Battery health state prediction method and device, computer equipment, readable storage medium and program product
By processing the current, voltage and cycle data of the battery during constant current discharge, target characteristics are generated and inputted to a pre-trained model for prediction, the health status prediction of power batteries in the prior art is solved. The time-consuming and accurate prediction of the health status of power batteries in the prior art is solved. The poor performance problem achieves efficient and accurate prediction of battery health status.
Patent Information
- Application Number
- CN202411253102.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2024-11-29
AI Technical Summary
In the prior art, the prediction of the health status of the power battery takes a long time and has poor accuracy, resulting in low prediction efficiency.
By obtaining the current data, voltage data and cycle number data of the battery during the constant current discharge process, data preprocessing and standardization are performed, target characteristics are generated, and inputted into the pre-trained battery health status determination model for prediction.
Fast and accurate battery health status prediction is achieved, computing efficiency is reduced, errors caused by artificial extraction of features are avoided, and prediction efficiency is improved.
Smart Images

Figure CN119044808A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a battery health status prediction method, device, computer equipment, computer-readable storage medium and computer program product. Background Art
[0002] Among the many types of power batteries, lithium-ion batteries are widely used in new energy vehicles due to their high energy density, long cycle life and low self-discharge rate. As a core component of new energy vehicles, the health status of power batteries can directly affect the vehicle's user experience and economic benefits.
[0003] In the existing technology, most of them are based on data-driven methods to predict the health status of the power battery of new energy vehicles.
[0004] However, this method not only takes a long time to predict the health status of the power battery, but also has poor accuracy, which in turn leads to low efficiency in predicting the health status of the power battery. Summary of the invention
[0005] Based on this, it is necessary to provide a more efficient battery health status prediction method, device, computer equipment, computer readable storage medium and computer program product to address the above technical problems.
[0006] In a first aspect, the present application provides a method for predicting a battery health state, comprising:
[0007] Acquire battery data of a target battery, the battery data including a plurality of current data, a plurality of voltage data, and a plurality of cycle number data corresponding to a plurality of cycles of the target battery during a constant current discharge process;
[0008] Performing data processing on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain target characteristics of the target battery;
[0009] The target feature is input into a pre-trained battery health status determination model to obtain the battery health status information of the target battery output by the battery health status determination model, and the battery health status information is used to characterize the safety information and service life of the target battery.
[0010] In one embodiment, the multiple current data, the multiple voltage data, and the multiple cycle number data are processed to obtain the target characteristics of the target battery, including: preprocessing the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain the first characteristic of the target battery; and standardizing the first characteristic of the target battery to obtain the target characteristic of the target battery.
[0011] In one embodiment, the multiple current data, the multiple voltage data and the multiple cycle number data are preprocessed to obtain the first characteristic of the target battery, including: averaging the multiple current data, the multiple voltage data and the multiple cycle number data to obtain a current mean, a voltage mean and a cycle number mean; calculating the standard deviation of the multiple current data, the multiple voltage data and the multiple cycle number data to obtain a current standard deviation, a voltage standard deviation and a cycle number standard deviation; determining the current mean, the voltage mean, the cycle number mean, the current standard deviation, the voltage standard deviation and the cycle number standard deviation as the first characteristic of the target battery.
[0012] In one embodiment, the first characteristic of the target battery is standardized to obtain the target characteristic of the target battery, including: substituting the current mean and the current standard deviation into a preset algorithm to obtain the current characteristic of the target battery; substituting the voltage mean and the voltage standard deviation into the preset algorithm to obtain the voltage characteristic of the target battery; substituting the cycle number mean and the cycle number standard deviation into the preset algorithm to obtain the cycle number characteristic of the target battery; and determining the current characteristic, the voltage characteristic, and the cycle number characteristic as the target characteristics of the target battery.
[0013] In one of the embodiments, the training method of the battery health status determination model includes: performing a charge and discharge cycle experiment on a test battery to obtain training data, the training data including test battery data and test battery health status information, the test battery and the target battery are the same type of battery, and the test battery data includes multiple test current data, multiple test voltage data, and multiple test cycle number data corresponding to multiple cycles of the test battery during constant current discharge; training an initial battery health status determination model based on the training data to obtain the battery health status determination model.
