A battery fault prediction method, device, electronic device and storage medium

Abstract

The present application discloses a battery fault prediction method, device, electronic device and storage medium, belonging to the technical field of lithium batteries. The method includes: constructing a neural network model with the charge and discharge parameters of the battery pack as the input and the ideal voltage of the battery pack as the output; obtaining the charge and discharge timing parameter set of the battery pack to be measured and the second curve of the battery cells in the battery pack to be measured, where the second curve is the voltage change curve of the battery cells; sequentially inputting the timing parameters in the charge and discharge timing parameter set into the neural network model to obtain the first curve, where the first curve is the ideal voltage change curve of the battery pack; calculating the class correlation coefficient between the first curve and the second curve; and locating the faulty battery cells and predicting the fault type according to the class correlation coefficient and a preset fault threshold. The present invention locates the faulty battery cells and predicts the fault type by comparing the class correlation between the voltage of the single battery and the ideal voltage during the charge and discharge process, realizing fault prediction at the initial stage of battery faults.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium batteries, and particularly to a battery fault prediction method, device, electronic device and storage medium. Background Art

[0002] Due to advantages such as large energy density and long cycle life, lithium-ion batteries are widely used in different scenarios such as consumer electronics, electric vehicles, distributed energy storage, and large-scale energy storage. Especially in the applications in the fields of electric vehicles, distributed energy storage, and large-scale energy storage, to meet the requirements of current, voltage, power, and energy, a large number of monomers often need to be combined into battery packs, battery modules, and even battery clusters through series and parallel means. This will have a large number of connection components, greatly increasing the complexity of the system, resulting in an increased probability of various types of failures and increasing potential safety hazards. Therefore, implementing accurate and reliable fault diagnosis is the key to ensuring the safe, stable, and reliable operation of the battery system.

[0003] In the prior art, relevant standards have been put forward for the BMS fault alarm system. The battery management system (BMS, Battery Management System) is responsible for monitoring the state of the lithium battery system, active balancing, charge and discharge control, fault alarm, etc., to ensure the safe and efficient operation of the battery. However, as the most basic guarantee for ensuring the safe operation of the battery system, when the alarm occurs, the battery fault has developed to a relatively serious stage, causing greater losses to the battery system and posing higher requirements for the structure, fire protection, etc. of the battery system.

[0004] Therefore, there is an urgent need for a battery fault prediction method that can, at the early stage of fault occurrence, locate and predict the faulty monomer according to the analysis of the voltage change curve during the charge and discharge process. Summary of the Invention

[0005] In view of this, it is necessary to provide a battery fault prediction method, device, electronic device and storage medium that can, at the early stage of fault occurrence, locate and predict the faulty monomer according to the analysis of the voltage change curve during the charge and discharge process.

[0006] To solve the above technical problems, on the one hand, the present invention provides a battery fault prediction method, including:

[0007] Taking the charge and discharge parameters of the battery pack as input and the ideal voltage of the battery pack as output, a neural network model is constructed;

[0008] Obtaining the charge and discharge timing parameter set of the battery pack to be tested and the second curve of the battery monomers in the battery pack to be tested, where the second curve is the voltage change curve of the battery monomers;

[0009] Sequentially input the timing parameters in the charge-discharge timing parameter set into the neural network model to obtain a first curve, which is the ideal voltage change curve of the battery pack;

[0010] Calculate the class correlation coefficient between the first curve and the second curve;

[0011] Locate the faulty battery cell and predict the fault type according to the class correlation coefficient and the preset fault threshold.

[0012] In a possible implementation manner, a neural network model is constructed with the charge-discharge parameters of the battery pack as the input and the ideal voltage of the battery pack as the output, including:

[0013] Construct an initial neural network model with the charge-discharge parameters at each sampling time during the charge-discharge process of the battery pack as the input and the ideal voltage at the sampling time of the battery pack as the output. The charge-discharge parameters include the battery pack SOC value, the ambient temperature, and the charge-discharge current;

[0014] Obtain the voltage value, the battery pack SOC value, the charge-discharge current, and the ambient temperature at each sampling time during the charge-discharge process of a battery pack with good performance;

[0015] Iteratively train the initial neural network model according to the battery pack SOC value, the charge-discharge current, the ambient temperature, and the voltage value at each sampling time to generate a first model;

[0016] Optimize the first model based on the AdamW optimization algorithm to generate a battery pack neural network model.

[0017] In a possible implementation manner, the calculation formula of the AdamW optimization algorithm is:

[0018] ,

[0019] where, is the neural network weight independent variable at the current moment, is the neural network weight independent variable at the previous moment, is the learning rate, is the adaptive adjustment parameter of the learning rate, is the cumulative gradient, is the weight decay parameter.

