic features, input the characteristic features into the trained energy storage battery identification model, and output the energy storage battery classification result.

[0010] Furthermore, the process of performing charge and discharge tests on different energy storage batteries, collecting charge and discharge data of different energy storage batteries and extracting transient characteristics of the charge and discharge data includes the following:

[0011] Taking each energy storage battery from the start of charging to the end of discharging as one cycle, collect charging and discharging data of multiple cycles;

[0012] Standardize the collected charge and discharge data;

[0013] Transient features are extracted from the standardized charge and discharge data.

[0014] Furthermore, the transient characteristics include voltage transient characteristics, current transient characteristics, temperature transient characteristics, steady-state recovery time and response time, wherein the voltage transient characteristics include charging cut-off voltage, discharging cut-off voltage, voltage rise time, voltage drop time, voltage change rate and voltage overshoot index, the current transient characteristics include charging cut-off current, discharging cut-off current, current rise time, current drop time, current change rate and current overshoot index, and the temperature transient characteristics include maximum temperature and minimum temperature.

[0015] Furthermore, the weight update rule of the energy storage battery identification model is:

[0016]

[0017] Among them, W new and W old Represent the weights before and after the update, γ represents the decay factor, α represents the learning rate, and t q represents the expected output of the qth feature, a q represents the actual output of the qth feature, p q It represents the input of the qth feature, and the superscript T represents transposition.

[0018] Furthermore, the following contents are also included:

[0019] The characteristic feature data of the energy storage battery of the type corresponding to the energy storage battery classification result obtained in the charge and discharge test are obtained, and the health status of the energy storage battery to be identified is identified in combination with the current characteristic features of the energy storage battery to be identified.

[0020] Furthermore, the process of obtaining characteristic feature data of the energy storage battery of the type corresponding to the energy storage battery classification result obtained in the charge and discharge test and identifying the health status of the energy storage battery to be identified in combination with the current characteristic features of the energy storage battery to be identified includes the following:

[0021] Obtain characteristic feature data of the type of energy storage battery corresponding to the energy storage battery classification result obtained in the charge and discharge test, and calculate the average value and standard deviation of each characteristic feature data;

[0022] Based on each current characteristic feature of the energy storage battery to be identified, a Gaussian distribution function value of each characteristic feature is calculated;

[0023] The health status of the energy storage battery to be identified is judged based on the Gaussian distribution function values ​​of all characteristic features.

[0024] Furthermore, for the Gaussian distribution function value of each characteristic feature, if it is within μ-2σ~μ+2σ, it is judged to be normal; if it is within μ-3σ~μ-2σ or μ+2σ~μ+3σ, it is judged to be a warning; if it is less than μ-3σ or greater than μ+3σ, it is judged to be abnormal, μ represents the mean value of the characteristic feature, and σ represents the standard deviation of the characteristic feature.

[0025] In addition, the present invention also provides a classification and identification system for energy storage batteries, comprising:

[0026] The charge and discharge test module is used to perform charge and discharge tests on different energy storage batteries, collect charge and discharge data of different energy storage batteries and extract transient characteristics of the charge and discharge data;

[0027] A principal component analysis module is used to perform principal component analysis on the transient characteristics of each energy storage battery to obtain multiple characteristic features;

[0028] A training data construction module, used to construct a feature vector based on multiple characteristic features of each energy storage battery, and to construct a training data set;

[0029] The model building and training module is used to build an energy storage battery identification model based on the Hebb neural network model, and train the energy storage battery identification model using the training data set until the model converges;

[0030] The battery classification and identification module is used to obtain the charging and discharging data of the energy storage battery to be identified and obtain its characteristic features, input the characteristic features into the trained energy storage battery identification model, and output the energy storage battery classification result.

[0031] In addition, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the above method by calling the computer program stored in the memory.

[0032] In addition, the present invention also provides a computer-readable storage medium for storing a computer program for classifying and identifying energy storage batteries, wherein the computer program executes the steps of the method described above when running on a computer.