[0014] In one of the embodiments, the method also includes: after training the initial battery health state determination model for a preset number of times based on the training data, obtaining prediction accuracy change information of the initial battery health state determination model; when the prediction accuracy change information indicates that the prediction accuracy of the initial battery health state determination model is reduced, determining a target number of times from the preset number of times according to the prediction accuracy change information; and determining the initial battery health state determination model after training the initial battery health state determination model for the target number of times based on the training data as the battery health state determination model.
[0015] In a second aspect, the present application also provides a battery health status prediction device, comprising:
[0016] An acquisition module, used to acquire battery data of a target battery, the battery data including a plurality of current data, a plurality of voltage data and a plurality of cycle number data corresponding to a plurality of cycles of the target battery during a constant current discharge process;
[0017] A first execution module is used to perform data processing on the multiple current data, the multiple voltage data and the multiple cycle number data to obtain the target characteristics of the target battery;
[0018] The second execution module is used to input the target feature into a pre-trained battery health status determination model to obtain the battery health status information of the target battery output by the battery health status determination model, and the battery health status information is used to characterize the safety information and usage time of the target battery.
[0019] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in any embodiment of the first aspect when executing the computer program.
[0020] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any one of the embodiments of the first aspect above.
[0021] In a fifth aspect, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in any embodiment of the first aspect above.
[0022] The above-mentioned battery health state prediction method, device, computer equipment, computer-readable storage medium and computer program product first obtain the battery data of the target battery, which includes multiple current data, multiple voltage data and multiple cycle number data corresponding to multiple cycles of the target battery during constant current discharge; then process the multiple current data, the multiple voltage data and the multiple cycle number data to obtain the target characteristics of the target battery; then input the target characteristics into a pre-trained battery health state determination model to obtain the battery health state information of the target battery output by the battery health state determination model, and the battery health state information is used to characterize the safety information and service life of the target battery. By adopting the battery health state prediction method provided by the present application, the battery health state can be predicted with only a small amount of data, that is, the battery health state can be predicted with the current, voltage and cycle number of the battery during constant current discharge, avoiding the input of more features into the model in the prior art, improving the calculation efficiency and reducing the prediction time. Furthermore, the battery data is processed to obtain target features, thereby avoiding the problem of human errors caused by artificial feature extraction, effectively improving the accuracy of the prediction, and further effectively improving the prediction efficiency of the battery health status. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0024] Figure 1 A schematic diagram of a flow chart of a method for predicting a battery health state in one embodiment;
[0025] Figure 2 A schematic flow chart of a method for processing the plurality of current data, the plurality of voltage data and the plurality of cycle number data to obtain target characteristics of the target battery in one embodiment;
[0026] Figure 3 A schematic flow chart of a method for obtaining a first characteristic of a target battery in one embodiment;
[0027] Figure 4 A schematic flow chart of a method for obtaining target characteristics of a target battery in one embodiment;
[0028] Figure 5 A flowchart of a method for training a battery health status determination model in one embodiment;
[0029] Figure 6 A flowchart of a method in one embodiment after training the initial battery health status determination model based on the training data for a preset number of times;
[0030] Figure 7 is a flowchart of a battery health status prediction method in another embodiment;
[0031] Figure 8 is a structural block diagram of a battery health status prediction device in one embodiment;
[0032] Fig. 9 is an internal structure diagram of a computer device in one embodiment;
[0033] Fig.10 is an internal structure diagram of a computer device in one embodiment;
[0034] Fig.11 This is a visualization diagram of predicted values and true values in an embodiment. DETAILED DESCRIPTION
[0035] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0036] Among the many types of power batteries, lithium-ion batteries are widely used in new energy vehicles due to their high energy density, long cycle life and low self-discharge rate. As a core component of new energy vehicles, the health status of power batteries can directly affect the vehicle's user experience and economic benefits.
[0037] In the existing technology, most of them are based on data-driven methods to predict the health status of the power battery of new energy vehicles.
[0038] However, this method not only takes a long time to predict the health status of the power battery, but also has poor accuracy, which in turn leads to low efficiency in predicting the health status of the power battery.