[0020] In a possible implementation manner, the timing parameters include the battery pack SOC value, the ambient temperature, the charge-discharge current, and the sampling time. Sequentially input the timing parameters in the charge-discharge timing parameter set into the neural network model to obtain a first curve, including:

[0021] Input the battery pack SOC value, ambient temperature, and charge and discharge current in the timing parameters into the neural network model to obtain the ideal voltage value at each sampling time point;

[0022] Generate a first curve based on the ideal voltage at each sampling time point and its corresponding sampling time.

[0023] In a possible implementation manner, the calculation formula for the class correlation coefficient between the first curve and the second curve is:

[0024] ,

[0025] where, is the class correlation coefficient between the ideal voltage change curve of the battery pack and the voltage change curve of the battery cell, is the ideal voltage value at the th sampling time of the ideal voltage change curve of the battery pack, is the voltage value at the th sampling time of the voltage change curve of the battery cell, is the total number of sampling times.

[0026] In a possible implementation manner, determining the battery inconsistency fault type according to the class correlation coefficient and a preset fault threshold includes:

[0027] When the class correlation coefficient is within the first preset fault threshold interval, it is determined that there is no battery inconsistency fault;

[0028] When the class correlation coefficient is within the second preset fault threshold interval, it is determined that the battery fault is a first-level inconsistency fault;

[0029] When the class correlation coefficient is within the third preset fault threshold interval, it is determined that the battery fault is a second-level inconsistency fault.

[0030] In a possible implementation manner, it further includes:

[0031] Determine the voltage change rate and temperature change rate of the battery cell within a preset time period during the charge and discharge process;

[0032] Based on a preset voltage change rate alarm threshold and temperature change rate alarm threshold, alarm the battery cell according to the voltage change rate and temperature change rate of the battery cell, and count the alarm duration;

[0033] When the alarm duration exceeds the preset alarm duration threshold, the battery cell is diagnosed as having a sudden internal short circuit fault.

[0034] In a second aspect, the present invention further provides a battery fault prediction device, including:

[0035] A model construction module, configured to construct a neural network model by using the charge and discharge parameters of the battery pack as inputs and the ideal voltage of the battery pack as an output;

[0036] A data acquisition module, configured to acquire a charge and discharge timing parameter set of the battery pack to be tested and a second curve of battery cells in the battery pack to be tested, where the second curve is a voltage change curve of the battery cells;

[0037] An ideal curve generation module, configured to sequentially input the timing parameters in the charge and discharge timing parameter set into the neural network model to obtain a first curve, where the first curve is an ideal voltage change curve of the battery pack;

[0038] A class correlation coefficient calculation module, configured to calculate the class correlation coefficient between the first curve and the second curve;

[0039] A fault location and prediction module, configured to locate a faulty battery cell and predict a fault type according to the class correlation coefficient and a preset fault threshold.

[0040] In a third aspect, the present invention further provides an electronic device, including a memory and a processor. Among them, the memory is configured to store programs and data; the processor is coupled to the memory and is configured to execute the programs stored in the memory to implement the battery fault prediction method as described above, and / or implement the battery fault prediction as described above.

[0041] In a fourth aspect, the present invention further provides a computer storage medium, configured to store computer-readable programs or instructions. When the programs or instructions are executed by a processor, the battery fault prediction method as described above can be implemented.

[0042] The beneficial effects of the present invention are as follows: First, a neural network model is constructed with the charge and discharge parameters of the battery pack as the input and the ideal voltage of the battery pack as the output. Then, the charge and discharge timing parameter set of the battery pack to be tested and the second curve of the battery cells in the battery pack to be tested are obtained. Then, the timing parameters in the charge and discharge timing parameter set are sequentially input into the neural network model to obtain a first curve, which is the ideal voltage change curve of the battery pack. Finally, the class correlation coefficient between the first curve and the second curve is determined, and according to the class correlation coefficient and the preset fault threshold, the faulty battery cell is located and the fault type is predicted. The present invention predicts the ideal voltage of the battery pack according to the charge and discharge parameters of the battery pack by constructing a model, generates an ideal voltage curve, then obtains the voltage change curve of the battery cell during charge and discharge, calculates the class correlation coefficient between these two curves, locates the faulty battery cell according to the class correlation coefficient, and predicts the fault type. By analyzing the class correlation between the ideal voltage curve of the battery pack and the voltage change curve of the battery cell during charge and discharge, the present invention predicts battery faults, can accurately locate and predict faults in the early stage of fault occurrence, and improves the safety and stability of the battery pack. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0044] Figure 1 It is a schematic flowchart of an embodiment of the battery fault prediction method provided by the present invention;

[0045] Figure 2 For the present invention Figure 1 It is a schematic flowchart of an embodiment of step S101;

[0046] Figure 3 For the present invention Figure 1 It is a schematic flowchart of an embodiment of step S102;

[0047] Figure 4 For the present invention Figure 1 It is a schematic flowchart of an embodiment of step S105;

[0048] Figure 5 It is a schematic flowchart of an embodiment of the sudden internal short circuit fault provided by the present invention;

[0049] Figure 6 It is a schematic structural diagram of an embodiment of the battery fault prediction electronic device provided by the present invention;

[0050] Figure 7 Schematic diagram of an embodiment structure of the battery fault prediction storage medium provided by the present invention. Specific embodiments

[0051] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present invention.

