A battery short circuit fault diagnosis method and system based on future parameter prediction
By constructing an equivalent circuit model and prediction model for short-circuit faults in the battery, predicting the future voltage and charge state of the battery, and evaluating and predicting the short-circuit resistance value in the existing technology, the short-circuit diagnosis in the battery caused by the lack of high-quality fault data is solved. The problem of low accuracy achieves fast and accurate fault diagnosis.
Patent Information
- Application Number
- CN202410577255.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-10
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-05-10
AI Technical Summary
The existing short-circuit fault diagnosis methods in the battery have the problems of low diagnostic accuracy and poor robustness due to lack of high-quality fault data. The model-based methods are complex, have large calculation volume and are susceptible to external interference.
Using the battery short-circuit fault diagnosis method based on future parameter prediction, a battery short-circuit fault equivalent circuit model is constructed by obtaining normal battery test data, predicting the future voltage and state of charge data of the battery to be diagnosed, and evaluating whether further diagnosis is needed based on the prediction results. , predict future short-circuit resistance values by constructing an equivalent circuit model to evaluate the severity of the fault.
It realizes rapid and accurate battery fault diagnosis without high-quality fault data, overcomes the problems of low diagnostic accuracy and high complexity caused by insufficient data by traditional methods, and combines the advantages of data-driven and model-based methods. , improves diagnosis speed and accuracy.
Smart Images

Figure CN118311432B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of battery fault diagnosis, and in particular to a battery short circuit fault diagnosis method and system based on future parameter prediction. Background Art
[0002] In the actual application of electric vehicles and energy storage systems, various internal and external faults may occur during battery operation, leading to performance problems and even serious consequences such as thermal runaway, fire or explosion. Among them, internal short circuit is the most common and representative safety failure mode, and one of the most important factors causing battery failure and safety problems. The deepening of the internal short circuit may cause thermal runaway and cause serious safety accidents. Therefore, when the internal short circuit is not serious, timely diagnosis of the internal short circuit and prevention of its further development are crucial to ensure the safe and reliable operation of the battery.
[0003] At present, the methods for internal short circuit fault diagnosis of batteries can be roughly divided into data-driven methods and model-based methods.
[0004] (1) Data-driven method: The data-driven internal short circuit diagnosis method learns features from historical fault battery data to form a nonlinear black box mapping model for fault diagnosis. It uses computational intelligence to simulate the inherent nonlinearity of the battery and uses statistical techniques to identify subtle deviations caused by faults. However, this method lacks high-quality fault training data, resulting in low model diagnostic accuracy and poor robustness.
[0005] (2) Model-based method: The model-based internal short circuit diagnosis method formalizes the physical behavior of the battery into a suitable analytical and mathematical model. Through the state space representation, the dynamic model of the faulty battery can be described. Then, fault diagnosis is achieved through state estimation. This method greatly reduces the dependence on data sets under data drive, but it has problems such as high complexity, large amount of calculation and susceptibility to external interference. Summary of the invention
[0006] In order to address the deficiencies of the prior art, an object of the present invention is to provide a battery short circuit fault diagnosis method and system based on future parameter prediction, so as to achieve rapid diagnosis of battery faults without the need for high-quality fault data.
[0007] In order to achieve the above object, according to some embodiments, a first aspect of the present invention provides a battery short circuit fault diagnosis method based on future parameter prediction, comprising:
[0008] Obtain normal battery test data and battery data to be diagnosed;
[0009] Construct an equivalent circuit model of internal short-circuit fault in the battery based on normal battery test data;
[0010] Inputting the battery data to be diagnosed into a prediction model to predict the future voltage and future state of charge data of the battery to be diagnosed; the prediction model is trained using normal battery test data;
[0011] According to the future voltage and future state of charge data, whether further fault diagnosis is needed is evaluated. If further diagnosis is needed, the future voltage and future state of charge data are input into the constructed battery internal short circuit fault equivalent circuit model to predict the future short circuit resistance value;
[0012] Evaluate the severity of the internal short-circuit fault based on the future short-circuit resistance value.