[0039] In view of this, the present application provides a battery health status prediction method, which can not only reduce the prediction time, but also improve the prediction accuracy, thereby effectively improving the prediction efficiency of the health status of the power battery.
[0040] The battery health status prediction method provided in the present application can be executed by a computer device, which can be a server or a terminal.
[0041] In an exemplary embodiment, Figure 1As shown, a battery health status prediction method is provided, the method comprising the following steps:
[0042] Step 101: Obtain battery data of a target battery.
[0043] The battery data includes a plurality of current data, a plurality of voltage data and a plurality of cycle number data corresponding to a plurality of cycles of the target battery during constant current discharge.
[0044] Optionally, the target battery is a battery for which battery health status prediction is to be performed, and the battery may be a power battery in a new energy vehicle. Specifically, the power battery may be a lithium-ion battery.
[0045] Optionally, the cycle refers to a process of charging and discharging a target battery, and each time the target battery is charged and discharged once is considered a cycle.
[0046] In one possible implementation, a computer device can obtain multiple current data, multiple voltage data, and multiple cycle count data corresponding to multiple cycles of the target battery during constant current discharge, and determine the multiple current data, multiple voltage data, and multiple cycle count data as battery data of the target battery.
[0047] Step 102: Process the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain target characteristics of the target battery.
[0048] In one possible implementation, the computer device can input the multiple current data, the multiple voltage data, and the multiple cycle number data into a pre-trained target feature determination model to obtain the target feature of the target battery.
[0049] In another possible implementation, the computer device can also perform data preprocessing on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain the first characteristic of the target battery, and then standardize the first characteristic of the target battery to obtain the target characteristic of the target battery.
[0050] Step 103: input the target feature into a pre-trained battery health status determination model to obtain battery health status information of the target battery output by the battery health status determination model.
[0051] The battery health status information is used to characterize the safety information and usage time of the target battery.
[0052] Optionally, the battery health status determination model may be a multi-layer long short-term memory network (LSTM).
[0053] Furthermore, the battery health state determination model includes an input layer, a forgetting layer, a candidate memory data state calculation layer, an update data state layer, an update data layer, an output layer and an update hidden state layer.
[0054] In one possible implementation, after the computer device determines the target characteristics of the target battery based on the multiple current data, the multiple voltage data, and the multiple cycle number data, the target characteristics can be input into a pre-trained battery health status determination model to obtain the battery health status information of the target battery output by the battery health status determination model, and the safety information and usage time of the target battery can be determined based on the battery health status information.
[0055] The above-mentioned battery health state prediction method first obtains the battery data of the target battery, and the battery data includes multiple current data, multiple voltage data and multiple cycle number data corresponding to multiple cycles of the target battery during constant current discharge; then the multiple current data, the multiple voltage data and the multiple cycle number data are processed to obtain the target feature of the target battery; then the target feature is input into the pre-trained battery health state determination model to obtain the battery health state information of the target battery output by the battery health state determination model, and the battery health state information is used to characterize the safety information and service life of the target battery. By adopting the battery health state prediction method provided by the present application, the battery health state can be predicted by only a small amount of data, that is, the battery health state can be predicted by the current, voltage and cycle number of the battery during constant current discharge, avoiding the input of more features into the model in the prior art, improving the calculation efficiency and reducing the prediction time. Further, the battery data is processed to obtain the target feature, avoiding the problem of human error caused by artificial feature extraction, effectively improving the accuracy of the prediction, and then effectively improving the prediction efficiency of the battery health state.
[0056] In an exemplary embodiment, Figure 2 As shown, the multiple current data, the multiple voltage data and the multiple cycle number data are processed to obtain the target characteristics of the target battery, including the following steps:
[0057] Step 201: preprocess the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a first feature of the target battery.
[0058] In one possible implementation, the computer device can input the multiple current data, the multiple voltage data, and the multiple cycle number data into a pre-trained first feature determination model to obtain the first feature of the target battery output by the first feature determination model.