[0052] In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more.

[0053] In the embodiments of the present invention, the descriptions such as "first" and "second" are only for the purpose of description, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Therefore, the technical features defined with "first" and "second" may explicitly or implicitly include at least one of such features.

[0054] Referring to "embodiments" herein means that the specific features, structures, or characteristics described in connection with the embodiments may be included in at least one embodiment of the present invention. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0055] The present invention provides a battery fault prediction method, device, electronic device, and storage medium, which will be described separately below.

[0056] Figure 1 Schematic diagram of an embodiment process of the battery fault prediction method provided by the present invention, as Figure 1 shown, the battery fault prediction method includes:

[0057] S101. Using the charge and discharge parameters of the battery pack as input and the ideal voltage of the battery pack as output, a neural network model is constructed;

[0058] S102. Obtaining the charge and discharge timing parameter set of the battery pack to be tested and the second curve of the battery cells in the battery pack to be tested, where the second curve is the voltage change curve of the battery cells;

[0059] S103. Sequentially inputting the timing parameters in the charge and discharge timing parameter set into the neural network model to obtain a first curve, where the first curve is the ideal voltage change curve of the battery pack;

[0060] S104. Calculate the class correlation coefficient of the first curve and the second curve;

[0061] S105. Locate the faulty battery cell and predict the fault type according to the class correlation coefficient and the preset fault threshold.

[0062] It should be noted that the battery pack in this example is applied to lithium battery systems including battery management systems (BMS) such as electric ships and electric vehicles, and a battery charger / discharger integrated machine is used to charge and discharge the lithium battery pack; the battery management system (BMS) is used to collect and monitor the charge and discharge parameter data of the battery pack and each battery cell, a neural network model is constructed through a model building tool on a mobile terminal, the charge and discharge parameters of the battery cell and the corresponding time series are analyzed by data analysis software to draw a voltage change curve, the class correlation coefficient between the curves is calculated and analyzed, and the class correlation coefficients are analyzed and compared; the final calculation results, as well as the results of locating the faulty battery cell and predicting the fault type, are displayed through the mobile terminal. The mobile terminal can be various electronic devices with a display screen and supporting data analysis and model building, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc. The battery fault prediction method provided in this embodiment can be implemented through applications, applets, or web pages installed on the mobile terminal.

[0063] Furthermore, it should be noted that under a specific ambient temperature, the battery pack is charged and discharged at a constant current, and the charge and discharge parameters of the battery pack and each battery cell are collected based on the battery management system (BMS). The charge and discharge parameters of the battery pack include the state of charge (SOC) of the battery pack, the battery pack voltage, and the sampling time, and the charge and discharge parameters of the battery cell include the battery cell voltage and the sampling time; the collected data is cleaned and normalized; the interval of each sampling time is set according to experimental needs, and can be set to 0.5 seconds, 1 second, 2 seconds, or 5 seconds, etc. In this embodiment, samples are taken every 1 second. The shorter the sampling time interval, the more accurate the calculation result.

[0064] Specifically, based on the LSTM neural network, the ideal voltage prediction model is constructed with the battery pack SOC, ambient temperature, and charge and discharge current as inputs and the ideal voltage of the battery pack as output. The ideal voltage at the sampling time under the ideal state is predicted according to the battery pack SOC, ambient temperature, and charge and discharge current obtained at the current sampling time of the battery pack to be tested. The ideal voltage is the voltage at the sampling time when the consistency and battery performance of the battery pack are good. According to the time series, the specific charge and discharge process is sampled and predicted in sequence, and the voltage change curve under the ideal state in the specific charge and discharge process can be obtained; at the same time, the voltage change curve of each battery cell is obtained by monitoring each battery cell through the BMS, and the class correlation coefficient and Euclidean distance between the voltage change curve of each battery cell and the voltage change curve under the ideal state are analyzed, so that the deviation degree of the voltage change of each battery cell can be intuitively obtained, and then the battery cell is predicted whether there is a fault and the cause of the fault, so as to locate the faulty battery cell, and the faulty battery cell is further analyzed through the size of the class correlation coefficient, and its fault type is predicted, so as to achieve accurate prediction of the fault type.