[0033] The present invention has the following beneficial effects:

[0034] The classification and identification method of the energy storage battery of the present invention first performs charge and discharge tests on different energy storage batteries, collects the charge and discharge data of different energy storage batteries and extracts the transient characteristics of the charge and discharge data. The transient characteristics can better characterize the charge and discharge characteristics of each energy storage battery, which is conducive to improving the accuracy of battery classification and identification. Then, the transient characteristics of each energy storage battery are subjected to principal component analysis processing to extract a plurality of main characteristic features, effectively reducing the characteristic dimension, reducing the amount of data processing while ensuring the accuracy of model recognition, and improving efficiency. Then, a training data set and an energy storage battery identification model are constructed, and the energy storage battery identification model is trained using the training data set until the model converges. Finally, the charge and discharge data of the energy storage battery to be identified and its characteristic features are obtained, and the characteristic features are input into the trained energy storage battery identification model to output the energy storage battery classification result, which can adaptively and accurately identify different types of energy storage batteries, thereby improving the applicability and robustness of the algorithm.

[0035] In addition, the energy storage battery classification and identification system of the present invention also has the above advantages.

[0036] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0038] Figure 1 It is a flow chart of a classification and identification method of energy storage batteries according to a preferred embodiment of the present application;

[0039] Figure 2 yes Figure 1 Schematic diagram of the sub-process of step S1;

[0040] Figure 3 It is another flow chart of the classification and identification method of the energy storage battery of the preferred embodiment of the present application;

[0041] Figure 4 yes Figure 3 Schematic diagram of the sub-process of step S6;

[0042] Figure 5 It is a schematic diagram of the module structure of a classification and identification system for energy storage batteries according to another embodiment of the present application. DETAILED DESCRIPTION

[0043] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0044] Reference Figure 1 The preferred embodiment of the present application provides a classification and identification method for energy storage batteries, comprising the following contents:

[0045] Step S1: performing charge and discharge tests on different energy storage batteries, collecting charge and discharge data of different energy storage batteries and extracting transient characteristics of the charge and discharge data;

[0046] Step S2: performing principal component analysis on the transient characteristics of each energy storage battery to obtain multiple characteristic features;

[0047] Step S3: constructing a feature vector based on multiple characteristic features of each energy storage battery, and constructing a training data set;

[0048] Step S4: constructing an energy storage battery identification model based on the Hebb neural network model, and training the energy storage battery identification model using a training data set until the model converges;

[0049] Step S5: Obtain the charging and discharging data of the energy storage battery to be identified and obtain its characteristic features, input the characteristic features into the trained energy storage battery identification model, and output the energy storage battery classification result.

[0050] It can be understood that the classification and identification method of the energy storage battery of this embodiment first performs charge and discharge tests on different energy storage batteries, collects charge and discharge data of different energy storage batteries, and extracts transient characteristics of the charge and discharge data. The transient characteristics can better characterize the charge and discharge characteristics of each energy storage battery, which is conducive to improving the accuracy of battery classification and identification. Then, the transient characteristics of each energy storage battery are subjected to principal component analysis, and a plurality of main characteristic features are extracted, which effectively reduces the characteristic dimension, reduces the amount of data processing while ensuring the accuracy of model recognition, and improves efficiency. Then, a training data set and an energy storage battery identification model are constructed, and the energy storage battery identification model is trained using the training data set until the model converges. Finally, the charge and discharge data of the energy storage battery to be identified and its characteristic features are obtained, and the characteristic features are input into the trained energy storage battery identification model, and the energy storage battery classification result can be output, which can adaptively and accurately identify different types of energy storage batteries, and improve the applicability and robustness of the algorithm.

[0051] It is understandable that Figure 2 As shown, in step S1, the process of performing charge and discharge tests on different energy storage batteries, collecting charge and discharge data of different energy storage batteries and extracting transient characteristics of the charge and discharge data includes the following:

[0052] Step S11: taking each energy storage battery from the start of charging to the end of discharging as one cycle, collecting charging and discharging data of multiple cycles;

[0053] Step S12: standardizing the collected charge and discharge data;

[0054] Step S13: extracting transient features from the normalized charge and discharge data.