[0059] In another possible implementation, the computer device can also perform averaging processing on the multiple current data, the multiple voltage data, and the multiple cycle number data, respectively, to obtain a current mean, a voltage mean, and a cycle number mean, and perform standard deviation processing on the multiple current data, the multiple voltage data, and the multiple cycle number data, respectively, to obtain a current standard deviation, a voltage standard deviation, and a cycle number standard deviation, and then determine the current mean, the voltage mean, the cycle number mean, the current standard deviation, the voltage standard deviation, and the cycle number standard deviation as the first characteristic of the target battery.
[0060] Step 202: Standardize the first feature of the target battery to obtain the target feature of the target battery.
[0061] Optionally, the standardization process refers to a process for making the average values of the feature dimensions of the first feature all equal to 0 and the standard deviations all equal to 1.
[0062] In one possible implementation, the computer device may input the first feature of the target battery into a pre-trained target feature determination model to obtain the target feature of the target battery output by the target feature determination model.
[0063] In another possible implementation, the computer device can also substitute the current mean and current standard deviation in the first feature into a preset algorithm to obtain the current feature of the target battery; substitute the voltage mean and voltage standard deviation in the first feature into the preset algorithm to obtain the voltage feature of the target battery, substitute the cycle number mean and cycle number standard deviation in the first feature into the preset algorithm to obtain the cycle number feature of the target battery, and then determine the current feature, the voltage feature, and the cycle number feature as the target feature of the target battery.
[0064] In an exemplary embodiment, Figure 3 As shown, the data preprocessing is performed on the multiple current data, the multiple voltage data and the multiple cycle number data to obtain the first feature of the target battery, including the following steps:
[0065] Step 301 : averaging the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current mean value, a voltage mean value, and a cycle number mean value.
[0066] In one possible implementation, the multiple current data, the multiple voltage data, and the multiple cycle number data can be respectively input into a pre-trained averaging model to obtain the current mean, voltage mean, and cycle number mean output by the averaging model.
[0067] In another possible implementation, the multiple current data, the multiple voltage data, and the multiple cycle number data may be averaged based on an averaging formula to obtain a current mean, a voltage mean, and a cycle number mean.
[0068] Step 302: performing standard deviation processing on the plurality of current data, the plurality of voltage data and the plurality of cycle number data respectively to obtain a current standard deviation, a voltage standard deviation and a cycle number standard deviation.
[0069] In one possible implementation, the multiple current data, the multiple voltage data, and the multiple cycle number data can be respectively input into a pre-trained standard deviation model to obtain the current standard deviation, voltage standard deviation, and cycle number standard deviation output by the standard deviation model.
[0070] In another possible implementation, the multiple current data, the multiple voltage data and the multiple cycle number data can be processed for standard deviation based on the standard deviation formula to obtain the current standard deviation, voltage standard deviation and cycle number standard deviation output by the standard deviation model.
[0071] Step 303: determine the current mean, the voltage mean, the cycle number mean, the current standard deviation, the voltage standard deviation and the cycle number standard deviation as the first characteristic of the target battery.
[0072] In one possible implementation, after the computer device performs averaging processing on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current mean, a voltage mean, and a cycle number mean, and performs standard deviation processing on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current standard deviation, a voltage standard deviation, and a cycle number standard deviation, the current mean, the voltage mean, the cycle number mean, the current standard deviation, the voltage standard deviation, and the cycle number standard deviation can be determined as the first characteristic of the target battery.
[0073] In an exemplary embodiment, Figure 4 As shown, the first feature of the target battery is standardized to obtain the target feature of the target battery, including the following steps:
[0074] Step 401: Substitute the current mean and the current standard deviation into a preset algorithm to obtain the current characteristics of the target battery.
[0075] Optionally, the preset algorithm can be , where I' refers to the current feature, I refers to multiple current data, and I 均值 Refers to the average current, the I标准差 Refers to the standard deviation of this current.
[0076] In one possible implementation, the computer device may substitute the current mean and the current standard deviation into a preset algorithm to obtain the current characteristics of the target battery.
[0077] Step 402: Substitute the voltage mean and the voltage standard deviation into the preset algorithm to obtain the voltage characteristics of the target battery.
[0078] Optionally, the preset algorithm can be , where V' refers to the voltage characteristic, V refers to multiple voltage data, and V 均值 Refers to the mean voltage, the V 标准差 Refers to the standard deviation of this voltage.