[0013] A second aspect of the present invention provides a battery short circuit fault diagnosis system based on future parameter prediction, comprising:
[0014] A data acquisition module, configured to acquire normal battery test data and battery data to be diagnosed;
[0015] A model building module is configured to build an equivalent circuit model of a short circuit fault in a battery based on normal battery test data;
[0016] A prediction module is configured to input the battery data to be diagnosed into a prediction model to predict the future voltage and future state of charge data of the battery to be diagnosed; the prediction model is trained using normal battery test data;
[0017] An evaluation module is configured to evaluate whether further fault diagnosis is needed based on the future voltage and the future state of charge data. If further diagnosis is needed, the future voltage and the future state of charge data are input into a constructed battery internal short circuit fault equivalent circuit model to predict the future short circuit resistance value;
[0018] The diagnosis module is configured to determine the severity of the internal short-circuit fault according to the future short-circuit resistance value.
[0019] According to a third aspect of the present invention, an electronic device is provided, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to complete the steps of the above-mentioned battery short circuit fault diagnosis method based on future parameter prediction.
[0020] According to a fourth aspect of the present invention, a computer-readable storage medium is provided for storing computer instructions, which, when executed by a processor, complete the steps of the above-mentioned battery short circuit fault diagnosis method based on future parameter prediction.
[0021] According to a fifth aspect of the present invention, a computer program product is provided, comprising a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned battery short circuit fault diagnosis method based on future parameter prediction.
[0022] Compared with the prior art, the present invention has the following beneficial effects:
[0023] The present invention provides a battery short-circuit fault diagnosis method and system based on future parameter prediction. A prediction model is trained by collecting normal battery test data, and the future voltage and charge state of a battery to be diagnosed can be predicted by the model; preliminary fault diagnosis can be achieved by evaluating the predicted voltage and charge state; then the predicted future voltage and charge state are input into a constructed battery short-circuit fault equivalent circuit model to achieve more accurate and rapid future current prediction; the short-circuit resistance value is automatically updated and iterated to reduce the error between the predicted current and the measured current until it is below a threshold value, and the estimated future short-circuit resistance value can achieve an accurate evaluation of the degree of the short-circuit fault and grasp the development trend of the short-circuit fault.
[0024] The method proposed in the present invention can complete the training of the model using only normal battery data, thus overcoming the problem that the traditional machine learning method cannot effectively train the model due to the lack of high-quality fault data.
[0025] The present invention first inputs the battery data into a trained regression prediction model to obtain a predicted value to achieve a preliminary diagnosis, and then inputs the predicted value into an equivalent circuit model to estimate future short-circuit resistance changes to further evaluate the degree of internal short circuit, thereby achieving a faster diagnosis speed and higher diagnostic accuracy.
[0026] The method proposed in the present invention has the advantages of both data-driven and model-based fault diagnosis methods, forming a complementary relationship; the predicted value of the neural network model is used as the input of the equivalent circuit model to improve the anti-interference ability of the model and realize the prediction of the changing trend of short-circuit faults. At the same time, the use of the equivalent circuit model can solve the problem that the neural network model is difficult to accurately assess the severity of the fault when there is a lack of high-quality fault data.
[0027] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The accompanying drawings in the specification, which constitute a part of the present invention, 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 improper limitations on the present invention.
[0029] Figure 1 Schematic diagram of the method in Embodiment 1 of the present invention;
[0030] Figure 2 is a flow chart of the fault diagnosis method;
[0031] Figure 3 Schematic diagram of the equivalent model of internal short circuit in the battery. DETAILED DESCRIPTION
[0032] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0033] Embodiment 1
[0034] like Figure 1-Figure 2 As shown, the first embodiment of the present invention provides a battery short circuit fault diagnosis method based on future parameter prediction, including:
[0035] S1. Obtain normal battery test data and battery data to be diagnosed;
[0036] S2. Construct an equivalent circuit model of internal short circuit fault in the battery based on normal battery test data;
[0037] S3, inputting the battery data to be diagnosed into a prediction model to predict the future voltage and future state of charge data of the battery to be diagnosed; the prediction model is trained using normal battery test data;
[0038] S4. Evaluate whether further fault diagnosis is needed based on the future voltage and future state of charge data. If further diagnosis is needed, input the future voltage and future state of charge data into the constructed battery internal short circuit fault equivalent circuit model to predict the future short circuit resistance value.