[0055] Specifically, the charging and discharging data of the first 50 cycles of each energy storage battery are collected from the start of charging to the end of discharging. The charging and discharging data include voltage, current, temperature and other data. The sampling points in one cycle are combined into a data sequence based on the frequency of sampling every 30 minutes. Then, each type of charging and discharging data collected is standardized and mapped to the range of [0,1] to eliminate the adverse effects caused by the difference in the original data dimension and the data set. The specific standardization process Z = x-μ

[0056] The formula is: σ, where Z represents the data after standardization, x represents the collected charge and discharge data, μ represents the average value of the charge and discharge data, and σ represents the standard deviation of the charge and discharge data. Next, the transient characteristics are extracted from the standardized charge and discharge data, where the transient characteristics include voltage transient characteristics, current transient characteristics, temperature transient characteristics, steady-state recovery time and response time. Among them, the voltage transient characteristics include the charge cut-off voltage Max (U c )、Discharge cut-off voltage Min(U c ), voltage rise time T uc =t 90％ -t 10％ (i.e. the time required for the voltage to change from 10% to 90% of SOC), voltage drop time T uf =t 10％ -t 90％ (i.e. the time required for the voltage to change from 90% to 10% SOC), voltage change rate and voltage overshoot indicators Current transient characteristics include charging cut-off current Max (I c )、Discharge cut-off current Min(I c ), current rise time T ic =t 90％ -t 10％ (i.e. the time required for the current to change from 10% to 90% of SOC), current fall time T if =t 10％ -t 90％ (i.e. the time required for the current to change from 90% to 10% SOC), current change rate and current overshoot indicators Temperature transient characteristics include maximum temperature Max(T(t)) and minimum temperature Min(T(t)), steady-state recovery time T stabilization =t1% refers to the time required for the battery to stabilize the voltage or current within a certain range (e.g. ±1%) from the start of charging and discharging. The response time T response =t 90 % refers to the time required for the battery to reach a certain percentage (e.g. 90%) of the steady-state value from the start of charging and discharging. It can be understood that the use of the above transient characteristic indicators can better characterize the charging and discharging characteristics of each energy storage battery, which is conducive to improving the accuracy of battery classification and identification. In addition, the types of energy storage batteries include lithium-ion batteries, sodium-ion batteries, and lead-acid batteries.

[0057] It can be understood that in step S2, the transient characteristics of each energy storage battery are reduced in dimension using the principal component analysis method to extract several main characteristic features that can characterize the charging and discharging characteristics of each energy storage battery, which can effectively reduce the characteristic dimension and reduce the subsequent data processing amount. Specifically, the transient characteristic data of each energy storage battery is constructed into a characteristic matrix n represents the amount of data in one cycle, m represents the number of cycles, and then the data is standardized to calculate the standardized feature covariance matrix: ζ represents the covariance matrix, N represents the number of samples, and then the covariance matrix is ​​decomposed into eigenvalues ​​to obtain eigenvalues ​​and eigenvectors: ζ = VDV T , D represents a diagonal matrix, the diagonal elements are eigenvalues, V represents a matrix composed of eigenvectors, and then the principal components are selected according to the size of the eigenvalues, and the first 4 components with the largest eigenvalues ​​are selected as the main characteristic features.

[0058] It can be understood that in step S3, labels are produced based on the four characteristic feature data obtained by principal component analysis to construct a training data set, and the training data set is divided into a training set, a validation set and a test set.

[0059] It can be understood that in step S4, an energy storage battery identification model is constructed based on the Hebb neural network model, wherein the Hebb neural network includes an input layer, multiple hidden layers and three output layers, each neuron has a weight connected to it, and for each training sample, the neurons in the input layer receive the four characteristic features of the battery, while the neurons in the output layer correspond to the probability distribution of different battery types. The goal of the Hebb neural network is to adjust the weight W so that the output vector The output vector y that is closest to the target is: Among them, σ() represents the activation function, and the Sigmoid function can be used: z represents the process quantity, that is, the value of the hidden layer after the input layer imports data, e represents the natural constant, and P represents the input feature vector. Different target output vectors y can be defined according to different types of batteries, for example, y 锂电池 =[1,0,0]

[0060] y 钠电池 =[0,1,0]

[0061] y 铅酸电池 =[0,0,1], so that according to the actual output of the Hebb neural network To determine which type of energy storage battery the energy storage battery to be identified belongs to.