[0079] In a possible implementation, the computer device may substitute the voltage mean and the voltage standard deviation into a preset algorithm to obtain the voltage characteristic of the target battery.
[0080] Step 403: Substitute the cycle number mean and the cycle number standard deviation into the preset algorithm to obtain the cycle number characteristics of the target battery.
[0081] Optionally, the preset algorithm can be , where X' refers to the cycle number feature, X refers to multiple cycle number data, and X 均值 Refers to the mean number of cycles, the X 标准差 Refers to the standard deviation of the number of cycles.
[0082] In one possible implementation, the computer device may substitute the cycle number mean and the cycle number standard deviation into a preset algorithm to obtain the cycle number characteristics of the target battery.
[0083] Step 404: determine the current characteristic, the voltage characteristic, and the cycle number characteristic as target characteristics of the target battery.
[0084] In one possible implementation, after the computer device determines the current characteristic of the target battery, the voltage characteristic of the target battery, and the cycle number characteristic of the target battery, the current characteristic, the voltage characteristic, and the cycle number characteristic can be determined as the target characteristics of the target battery.
[0085] In an exemplary embodiment, Figure 5 As shown, the training method of the battery health status determination model includes the following steps:
[0086] Step 501: Perform a charge-discharge cycle experiment on a test battery to obtain training data.
[0087] Among them, the training data includes test battery data and test battery health status information. The test battery and the target battery are of the same type of battery. The test battery data includes multiple test current data, multiple test voltage data and multiple test cycle number data corresponding to multiple cycles of the test battery during constant current discharge.
[0088] Optionally, the test battery is a lithium-ion battery of the same model as the target battery.
[0089] Step 502: Train the initial battery health state determination model based on the training data to obtain the battery health state determination model.
[0090] In one possible implementation, after acquiring the training data, the computer device can perform data preprocessing on the multiple test current data, the multiple test voltage data, and the multiple test cycle number data to obtain a first test characteristic of the test battery, and then standardize the first test characteristic of the test battery to obtain a target test characteristic of the test battery, and use the target test characteristic as an input set and the corresponding test battery health status information as an output set to continuously train the initial battery health status determination model to obtain the battery health status determination model.
[0091] In an exemplary embodiment, Figure 6 As shown, after the initial battery health status determination model is trained a preset number of times based on the training data, the method further includes the following steps:
[0092] Step 601: Obtain prediction accuracy change information of the initial battery health status determination model.
[0093] Step 602: when the prediction accuracy change information indicates that the prediction accuracy of the initial battery health state determination model is reduced, determine a target number of times from the preset number of times according to the prediction accuracy change information;
[0094] Step 603: Determine the initial battery health state determination model after training the initial battery health state determination model for the target number of times based on the training data as the battery health state determination model.
[0095] In one possible implementation, the present application adopts an early stopping method in the process of training the initial battery health status determination model based on the training data, that is, after the initial battery health status determination model is trained for a preset number of times based on the training data, the prediction accuracy change information of the initial battery health status determination model is obtained. If the prediction accuracy change information indicates that the prediction accuracy of the initial battery health status determination model is reduced, the training is stopped, and the target number of times is determined from the preset number of times according to the prediction accuracy change information, that is, the number corresponding to the highest prediction accuracy, and the initial battery health status determination model after the initial battery health status determination model is trained for the target number of times based on the training data is determined as the battery health status determination model.
[0096] In an optional embodiment of the present application, the first preset proportion of data in the training data can be used as a training set to train the initial battery health status determination model, and the second preset proportion of data in the training data can be used as a validation set to perform model evaluation on the trained battery health status determination model.
[0097] Furthermore, during the training of the initial battery health status determination model, the learning rate is dynamically adjusted according to the loss of the validation set. If the loss value of the validation set does not improve within 10 consecutive cycles, the learning rate is reduced by 20% of the initial learning rate.
[0098] Specifically, the mean squared error (MSE) can be used as the loss function; the root mean squared error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) can be used as evaluation indicators of the model. The specific calculation formula is as follows: , , , ;in, is the true value of the health status of the ith battery, is the predicted value of the health status of the ith battery, and n is the total number of samples. The inventor of the present application recorded the predicted values and true values during the training process, and the visualization diagram of the predicted values and true values can be shown as follows: Fig.11 As shown in the figure, the prediction error of the battery health status prediction model trained based on the above training method can be kept within 3%.