[0065] This embodiment constructs a model to predict the ideal voltage of the battery pack according to the battery pack charging and discharging parameters, generates an ideal voltage curve, obtains the voltage change curve of the battery cell during the charging and discharging process, calculates the class correlation coefficient between the two curves, locates the faulty battery cell according to the class correlation coefficient, and predicts the fault type. The present invention predicts battery faults by analyzing the class correlation of the voltage change curves of the battery pack and the battery cell during the charging and discharging process, and can accurately locate and predict faults in the early stage of the fault, thereby improving the safety and stability of the battery pack.

[0066] In some embodiments of the present invention, Figure 2 As shown, Figure 2 The present invention provides Figure 1 The flowchart of an embodiment of step S101 in the embodiment includes:

[0067] S201, taking the charge and discharge parameters at each sampling time during the charge and discharge process of the battery pack as input and the ideal voltage of the battery pack at the sampling time as output, constructing an initial neural network model, wherein the charge and discharge parameters include the battery pack SOC value, ambient temperature and charge and discharge current;

[0068] S202, obtaining the voltage value, battery pack SOC value, charge and discharge current and ambient temperature of a battery pack with good performance at each sampling time during the charge and discharge process;

[0069] S203, iteratively training the initial neural network model according to the battery pack SOC value, charge and discharge current, ambient temperature and voltage value at each sampling time to generate a first model;

[0070] S204. Optimize the first model based on the AdamW optimization algorithm to generate a neural network model for the battery pack.

[0071] It should be noted that the SOC of the battery pack describes the remaining power state of the battery pack. During the charging process, as the SOC increases, the chemical reactions inside the battery gradually tend to saturation, and the voltage will also rise accordingly. During the discharging process, as the SOC decreases, the battery releases energy and the voltage gradually decreases. The ambient temperature has a significant impact on the performance of the battery. At high temperatures, the chemical reaction rate inside the battery accelerates, and the charge transfer is smoother, resulting in an increase in the battery voltage. On the contrary, at low temperatures, the chemical reaction rate inside the battery slows down, the charge transfer is blocked, and the battery voltage decreases. The magnitude of the charge and discharge current directly affects the average voltage of the battery. During the charging process, a larger charging current will cause more heat and voltage drop inside the battery, thereby reducing the average voltage of the battery. Similarly, during the discharging process, a larger discharging current will also cause the average voltage of the battery to drop faster. During each time period, the SOC, ambient temperature, and charge and discharge current of the battery jointly affect the average voltage of the battery.

[0072] Specifically, construct an initial neural network model. The input layer contains three neurons, namely the SOC value of the battery pack, the ambient temperature, and the charge and discharge current. The output layer contains one neuron, which outputs the ideal voltage of the battery pack. Select normal battery packs with good battery performance and consistency, perform constant current charge and discharge operations on them at a specific ambient temperature, and based on the BMS system, monitor the SOC, charge and discharge current, ambient temperature, and battery voltage of the battery pack during the charge and discharge process. During this charge and discharge process, sample according to the preset sampling time. After cleaning and normalizing all the data, divide it into a training set and a test set. Iteratively train the initial neural network model through the training set, select an appropriate loss function, such as the mean square error as the loss function for the regression problem, but not limited to this loss function, and use the AdamW optimization algorithm to optimize the neural network model to generate the final neural network model, which can obtain the ideal voltage of the battery pack during the charge and discharge process based on the SOC value, charge and discharge current, and ambient temperature of the battery pack at the sampling time.

[0073] In this embodiment, by constructing a neural network model, predicting the ideal voltage of the battery pack according to the SOC, ambient temperature, and charge and discharge current of the battery pack, and using the AdamW optimization algorithm to optimize the neural network model, the accuracy of the model prediction is improved. At the same time, using the trained model to predict the ideal voltage greatly improves the efficiency of the model prediction, and improves the accuracy and efficiency of battery fault prediction.

[0074] In some embodiments of the present invention, the calculation formula of the AdamW optimization algorithm is:

[0075] ,

[0076] wherein, is the neural network weight independent variable at the current moment, is the neural network weight independent variable at the previous moment, is a decimal constant, is the learning rate, is the adaptive adjustment parameter of the learning rate, is the cumulative gradient, is the weight decay parameter.

[0077] Specifically, in the AdamW optimization algorithm, is a decimal constant used to prevent the denominator from being zero and ensure numerical stability, is the cumulative gradient, that is, the first moment estimate after variance correction, representing the moving average of the gradient, which helps to accelerate convergence, is the second moment estimate after bias correction, which represents the moving average of the square of the gradient and is used to adjust the learning rate to achieve the effect of adaptive learning rate, is the weight decay parameter used to control the intensity of weight decay and helps to prevent model overfitting. The AdamW optimization algorithm improves the convergence speed and generalization ability of the model by improving the processing method of weight decay.