[0062] In addition, the weight update rule of the existing Hebb neural network model is: In the present invention, an incremental rule is introduced to replace the expected output with the difference between the expected output and the actual output, that is, the weight update rule is:

[0063]

[0064] Among them, W new and W old They represent the weights before and after the update, γ represents the attenuation factor, γ < 1, which is a constant, α represents the learning rate, which is a constant, and t q represents the expected output of the qth feature, a q represents the actual output of the qth feature, p q It represents the input of the qth feature, and the superscript T represents transposition. It can be understood that by replacing the expected output with the difference between the expected output and the actual output in the weight update rule, the mean square error of the model is minimized, which is conducive to improving the recognition performance of the model.

[0065] Then, the model is trained using the training set until the model converges, the performance of the model is verified using the validation set, and the performance of the model is tested using the test set.

[0066] It can be understood that in step S5, the charging and discharging data of the energy storage battery to be identified in the actual charging and discharging process is obtained, and after transient feature extraction and principal component dimensionality reduction processing, the current characteristic feature data of the energy storage battery to be identified is obtained, and it is input into the trained energy storage battery identification model to output the energy storage battery classification result, which can adaptively and accurately identify different types of energy storage batteries, thereby improving the applicability and robustness of the algorithm.

[0067] In addition, if Figure 3 As shown, the classification and identification method of the energy storage battery also includes the following contents:

[0068] Step S6: Acquire characteristic feature data of the energy storage battery of the type corresponding to the energy storage battery classification result obtained in the charge and discharge test, and identify the health status of the energy storage battery to be identified in combination with the current characteristic features of the energy storage battery to be identified.

[0069] It can be understood that according to the classification and identification result in step S5, the characteristic feature data of this type of energy storage battery obtained in the charge and discharge test is obtained, and combined with the current characteristic features of the energy storage battery to be identified, the current health status of the energy storage battery to be identified can be identified, and automatic identification of the battery health status can be achieved.

[0070] Among them, Figure 4 As shown, the process of obtaining characteristic feature data of the energy storage battery of the type corresponding to the energy storage battery classification result obtained in the charge and discharge test, and identifying the health status of the energy storage battery to be identified in combination with the current characteristic features of the energy storage battery to be identified includes the following:

[0071] Step S61: obtaining characteristic feature data of the energy storage battery of the type corresponding to the energy storage battery classification result obtained in the charge and discharge test, and calculating the average value and standard deviation of each characteristic feature data;

[0072] Step S62: Calculate the Gaussian distribution function value of each characteristic feature based on each current characteristic feature of the energy storage battery to be identified;

[0073] Step S63: judging the health status of the energy storage battery to be identified based on the Gaussian distribution function values ​​of all characteristic features.

[0074] Specifically, taking the classification result of the energy storage battery as a lithium-ion battery as an example, first obtain four characteristic feature data of the lithium-ion battery in the charge and discharge test, and then calculate the average value and standard deviation of each characteristic feature data. The calculation formula is: μ represents the mean value of the characteristic feature, σ represents the standard deviation of the characteristic feature, and p i represents the i-th characteristic feature data, and N represents the number of the i-th characteristic feature data. Then, based on each current characteristic feature of the energy storage battery to be identified, the Gaussian distribution function value of each characteristic feature is calculated, and the calculation formula is: Among them, p′ iRepresents the current i-th characteristic feature data of the energy storage battery to be identified. The closer the H value is to 1, the better the health state of the battery is, and the closer the H value is to 0, the worse the health state of the battery is. For the Gaussian distribution function value of each characteristic feature, if the H value is within μ-2σ~μ+2σ, it is judged to be normal, if the H value is within μ-3σ~μ-2σ or μ+2σ~μ+3σ, it is judged to be a warning, if the H value is less than μ-3σ or greater than μ+3σ, it is judged to be abnormal, μ represents the average value of the characteristic feature, and σ represents the standard deviation of the characteristic feature. When the H values ​​based on the four characteristic features of the energy storage battery to be identified are all judged to be normal, the health state of the energy storage battery to be identified is judged to be a normal state, if there is at least one characteristic feature whose H value is judged to be a warning, the health state of the energy storage battery to be identified is judged to be a warning state, and if there is at least one characteristic feature whose H value is judged to be abnormal, the health state of the energy storage battery to be identified is judged to be an abnormal state, which means that the battery is faulty.