[0099] In an exemplary embodiment, Figure 7 As shown, another method for predicting the health status of a battery is provided, the method comprising the following steps:
[0100] Step 701, obtaining battery data of a target battery, the battery data including a plurality of current data, a plurality of voltage data and a plurality of cycle number data corresponding to a plurality of cycles of the target battery during a constant current discharge process;
[0101] Step 702: averaging the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current mean, a voltage mean, and a cycle number mean; performing standard deviation processing on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current standard deviation, a voltage standard deviation, and a cycle number standard deviation; determining the current mean, the voltage mean, the cycle number mean, the current standard deviation, the voltage standard deviation, and the cycle number standard deviation as the first feature of the target battery;
[0102] Step 703: Substitute the current mean and the current standard deviation into a preset algorithm to obtain the current characteristic of the target battery; substitute the voltage mean and the voltage standard deviation into the preset algorithm to obtain the voltage characteristic of the target battery; substitute the cycle number mean and the cycle number standard deviation into the preset algorithm to obtain the cycle number characteristic of the target battery; determine the current characteristic, the voltage characteristic and the cycle number characteristic as the target characteristic of the target battery;
[0103] Step 704: input the target feature into a pre-trained battery health status determination model to obtain battery health status information of the target battery output by the battery health status determination model, where the battery health status information is used to characterize the safety information and usage time of the target battery.
[0104] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0105] Based on the same inventive concept, the embodiment of the present application also provides a battery health state prediction device for implementing the battery health state prediction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more battery health state prediction device embodiments provided below can refer to the limitations of the battery health state prediction method above, and will not be repeated here.
[0106] In an exemplary embodiment, Figure 8 As shown, a battery health status prediction device 800 is provided, comprising: an acquisition module 801, a first execution module 802 and a second execution module 803, wherein:
[0107] An acquisition module 801 is used to acquire battery data of a target battery, wherein the battery data includes a plurality of current data, a plurality of voltage data, and a plurality of cycle number data corresponding to a plurality of cycles of the target battery during a constant current discharge process;
[0108] A first execution module 802 is used to perform data processing on the multiple current data, the multiple voltage data and the multiple cycle number data to obtain the target characteristics of the target battery;
[0109] The second execution module 803 is used to input the target feature into a pre-trained battery health status determination model to obtain the battery health status information of the target battery output by the battery health status determination model, and the battery health status information is used to characterize the safety information and usage time of the target battery.
[0110] In one embodiment, the first execution module 802 is specifically used to perform data preprocessing on the multiple current data, the multiple voltage data and the multiple cycle number data to obtain the first characteristic of the target battery; and perform standardization on the first characteristic of the target battery to obtain the target characteristic of the target battery.
[0111] In one embodiment, the first execution module 802 is specifically used to perform averaging processing on the multiple current data, the multiple voltage data and the multiple cycle number data respectively to obtain a current mean, a voltage mean and a cycle number mean; perform standard deviation processing on the multiple current data, the multiple voltage data and the multiple cycle number data respectively to obtain a current standard deviation, a voltage standard deviation and a cycle number standard deviation; and determine the current mean, the voltage mean, the cycle number mean, the current standard deviation, the voltage standard deviation and the cycle number standard deviation as the first feature of the target battery.
[0112] In one embodiment, the first execution module 802 is specifically used to substitute the current mean and the current standard deviation into a preset algorithm to obtain the current characteristics of the target battery; substitute the voltage mean and the voltage standard deviation into the preset algorithm to obtain the voltage characteristics of the target battery; substitute the cycle number mean and the cycle number standard deviation into the preset algorithm to obtain the cycle number characteristics of the target battery; and determine the current characteristics, the voltage characteristics, and the cycle number characteristics as the target characteristics of the target battery.
[0113] In one embodiment, the second execution module 803 is also used to perform a charge and discharge cycle experiment on the test battery to obtain training data, the training data including test battery data and test battery health status information, the test battery and the target battery are of the same type of battery, and the test battery data includes multiple test current data, multiple test voltage data, and multiple test cycle number data corresponding to multiple cycles of the test battery during constant current discharge; based on the training data, the initial battery health status determination model is trained to obtain the battery health status determination model.