[0039] S5. Evaluate the severity of the internal short-circuit fault based on the future short-circuit resistance value.
[0040] In step S1, the normal battery is consistent with the battery model to be diagnosed, and the normal battery test data is used to construct an internal short-circuit fault equivalent circuit model and a training prediction model. Select multiple normal batteries, perform charge and discharge cycle experiments under selected working conditions, and collect battery test data. The number of batteries n and the cycle conditions are selected according to actual applications. The cycle conditions of the working conditions include the current rate of battery charging and discharging, discharge depth, temperature and cut-off voltage; the collected normal battery test data and the battery data to be diagnosed include but are not limited to each battery voltage, current, state of charge (SOC) data and the corresponding data collection time.
[0041] In step S2, an equivalent circuit model of a short circuit fault in a battery is constructed, and the model parameters are identified using battery data. The specific steps are:
[0042] S21. Construct a first-order RC equivalent circuit model and establish parameter identification equations. Figure 3As shown in the figure, the internal short-circuit equivalent circuit model is selected as the first-order RC equivalent circuit model to reduce the calculation requirements. According to Kirchhoff's law, the polarization voltage U p and terminal voltage U t The dynamic change law of can be expressed as:
[0043]
[0044] U t (t) = U oc (SOC)+U p (t)+R0(t)(I L (t)-I f (t))
[0045] In the formula, R p is the polarization resistance, C p is a polarized capacitor, R0 represents the internal resistance, U oc and U t Represent the open circuit voltage and terminal voltage of the battery, I L is the battery input current, I f is the short-circuit current. oc Related to SOC, the OCV-SOC curve is divided into N small segments, U oc It can be expressed as:
[0046] U oc (SOC) = a i SOC+b i
[0047] In the formula, i=1...N, a i and b i They represent the slope and y-intercept of the OCV-SOC curve respectively. The SOC change rate can be expressed as:
[0048]
[0049] In the formula, C n is the battery capacity, and ρ is the Coulomb efficiency constant. According to the above formula, the continuous time state space model can be obtained:
[0050]
[0051] y(t)=C i x(t)+D(t)w(t),i=1…N
[0052] In the formula, x(t)=[x1(t),x2(t)]=[U p (t),SOC(t)] Trepresents the state vector of the battery power system; w(t) represents the unknown input current of the system. For example, in the normal state, w(t) = I L (t), in the fault state, w(t)=I L (t)-I f (t); y(t) = U t (t)-b i is the available measured output of the battery system. System and output matrices A(t), D(t), C i , B(t) is defined as follows:
[0053]
[0054] C i =[1,a i ],D(t)=R0(t)
[0055] S22: Using the measured voltage and current data of the normal battery, an optimization algorithm including but not limited to a genetic algorithm is used to identify the model parameters, and the average value of the identification results can be used as the final value of the model parameters. The corresponding model is:
[0056]
[0057] y(t)=C i x(t)+Dw(t),i=1…N
[0058] A, B, and D are defined as follows:
[0059]
[0060]
[0061] in, R0, R p , C p Identification parameters.
[0062] In step S3, the prediction model uses a regression prediction model, including but not limited to long short-term memory neural networks and time domain convolutional neural networks that can be used for sequence modeling. The data of each normal battery is processed to obtain samples for training the model, and the obtained samples are used to train the regression prediction neural network model to predict the future voltage and state of charge. The sample acquisition process includes:
[0063] S31. Use noise reduction methods to remove gross errors in the data.
[0064] S32: Process the measured voltage data and state of charge data to obtain voltage increment characteristics.
[0065] S33. Normalize each battery data (including voltage, current, state of charge, voltage increment characteristics):
[0066]
[0067] Where X is the original data, X′ is the normalized data, max(X) is the maximum value in the original data, and min(X) is the minimum value in the original data.
[0068] S34. Process the data using a sliding window, taking voltage, current, and voltage increment as input features, and future voltage and future state of charge as labels to jointly form samples for training the neural network model. The input matrix A of the neural network is expressed as:
[0069]
[0070] where k is the time step, U t , I t , ΔU t are the voltage, current, and voltage increment at time step t, respectively.