[0078] In some embodiments of the present invention, as Figure 3 shown, Figure 3 is the flow schematic diagram of an embodiment of step S102 provided by the present invention. The timing parameter set includes the battery pack SOC value, ambient temperature, charge and discharge current, and sampling time. The timing parameters in the charge and discharge timing parameter set are input into the neural network model in sequence to obtain the first curve, including: Figure 1 The battery pack SOC value, ambient temperature, and charge and discharge current in the timing parameters are input into the neural network model to obtain the ideal voltage values at each sampling time point;

[0079] S301. Input the battery pack SOC value, ambient temperature, and charge and discharge current in the timing parameters into the neural network model to obtain the ideal voltage values at each sampling time point;

[0080] S302. Generate the first curve according to the ideal voltage at each sampling time point and its corresponding sampling time.

[0081] Specifically, when the battery pack to be tested is charged and discharged at a constant current under a specific ambient temperature, based on the BMS system, the SOC value of the battery pack is sampled at a preset sampling time. Based on the neural network model, the battery pack SOC value, ambient temperature, and charge and discharge current at each sampling time are input to obtain the ideal voltage value corresponding to the sampling time, and the ideal voltage change curve of the battery pack during the charge and discharge process is obtained according to each sampling time and its corresponding ideal voltage value.

[0082] In this embodiment, a neural network model is used to predict the ideal voltage value of the battery pack to be tested and generate an ideal voltage curve, providing a data basis for battery fault prediction and improving the accuracy of fault prediction.

[0083] In some embodiments of the present invention, the calculation formula for the class correlation coefficient of the first curve and the second curve is:

[0084] ,

[0085] where is the class correlation coefficient between the ideal voltage change curve of the battery pack and the voltage change curve of the battery cell, is the ideal voltage value of the ideal voltage change curve of the battery pack at the th sampling time, is the voltage value of the voltage change curve of the battery cell at the th sampling time, is the total number of sampling times.

[0086] Specifically, the class correlation coefficient algorithm ICC is used to calculate the similarity of two columns of data sets, and its formula is:

[0087] ,

[0088] ,

[0089] ,

[0090] where is the class correlation coefficient of the two columns of data sets, is the th data of the first column of data sets, is the th data of the second column of data sets. There are N data in both the first column of data sets and the second column of data sets. is the average value of all data in the first column of data sets and the second column of data sets, is the variance of all data sets in the first column of data sets and the second column of data sets;

[0091] According to the formula of the above-mentioned class correlation coefficient algorithm ICC, the calculation formula of the correlation coefficient between the battery cell voltage change curve and the ideal voltage curve of the battery pack changing with time is finally obtained, which is used to analyze the deviation between the battery cell voltage and the ideal voltage of the battery pack at a certain moment. This class correlation coefficient is a value between [0, 1], which is used to quantify the correlation between the battery cell voltage and the ideal voltage of the battery pack. The closer this value is to 1, the more ideal the performance of the battery cell is, and the higher the consistency with the ideal voltage of the battery pack, indicating that the performance of the battery cell is better. The closer this value is to 0, the more deviated the voltage change of the battery cell is from the ideal voltage of the battery pack, and the higher the possibility of a fault.

[0092] In this embodiment, the ICC algorithm is used to evaluate the correlation between the battery cell voltage change and the ideal voltage of the battery pack, providing a data basis for the fault prediction of the battery cell.

[0093] In some embodiments of the present invention, as Figure 4 shown, Figure 4 is a schematic flowchart of an embodiment of step S105 provided by the present invention, including: Figure 1

[0094] S401. When the class correlation coefficient is within the first preset fault threshold interval, it is determined that the battery has no inconsistency fault;

[0095] S402. When the class correlation coefficient is within the second preset fault threshold interval, it is determined that the battery fault is a first-level inconsistency fault;

[0096] S403. When the class correlation coefficient is within the third preset fault threshold interval, it is determined that the battery fault is a second-level inconsistency fault.

[0097] Specifically, when the class correlation coefficient is within the first preset fault threshold interval, that is, the correlation coefficient is greater than or equal to 0.75 and less than or equal to 1, it indicates that the voltage change of the battery cell is highly consistent with the ideal voltage change of the battery pack. At this time, it is determined that the battery has no inconsistency fault; when the class correlation coefficient is within the second preset fault threshold interval, that is, the correlation coefficient is greater than or equal to 0.4 and less than 0.75, it indicates that the voltage change of the battery cell is inconsistent with the ideal voltage change of the battery pack. At this time, it is determined that the battery cell has a first-level inconsistency fault, that is, the battery cell has an inconsistency fault; when the class correlation coefficient is within the second preset fault threshold interval, that is, the correlation coefficient is greater than or equal to 0 and less than 0.4, it indicates that the deviation between the voltage change of the battery cell and the ideal voltage change of the battery pack is large. At this time, it is determined that the battery cell has a second-level inconsistency fault, that is, the battery cell has a serious fault.