[0075] It can be understood that the present invention takes into account that the fluctuation of battery parameters obeys Gaussian distribution, and the fluctuation of battery parameters of the same specification is caused by random errors. Therefore, Gaussian distribution is used to determine whether the current electrochemical characteristic parameters of the battery are within a reasonable range, so as to detect whether the battery has a fault.

[0076] In addition, if Figure 5 As shown, another embodiment of the present invention further provides a classification and identification system for energy storage batteries, preferably using the classification and identification method for energy storage batteries as described above, the system comprising:

[0077] The charge and discharge test module is used to perform charge and discharge tests on different energy storage batteries, collect charge and discharge data of different energy storage batteries and extract transient characteristics of the charge and discharge data;

[0078] A principal component analysis module is used to perform principal component analysis on the transient characteristics of each energy storage battery to obtain multiple characteristic features;

[0079] A training data construction module, used to construct a feature vector based on multiple characteristic features of each energy storage battery, and to construct a training data set;

[0080] The model building and training module is used to build an energy storage battery identification model based on the Hebb neural network model, and train the energy storage battery identification model using the training data set until the model converges;

[0081] The battery classification and identification module is used to obtain the charging and discharging data of the energy storage battery to be identified and obtain its characteristic features, input the characteristic features into the trained energy storage battery identification model, and output the energy storage battery classification result.

[0082] It can be understood that the energy storage battery classification and identification system of this embodiment first performs charge and discharge tests on different energy storage batteries, collects charge and discharge data of different energy storage batteries and extracts transient characteristics of the charge and discharge data. The transient characteristics can better characterize the charge and discharge characteristics of each energy storage battery, which is conducive to improving the accuracy of battery classification and identification. Then, the transient characteristics of each energy storage battery are subjected to principal component analysis, and a plurality of main characteristic features are extracted, which effectively reduces the characteristic dimension, reduces the amount of data processing while ensuring the accuracy of model recognition, and improves efficiency. Then, a training data set and an energy storage battery identification model are constructed, and the energy storage battery identification model is trained using the training data set until the model converges. Finally, the charge and discharge data of the energy storage battery to be identified and its characteristic features are obtained, and the characteristic features are input into the trained energy storage battery identification model, and the energy storage battery classification result can be output, which can adaptively and accurately identify different types of energy storage batteries, and improve the applicability and robustness of the algorithm.

[0083] In addition, the energy storage battery classification and identification system also includes:

[0084] The health status identification module is used to obtain the characteristic feature data of the energy storage battery of the type corresponding to the energy storage battery classification result obtained in the charge and discharge test, and identify the health status of the energy storage battery to be identified in combination with the current characteristic features of the energy storage battery to be identified.

[0085] It can be understood that the various modules of the system embodiment correspond to the various steps of the above method embodiment, so the specific working principles of each module will not be repeated here, and the corresponding references can be made to the above method embodiment.

[0086] In addition, another embodiment of the present invention further provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the above method by calling the computer program stored in the memory.

[0087] In addition, another embodiment of the present invention further provides a computer-readable storage medium for storing a computer program for classifying and identifying energy storage batteries, wherein the computer program executes the steps of the method described above when running on a computer.

[0088] The general form of computer readable storage media includes: floppy disk, flexible disk, hard disk, magnetic tape, any other magnetic medium, CD-ROM, any other optical medium, punch cards, paper tape, any other physical medium with a pattern of holes, random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), flash erasable programmable read-only memory (FLASH-EPROM), any other memory chip or cartridge, or any other medium that can be read by a computer. The instructions can further be transmitted or received by a transmission medium. The term transmission medium can include any tangible or intangible medium that can be used to store, encode or carry instructions for execution by a machine, and includes digital or analog communication signals or other intangible media that facilitate the communication of the above instructions. Transmission media include coaxial cables, copper wires and optical fibers, which include the wires of a bus used to transmit a computer data signal.

[0089] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0090] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0093] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0094] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0095] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A classification and identification method for energy storage batteries, characterized in that: Includes the following: Carry out charge and discharge tests on different energy storage batteries, collect charge and discharge data of different energy storage batteries and extract transient characteristics of charge and discharge data; The transient characteristics of each energy storage battery are processed by principal component analysis to obtain multiple characteristic features; Construct a feature vector based on multiple characteristic features of each energy storage battery, and construct a training data set; An energy storage battery identification model is constructed based on the Hebb neural network model, and the energy storage battery identification model is trained using the training data set until the model converges; Obtain the charging and discharging data of the energy storage battery to be identified and obtain its characteristic features, input the characteristic features into the trained energy storage battery identification model, and output the energy storage battery classification result.