[0071] Input the processed data of the battery to be diagnosed into the trained prediction model to obtain the predicted future voltage U pre and the future state of charge data SOC pre .
[0072] In step S4, preliminarily diagnose the predicted data and the measured data of the battery to be diagnosed, and judge whether further diagnosis is needed based on the evaluation results. The battery to be diagnosed is of the same model as the battery used for training the model. Use the residual between the predicted voltage and the measured voltage and the corresponding relationship between the residual and the state of charge to comprehensively evaluate the battery and judge whether further diagnosis is needed. If:
[0073] U pre -U raw >TH1
[0074] Then it is determined as an external short circuit fault or a very serious internal short circuit fault, and a serious alarm is immediately issued. If:
[0075] TH2 < U pre -U raw < TH1 or SOC pre -SOC raw > αC
[0076] Then it is determined that a fault has occurred, and the data is input into the constructed equivalent circuit model for further diagnosis. Where U pre is the predicted future voltage, U raw is the current measured voltage, and SOC rawis the latest state of charge measured using the ampere-hour integration method, TH1 and TH2 are the set multi-level thresholds (selected according to actual conditions), α is the set multiplier greater than 1 to eliminate the influence of noise, and C is the battery discharge capacity calculated by the ampere-hour integration method using the known operating current to the predicted time point. The calculation formula of C is:
[0077]
[0078] Where C N is the rated capacity of the battery, ρ is the charge and discharge efficiency, I raw is the set operating current, t1 and t2 are the latest measurement time and the prediction time respectively.
[0079] If further diagnosis is required, the predicted voltage and state of charge data are input into the equivalent circuit model, and the predicted current can be obtained by constructing an observer. The specific structure of the observer is:
[0080]
[0081]
[0082] Where i = 1…N, is the state estimate of the full battery system state x(t), is an estimate of the unknown input current w(t). Finally, the gain matrix P is always bounded. i and G must meet the following conditions:
[0083] (1) G = BD -1 , (2) P i =A-GC i , i=1…N is Hurwitz stable.
[0084] This embodiment uses the above-mentioned observer to complete the prediction of future current. Among them, the predicted current estimated by the observer has higher predictability and accuracy compared with the direct prediction using the equivalent circuit model due to the addition of predicted voltage and state of charge as input. If an internal short circuit fault exists, the predicted current will deviate from the set future operating current, which is included in the operating conditions set when the battery is tested. Therefore, the mean absolute value of the residual between the current estimated value (predicted current) and the set operating current value can be used as a fault indicator.
[0085] Automatically iterate and update the short-circuit resistance value in the equivalent circuit model, that is, if the predicted current is greater than the known future operating current, increase the short-circuit resistance value, otherwise decrease it, until the error between the predicted future current and the future operating current is stabilized below the set threshold, and obtain the future short-circuit resistance value. The error between the predicted current and the future operating current is characterized by including but not limited to the mean square error (MSE), and the specific expression is as follows:
[0086]
[0087] Among them, MSE k It represents the mean square error of the battery when the sliding window length is k. is the future operating current, is the predicted future current. When updating the resistance in the equivalent circuit model, the error in the future period should be considered to obtain a high-precision short-circuit resistance estimate.
[0088] In step S5, the severity and development trend of the internal short-circuit fault can be evaluated according to the short-circuit resistance value. The estimated future short-circuit resistance value can be used to evaluate the fault severity. The smaller the short-circuit resistance value, the more serious the fault. The fault development trend can be predicted by the change of the short-circuit resistance value in the future. If the circuit resistance value has a decreasing trend, it means that the fault has an aggravating trend.
[0089] Embodiment 2
[0090] This embodiment provides a battery short circuit fault diagnosis system based on future parameter prediction, including:
[0091] A data acquisition module, configured to acquire normal battery test data and battery data to be diagnosed;
[0092] A model building module is configured to build an equivalent circuit model of a short circuit fault in a battery based on normal battery test data;
[0093] A prediction module is configured to input the battery data to be diagnosed into a prediction model to predict the future voltage and future state of charge data of the battery to be diagnosed; the prediction model is trained using normal battery test data;
[0094] An evaluation module is configured to evaluate whether further fault diagnosis is needed based on the future voltage and the future state of charge data. If further diagnosis is needed, the future voltage and the future state of charge data are input into a constructed battery internal short circuit fault equivalent circuit model to predict the future short circuit resistance value;
[0095] The diagnosis module is configured to determine the severity of the internal short-circuit fault according to the future short-circuit resistance value.