[0098] ​In this embodiment, the fault battery cell is accurately located according to the correlation coefficient between the voltage change curve of the battery cell obtained by analysis and calculation and the ideal voltage curve of the battery pack, and the fault type and fault degree are predicted, improving the accuracy of fault prediction.

[0099] In some embodiments of the present invention, it also includes the identification of sudden internal short-circuit faults, such as Figure 5 shown Figure 5 is a schematic flowchart of an embodiment of the sudden internal short-circuit fault provided by the present invention, including:

[0100] S501. Determine the voltage change rate and temperature change rate of the battery cell within a preset time period during the charge and discharge process;

[0101] S502. Based on a preset voltage change rate alarm threshold and temperature change rate alarm threshold, alarm the battery cell according to the voltage change rate and temperature change rate of the battery cell, and count the alarm duration;

[0102] S503. When the alarm duration exceeds the preset alarm duration threshold, the battery cell is diagnosed as having a sudden internal short-circuit fault.

[0103] Specifically, the BMS monitors the voltage and temperature changes of the battery cell during the charge and discharge process, calculates the voltage change rate and temperature change rate within a preset time period; sets a voltage change rate alarm threshold, a temperature change rate alarm threshold, and an alarm duration threshold. When the voltage change rate exceeds the voltage change rate alarm threshold and the temperature change rate exceeds the temperature change rate alarm threshold, the system triggers an alarm. When the alarm duration exceeds the alarm duration threshold, the battery cell is diagnosed as having a sudden internal short-circuit fault.

[0104] Further, in order to further diagnose a faulty battery cell, after determining that a battery cell has a first-level inconsistency fault or a second-level inconsistency fault, the cause of the fault is further analyzed. During the discharge process, the voltage drops rapidly in the early stage, and the voltage change rate is large. After discharging for a period of time, the voltage enters a stage of slow change, that is, the plateau period, where the voltage change rate is small. In the later stage of discharge, the voltage gradually decreases. Therefore, first, the voltage change curve of the battery cell during the discharge process is divided into the early stage, the plateau period, and the later stage according to the above voltage change intervals and the voltage change rate. Then, the Euclidean distances of the first curve and the second curve in the early stage, the plateau period, and the later stage are calculated respectively, and the Euclidean distance is used to quantify the straight-line distance between the first curve and the second curve, measuring the deviation degree between the voltage change curve of the battery cell and the ideal voltage within its corresponding interval. Finally, based on the fault simulation experiment, the relationship between the cause of the fault and the change characteristics of the Euclidean distance is set, and the diagnosis of the cause of the inconsistency fault is carried out accordingly. Among them, the connection fault is manifested as that the value of the Euclidean distance is large and stable in the early stage, the plateau period, and the later stage; the aging fault is manifested as that the Euclidean distance is not obvious in the early stage and the plateau period, that is, the value of the Euclidean distance is small, and the Euclidean distance gradually increases at the end of discharge; the initial SOC inconsistency is manifested as that the Euclidean distance is large in the early stage, gradually decreases in the plateau period, and gradually increases in the later stage.

[0105] In this embodiment, the sudden internal short-circuit fault of the battery cell is predicted by analyzing the voltage change rate and the temperature change rate of the battery cell.

[0106] In order to better implement the battery fault prediction method in the embodiments of the present invention, correspondingly, based on the battery fault prediction method, as Figure 6 shown, the embodiments of the present invention further provide a battery fault prediction device 600, including:

[0107] A model construction module 601, configured to use the charge and discharge parameters of the battery pack as inputs and the ideal voltage of the battery pack as outputs to construct a neural network model;

[0108] A data acquisition module 602, configured to acquire the charge and discharge timing parameter set of the battery pack to be measured and the second curve of the battery cells in the battery pack to be measured, where the second curve is the voltage change curve of the battery cell;

[0109] An ideal curve generation module 603, configured to sequentially input the timing parameters in the charge and discharge timing parameter set into the neural network model to obtain a first curve, where the first curve is the ideal voltage change curve of the battery pack;

[0110] A class correlation coefficient calculation module 604, configured to calculate the class correlation coefficient of the first curve and the second curve;

[0111] A fault location and prediction module 605, configured to locate a faulty battery cell and predict a fault type according to the class correlation coefficient and a preset fault threshold.

[0112] The battery fault prediction device 600 provided in the above embodiment can implement the technical solutions described in the above battery fault prediction method embodiment. The specific implementation principles of the above modules or units can be referred to the corresponding content in the above battery fault prediction method embodiment, and will not be elaborated here.