2. The method for classifying and identifying energy storage batteries according to claim 1, characterized in that: The process of performing charge and discharge tests on different energy storage batteries, collecting charge and discharge data of different energy storage batteries, and extracting transient characteristics of the charge and discharge data includes the following: Taking each energy storage battery from the start of charging to the end of discharging as one cycle, collect charging and discharging data of multiple cycles; Standardize the collected charge and discharge data; Transient features are extracted from the standardized charge and discharge data.

3. The classification and identification method of energy storage batteries according to claim 2, characterized in that: Transient characteristics include voltage transient characteristics, current transient characteristics, temperature transient characteristics, steady-state recovery time and response time. Among them, voltage transient characteristics include charging cut-off voltage, discharging cut-off voltage, voltage rise time, voltage drop time, voltage change rate and voltage overshoot index; current transient characteristics include charging cut-off current, discharging cut-off current, current rise time, current drop time, current change rate and current overshoot index; temperature transient characteristics include maximum temperature and minimum temperature.

4. The method for classifying and identifying energy storage batteries according to claim 1, characterized in that: The weight update rule of the energy storage battery identification model is: Among them, W new and W old Represent the weights before and after the update, γ represents the decay factor, α represents the learning rate, and t q represents the expected output of the qth feature, a q represents the actual output of the qth feature, p q It represents the input of the qth feature, and the superscript T represents transposition.

5. The method for classifying and identifying energy storage batteries according to claim 1, characterized in that: Also included are the following: The characteristic feature data of the energy storage battery of the type corresponding to the energy storage battery classification result obtained in the charge and discharge test are obtained, and the health status of the energy storage battery to be identified is identified in combination with the current characteristic features of the energy storage battery to be identified.

6. The method for classifying and identifying energy storage batteries according to claim 5, characterized in that: The process of obtaining characteristic feature data of the energy storage battery of the type corresponding to the energy storage battery classification result obtained in the charge and discharge test, and identifying the health status of the energy storage battery to be identified in combination with the current characteristic features of the energy storage battery to be identified includes the following: Obtain characteristic feature data of the type of energy storage battery corresponding to the energy storage battery classification result obtained in the charge and discharge test, and calculate the average value and standard deviation of each characteristic feature data; Based on each current characteristic feature of the energy storage battery to be identified, a Gaussian distribution function value of each characteristic feature is calculated; The health status of the energy storage battery to be identified is judged based on the Gaussian distribution function values ​​of all characteristic features.

7. The method for classifying and identifying energy storage batteries according to claim 6, characterized in that: For each characteristic feature, the Gaussian distribution function value is within μ-2σ~μ+ 2 If it is within σ, it is judged to be normal. If it is within μ-3σ~μ-2σ or μ+2σ~μ+3σ, it is judged to be warning. If it is less than μ-3σ or greater than μ+3σ, it is judged to be abnormal. μ represents the mean value of the characteristic feature, and σ represents the standard deviation of the characteristic feature.

8. A classification and identification system for energy storage batteries, characterized in that: include: The charge and discharge test module is used to perform charge and discharge tests on different energy storage batteries, collect charge and discharge data of different energy storage batteries and extract transient characteristics of the charge and discharge data; A principal component analysis module is used to perform principal component analysis on the transient characteristics of each energy storage battery to obtain multiple characteristic features; A training data construction module, used to construct a feature vector based on multiple characteristic features of each energy storage battery, and to construct a training data set; The model building and training module is used to build an energy storage battery identification model based on the Hebb neural network model, and train the energy storage battery identification model using the training data set until the model converges; The battery classification and identification module is used to obtain the charging and discharging data of the energy storage battery to be identified and obtain its characteristic features, input the characteristic features into the trained energy storage battery identification model, and output the energy storage battery classification result.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the method according to any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium for storing a computer program for classifying and identifying energy storage batteries, characterized in that: When the computer program is run on a computer, the steps of the method according to any one of claims 1 to 7 are executed.

Images