[0096] It should be noted here that the various modules in this embodiment correspond one-to-one to the steps of the method in Example 1, and the specific implementation process is the same, which will not be repeated here.
[0097] Embodiment 3
[0098] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to complete the steps of the method in the first embodiment.
[0099] Embodiment 4
[0100] This embodiment provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps of the method in the first embodiment are completed.
[0101] Embodiment 5
[0102] This embodiment provides a computer program product, including a computer program / instruction, characterized in that the computer program / instruction implements the steps of the method in the first embodiment when executed by a processor.
[0103] 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 battery short circuit fault diagnosis method based on future parameter prediction, characterized in that: include: Obtain normal battery test data and battery data to be diagnosed; Construct an equivalent circuit model of internal short-circuit fault in the battery based on normal battery test data; Inputting the battery data to be diagnosed into a prediction model to predict the future voltage and future state of charge data of the battery to be diagnosed; the prediction model is trained using normal battery test data; According to the future voltage and future state of charge data, whether further fault diagnosis is needed is evaluated. If further diagnosis is needed, the future voltage and future state of charge data are input into the constructed battery internal short circuit fault equivalent circuit model to predict the future short circuit resistance value; Evaluate the predicted data and measured data of the battery to be diagnosed for preliminary diagnosis, and determine whether further diagnosis is needed based on the evaluation results; use the residual of the predicted voltage and the measured voltage and the corresponding relationship between the residual and the state of charge to comprehensively evaluate the battery to determine whether further diagnosis is needed; if the difference between the future voltage and the current voltage is greater than the first threshold: YOU pre -YOU raw >TH1 It is determined that a first fault occurs and an alarm is issued; wherein TH1 is a first threshold, and the first fault is an external short circuit fault or an extremely serious internal short circuit fault; if the difference between the future voltage and the current voltage is less than the first threshold and greater than the second threshold, or the difference between the future state of charge and the measured state of charge is greater than the third threshold: TH2<U pre -U raw <TH1 or SOC pre -SOC raw >αC It is determined that a second fault has occurred, and the data is input into the constructed equivalent circuit model for further diagnosis; wherein TH2 is the second threshold value, U pre is the predicted future voltage, U raw is the current measured voltage, SOC raw is the state of charge measured by the ampere-hour integration method. The third threshold is calculated by the battery discharge amount and the set rate. α is the set rate, and C is the battery discharge amount to the predicted time point calculated by the ampere-hour integration method using the known operating current. The calculation formula of C is: In the formula, C N is the rated capacity of the battery, ρ is the charge and discharge efficiency, I raw is the set working current, t1 and t2 are the latest measurement time and the prediction time respectively; If further diagnosis is required, the predicted voltage and state of charge data are input into the equivalent circuit model, and the predicted current is obtained through the observer; The prediction model uses a regression prediction model; the data of each normal battery is processed to obtain samples for training the prediction model, and the obtained samples are used to train the prediction model to predict the future voltage and state of charge; The method of inputting the future voltage and the future state of charge data into the constructed battery internal short-circuit fault equivalent circuit model to predict the future short-circuit resistance value includes: inputting the future voltage and the future state of charge data into the constructed battery internal short-circuit fault equivalent circuit model to obtain the predicted current through an observer; iteratively updating the short-circuit resistance value in the equivalent circuit model based on the difference between the predicted current and the set working condition current; and obtaining the future short-circuit resistance value when the difference between the predicted current and the set working condition current is lower than a set threshold; Evaluate the severity of the internal short-circuit fault based on the future short-circuit resistance value.
2. A battery short circuit fault diagnosis method based on future parameter prediction as claimed in claim 1, characterized in that: The battery internal short-circuit fault equivalent circuit model is a first-order RC equivalent circuit model. Normal battery test data is used to perform parameter identification on the model, and the average value of the identification results is used as the model parameter.