[0113] In an embodiment of the present invention, the battery fault prediction device may be an independent server, or a server network or server cluster composed of servers. For example, the battery fault prediction device described in the embodiment of the present invention includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. Among them, the cloud server is composed of a large number of computers or network servers based on cloud computing.

[0114] As Figure 7 shown, the present invention also correspondingly provides a battery fault prediction electronic device 700. The battery fault prediction electronic device 700 includes a processor 701, a memory 702, and a display 703. Figure 7 Only some components of the battery fault prediction electronic device 700 are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0115] The processor 701 may be a central processing unit (CPU), a microprocessor, or other data processing chips in some embodiments, and is used to run program codes stored in the memory 702 or process data, such as the battery fault prediction method in the present invention.

[0116] In some embodiments of the present invention, the processor 701 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 701 may be local or remote. In some embodiments, the processor 701 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination of the above.

[0117] The memory 702 can be an internal storage unit of the battery fault prediction electronic device 700 in some embodiments, such as the hard disk or memory of the battery fault prediction electronic device 700. The memory 702 can also be an external storage device of the battery fault prediction electronic device 700 in other embodiments, such as a plug-in hard disk equipped on the battery fault prediction electronic device 700, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc.

[0118] Furthermore, the memory 702 can include both an internal storage unit and an external storage device of the battery fault prediction electronic device 700. The memory 702 is used to store the application software and various types of data installed in the battery fault prediction electronic device 700.

[0119] The display 703 can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. in some embodiments. The display 703 is used to display the information of the battery fault prediction electronic device 700 and to display a visual user interface. The components 901 - 903 of the battery fault prediction electronic device 700 communicate with each other through the system bus.

[0120] In some embodiments of the present invention, when the processor 701 executes the battery fault prediction program in the memory 702, the following steps can be achieved:

[0121] Taking the charge and discharge parameters of the battery pack as input and the ideal voltage of the battery pack as output, a neural network model is constructed;

[0122] Obtaining the charge and discharge timing parameter set of the battery pack to be tested and the second curve of the battery cells in the battery pack to be tested, where the second curve is the voltage change curve of the battery cells;

[0123] Sequentially inputting the timing parameters in the charge and discharge timing parameter set into the neural network model to obtain a first curve, where the first curve is the ideal voltage change curve of the battery pack;

[0124] Calculating the class correlation coefficient between the first curve and the second curve according to the voltage values at each sampling time on the first curve and the second curve;

[0125] Locating the faulty battery cells and predicting the fault type according to the class correlation coefficient and a preset fault threshold.

[0126] It should be understood that when the processor 701 executes the battery fault prediction program in the memory 702, in addition to the above functions, other functions can also be implemented. For specific details, reference can be made to the descriptions of the corresponding method embodiments above.

[0127] Furthermore, the embodiments of the present invention do not specifically limit the type of the battery fault prediction electronic device 700 mentioned. The battery fault prediction electronic device 700 can be a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, or other portable battery fault prediction electronic devices. Exemplary embodiments of the portable battery fault prediction electronic device include, but are not limited to, portable battery fault prediction electronic devices equipped with IOS, Android, Microsoft, or other operating systems. The above-mentioned portable battery fault prediction electronic device can also be other portable battery fault prediction electronic devices. It should also be understood that in some other embodiments of the present invention, the battery fault prediction electronic device 700 may not be a portable battery fault prediction electronic device, but a desktop computer with a touch-sensitive surface (such as a touch panel).

[0128] In this embodiment, the battery fault prediction electronic device is applied to electric ships, electric vehicles, etc. that include a battery management system BMS, and is used to predict faults in the lithium battery system of the electric ship or electric vehicle. When fault prediction is required, the electronic device is connected to the battery management system BMS of the lithium battery system, and data in the battery management system BMS is obtained through the electronic device. The electronic device analyzes and processes the obtained data, outputs the model, further analyzes the result output by the model, obtains the final battery fault prediction result, and displays the prediction result through the electronic device.

[0129] Correspondingly, the embodiments of the present invention also provide a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the programs or instructions are executed by a processor, the steps or functions in the battery fault prediction methods provided by the above-mentioned method embodiments can be implemented.

[0130] Those skilled in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program. The computer program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a magnetic disk, an optical disk, a read-only memory, or a random access memory, etc.