[0114] In one embodiment, the second execution module 803 is specifically used to obtain prediction accuracy change information of the initial battery health status determination model after the initial battery health status determination model is trained a preset number of times based on the training data; when the prediction accuracy change information indicates that the prediction accuracy of the initial battery health status determination model is reduced, determine a target number of times from the preset number of times according to the prediction accuracy change information; and determine the initial battery health status determination model after the initial battery health status determination model is trained the target number of times based on the training data as the battery health status determination model.
[0115] Each module in the above-mentioned battery health status prediction device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.
[0116] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig. 9As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a battery health status prediction method is implemented.
[0117] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a battery health status prediction method is implemented.
[0118] Those skilled in the art will understand that Fig. 9 and Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0119] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0120] Acquire battery data of a target battery, the battery data including a plurality of current data, a plurality of voltage data, and a plurality of cycle number data corresponding to a plurality of cycles of the target battery during a constant current discharge process;
[0121] Performing data processing on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain target characteristics of the target battery;
[0122] The target feature is input into a pre-trained battery health status determination model to obtain the battery health status information of the target battery output by the battery health status determination model, and the battery health status information is used to characterize the safety information and service life of the target battery.
[0123] In one embodiment, when the processor executes the computer program, the following steps are also implemented: preprocessing the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain the first characteristic of the target battery; and standardizing the first characteristic of the target battery to obtain the target characteristic of the target battery.
[0124] In one embodiment, when the processor executes the computer program, the following steps are also implemented: averaging the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current mean, a voltage mean, and a cycle number mean; standard deviation processing is performed on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current standard deviation, a voltage standard deviation, and a cycle number standard deviation; and the current mean, the voltage mean, the cycle number mean, the current standard deviation, the voltage standard deviation, and the cycle number standard deviation are determined as the first characteristic of the target battery.
[0125] In one embodiment, when the processor executes the computer program, the following steps are also implemented: substituting the current mean and the current standard deviation into a preset algorithm to obtain the current characteristics of the target battery; substituting the voltage mean and the voltage standard deviation into the preset algorithm to obtain the voltage characteristics of the target battery; substituting the cycle number mean and the cycle number standard deviation into the preset algorithm to obtain the cycle number characteristics of the target battery; and determining the current characteristics, the voltage characteristics, and the cycle number characteristics as the target characteristics of the target battery.
[0126] In one embodiment, when the processor executes the computer program, the following steps are also implemented: performing a charge and discharge cycle experiment on a test battery to obtain training data, the training data including test battery data and test battery health status information, the test battery and the target battery are of the same type of battery, and the test battery data includes multiple test current data, multiple test voltage data, and multiple test cycle number data corresponding to multiple cycles of the test battery during constant current discharge; training an initial battery health status determination model based on the training data to obtain the battery health status determination model.
[0127] In one embodiment, when the processor executes the computer program, the following steps are also implemented: after the initial battery health state determination model is trained a preset number of times based on the training data, prediction accuracy change information of the initial battery health state determination model is obtained; when the prediction accuracy change information indicates that the prediction accuracy of the initial battery health state determination model is reduced, a target number of times is determined from the preset number of times according to the prediction accuracy change information; and the initial battery health state determination model after the initial battery health state determination model is trained the target number of times based on the training data is determined as the battery health state determination model.
[0128] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0129] Acquire battery data of a target battery, the battery data including a plurality of current data, a plurality of voltage data, and a plurality of cycle number data corresponding to a plurality of cycles of the target battery during a constant current discharge process;
[0130] Performing data processing on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain target characteristics of the target battery;
[0131] The target feature is input into a pre-trained battery health status determination model to obtain the battery health status information of the target battery output by the battery health status determination model, and the battery health status information is used to characterize the safety information and service life of the target battery.
[0132] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: preprocessing the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a first characteristic of the target battery; and standardizing the first characteristic of the target battery to obtain a target characteristic of the target battery.