3. A battery short circuit fault diagnosis method based on future parameter prediction as claimed in claim 1, characterized in that: The evaluation of the severity of the internal short-circuit fault according to the future short-circuit resistance value includes: if the short-circuit resistance value is smaller, the internal short-circuit fault is more severe; and if the circuit resistance value has a trend of decreasing, the internal short-circuit fault has a trend of aggravating.
4. A battery short circuit fault diagnosis system based on future parameter prediction, characterized in that: include: A data acquisition module, configured to acquire normal battery test data and battery data to be diagnosed; A model building module is configured to build an equivalent circuit model of a short circuit fault in a battery based on normal battery test data; A prediction module is configured to input the battery data to be diagnosed into a prediction model to predict the future voltage and future state of charge data of the battery to be diagnosed; the prediction model is trained using normal battery test data; An evaluation module is configured to evaluate whether further fault diagnosis is needed based on the future voltage and the future state of charge data. If further diagnosis is needed, the future voltage and the future state of charge data are input into a constructed battery internal short circuit fault equivalent circuit model to predict the future short circuit resistance value; Evaluate the predicted data and measured data of the battery to be diagnosed for preliminary diagnosis, and determine whether further diagnosis is needed based on the evaluation results; use the residual of the predicted voltage and the measured voltage and the corresponding relationship between the residual and the state of charge to comprehensively evaluate the battery to determine whether further diagnosis is needed; if the difference between the future voltage and the current voltage is greater than the first threshold: YOU pre -YOU raw >TH1 It is determined that a first fault occurs and an alarm is issued; wherein TH1 is a first threshold, and the first fault is an external short circuit fault or an extremely serious internal short circuit fault; if the difference between the future voltage and the current voltage is less than the first threshold and greater than the second threshold, or the difference between the future state of charge and the measured state of charge is greater than the third threshold: TH2<U pre -U raw <TH1 or SOC pre -SOC raw >αC It is determined that a second fault has occurred, and the data is input into the constructed equivalent circuit model for further diagnosis; wherein TH2 is the second threshold value, U pre is the predicted future voltage, U raw is the current measured voltage, SOC raw is the state of charge measured by the ampere-hour integration method. The third threshold is calculated by the battery discharge amount and the set rate. α is the set rate, and C is the battery discharge amount to the predicted time point calculated by the ampere-hour integration method using the known operating current. The calculation formula of C is: In the formula, C N is the rated capacity of the battery, ρ is the charge and discharge efficiency, I raw is the set working current, t1 and t2 are the latest measurement time and the prediction time respectively; If further diagnosis is required, the predicted voltage and state of charge data are input into the equivalent circuit model, and the predicted current is obtained through the observer; The prediction model uses a regression prediction model; the data of each normal battery is processed to obtain samples for training the prediction model, and the obtained samples are used to train the prediction model to predict the future voltage and state of charge; The method of inputting the future voltage and the future state of charge data into the constructed battery internal short-circuit fault equivalent circuit model to predict the future short-circuit resistance value includes: inputting the future voltage and the future state of charge data into the constructed battery internal short-circuit fault equivalent circuit model to obtain the predicted current through an observer; iteratively updating the short-circuit resistance value in the equivalent circuit model based on the difference between the predicted current and the set working condition current; and obtaining the future short-circuit resistance value when the difference between the predicted current and the set working condition current is lower than a set threshold; The diagnosis module is configured to determine the severity of the internal short-circuit fault according to the future short-circuit resistance value.
5. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to complete the steps of the method according to any one of claims 1 to 3.
6. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the steps of the method according to any one of claims 1 to 3.
7. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.
Citation Information
Patent Citations
Method and device for estimating state of charge of battery
CN106716158A
Lithium ion battery pack voltage abnormity fault diagnosis method based on double models
CN113687251A
Battery capacity loss and internal short circuit fault identification method based on feature extraction
CN114910802A
Battery fault diagnosis method and device for energy storage power station and storage medium
CN114994543A
Energy storage battery fault diagnosis method and system based on multi-source information fusion
CN116224076A