[0131] The above has introduced in detail the battery fault prediction method, device, equipment and storage device provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A battery fault prediction method, characterized in that, Including: Construct a neural network model with the charge and discharge parameters of the battery pack as the input and the ideal voltage of the battery pack as the output; Obtain the charge and discharge timing parameter set of the battery pack to be tested and the second curve of the battery cells in the battery pack to be tested, where the second curve is the voltage change curve of the battery cells; Input the timing parameters in the charge and discharge timing parameter set into the neural network model in sequence to obtain the first curve, where the first curve is the ideal voltage change curve of the battery pack; Calculate the class correlation coefficient between the first curve and the second curve; The calculation formula for the class correlation coefficient between the first curve and the second curve is: ， Among them, is the class correlation coefficient between the ideal voltage change curve of the battery pack and the voltage change curve of the single battery cell, is the ideal voltage value at the th sampling time of the ideal voltage change curve of the battery pack, is the voltage value at the th sampling time of the voltage change curve of the single battery cell, is the total number of sampling times; Locate the faulty battery cells and predict the fault type according to the class correlation coefficient and the preset fault threshold.

2. The battery fault prediction method according to claim 1, wherein Construct a neural network model with the charge and discharge parameters of the battery pack as the input and the ideal voltage of the battery pack as the output, including: Construct an initial neural network model with the charge and discharge parameters at each sampling time during the charge and discharge process of the battery pack as the input and the ideal voltage at the sampling time of the battery pack as the output, where the charge and discharge parameters include the battery pack SOC value, ambient temperature, and charge and discharge current; Obtain the voltage values, battery pack SOC values, charge and discharge currents, and ambient temperatures at each sampling time during the charge and discharge process of a battery pack with good performance; Iteratively train the initial neural network model according to the battery pack SOC value, charge and discharge current, ambient temperature, and voltage value at each sampling time to generate the first model; Optimize the first model based on the AdamW optimization algorithm to generate a neural network model for the battery pack.

3. The battery fault prediction method according to claim 2, wherein The calculation formula of the AdamW optimization algorithm is: ， Among them, is the neural network weight independent variable at the current moment, is the neural network weight independent variable at the previous moment, is the learning rate, is the adaptive adjustment parameter of the learning rate, is the cumulative gradient, is the weight decay parameter.

4. The battery fault prediction method according to claim 1, wherein, The timing parameters include the battery pack SOC value, ambient temperature, charge and discharge current, and sampling time. Input the timing parameters in the charge and discharge timing parameter set into the neural network model in sequence to obtain the first curve, including: Input the battery pack SOC value, ambient temperature, and charge and discharge current in the timing parameters into the neural network model to obtain the ideal voltage values at each sampling time point; Generate the first curve according to the ideal voltage at each sampling time point and its corresponding sampling time.

5. The battery fault prediction method according to claim 1, characterized in that Predict the fault type according to the class correlation coefficient and the preset fault threshold, including: When the class correlation coefficient is within the first preset fault threshold interval, it is determined that the battery has no inconsistency fault; When the class correlation coefficient is within the second preset fault threshold interval, it is determined that the battery fault is a first-level inconsistency fault; When the class correlation coefficient is within the third preset fault threshold interval, it is determined that the battery fault is a second-level inconsistency fault.

6. The battery fault prediction method according to claim 1, wherein, It also includes: Determine the voltage change rate and temperature change rate of the battery cells within a preset time period during the charge and discharge process; Based on the preset voltage change rate alarm threshold and temperature change rate alarm threshold, alarm the battery cells according to the voltage change rate and temperature change rate of the battery cells, and count the alarm duration; When the alarm duration exceeds the preset alarm duration threshold, the battery cell is diagnosed as having a sudden internal short circuit fault.

7. A battery fault prediction device, characterized in that, Including: A model construction module for constructing a neural network model with the charge and discharge parameters of the battery pack as the input and the ideal voltage of the battery pack as the output; A data acquisition module for acquiring a charge-discharge timing parameter set of a battery pack to be tested and a second curve of battery cells in the battery pack to be tested, where the second curve is a voltage change curve of the battery cells; An ideal curve generation module for sequentially inputting the timing parameters in the charge-discharge timing parameter set into the neural network model to obtain a first curve, where the first curve is an ideal voltage change curve of the battery pack; A class correlation coefficient calculation module for calculating the class correlation coefficient between the first curve and the second curve; the calculation formula for the class correlation coefficient between the first curve and the second curve is: ， Among them, is the class correlation coefficient between the ideal voltage change curve of the battery pack and the voltage change curve of the single battery cell, is the ideal voltage value at the th sampling time of the ideal voltage change curve of the battery pack, is the voltage value at the th sampling time of the voltage change curve of the single battery cell, is the total number of sampling times; A fault location and prediction module for locating faulty battery cells and predicting fault types according to the class correlation coefficient and a preset fault threshold.

8. An electronic device for predicting battery faults, characterized in that, It includes a processor and a memory, and a computer program is stored on the memory. When the computer program is executed by the processor, the steps of the battery fault prediction method according to any one of claims 1 to 6 are implemented.

9. A storage medium, characterized in that, The storage medium stores computer program instructions. When the computer program instructions are executed by a computer, the computer is made to execute the battery fault prediction method according to any one of claims 1 to 6.

Images