[0133] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: averaging the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current mean, a voltage mean, and a cycle number mean; standard deviation processing is performed on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current standard deviation, a voltage standard deviation, and a cycle number standard deviation; and the current mean, the voltage mean, the cycle number mean, the current standard deviation, the voltage standard deviation, and the cycle number standard deviation are determined as the first characteristic of the target battery.
[0134] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: substituting the current mean and the current standard deviation into a preset algorithm to obtain the current characteristics of the target battery; substituting the voltage mean and the voltage standard deviation into the preset algorithm to obtain the voltage characteristics of the target battery; substituting the cycle number mean and the cycle number standard deviation into the preset algorithm to obtain the cycle number characteristics of the target battery; and determining the current characteristics, the voltage characteristics, and the cycle number characteristics as the target characteristics of the target battery.
[0135] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: performing a charge and discharge cycle experiment on a test battery to obtain training data, the training data including test battery data and test battery health status information, the test battery and the target battery are of the same type of battery, and the test battery data includes multiple test current data, multiple test voltage data, and multiple test cycle number data corresponding to multiple cycles of the test battery during constant current discharge; training an initial battery health status determination model based on the training data to obtain the battery health status determination model.
[0136] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: after training the initial battery health state determination model for a preset number of times based on the training data, obtaining prediction accuracy change information of the initial battery health state determination model; when the prediction accuracy change information indicates that the prediction accuracy of the initial battery health state determination model is reduced, determining a target number of times from the preset number of times according to the prediction accuracy change information; and determining the initial battery health state determination model after training the initial battery health state determination model for the target number of times based on the training data as the battery health state determination model.
[0137] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0138] Acquire battery data of a target battery, the battery data including a plurality of current data, a plurality of voltage data, and a plurality of cycle number data corresponding to a plurality of cycles of the target battery during a constant current discharge process;
[0139] Performing data processing on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain target characteristics of the target battery;
[0140] The target feature is input into a pre-trained battery health status determination model to obtain the battery health status information of the target battery output by the battery health status determination model, and the battery health status information is used to characterize the safety information and service life of the target battery.
[0141] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: preprocessing the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a first characteristic of the target battery; and standardizing the first characteristic of the target battery to obtain a target characteristic of the target battery.
[0142] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: averaging the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current mean, a voltage mean, and a cycle number mean; standard deviation processing is performed on the multiple current data, the multiple voltage data, and the multiple cycle number data to obtain a current standard deviation, a voltage standard deviation, and a cycle number standard deviation; and the current mean, the voltage mean, the cycle number mean, the current standard deviation, the voltage standard deviation, and the cycle number standard deviation are determined as the first characteristic of the target battery.
[0143] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: substituting the current mean and the current standard deviation into a preset algorithm to obtain the current characteristics of the target battery; substituting the voltage mean and the voltage standard deviation into the preset algorithm to obtain the voltage characteristics of the target battery; substituting the cycle number mean and the cycle number standard deviation into the preset algorithm to obtain the cycle number characteristics of the target battery; and determining the current characteristics, the voltage characteristics, and the cycle number characteristics as the target characteristics of the target battery.
[0144] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: performing a charge and discharge cycle experiment on a test battery to obtain training data, the training data including test battery data and test battery health status information, the test battery and the target battery are of the same type of battery, and the test battery data includes multiple test current data, multiple test voltage data, and multiple test cycle number data corresponding to multiple cycles of the test battery during constant current discharge; training an initial battery health status determination model based on the training data to obtain the battery health status determination model.
[0145] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: after training the initial battery health state determination model for a preset number of times based on the training data, obtaining prediction accuracy change information of the initial battery health state determination model; when the prediction accuracy change information indicates that the prediction accuracy of the initial battery health state determination model is reduced, determining a target number of times from the preset number of times according to the prediction accuracy change information; and determining the initial battery health state determination model after training the initial battery health state determination model for the target number of times based on the training data as the battery health state determination model.
[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0147] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0148] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for predicting battery health status, characterized in that: The method comprises: Acquire battery data of a target battery, wherein the battery data includes a plurality of current data, a plurality of voltage data, and a plurality of cycle number data corresponding to a plurality of cycles of the target battery during a constant current discharge process; Performing data processing on the plurality of current data, the plurality of voltage data, and the plurality of cycle number data to obtain target characteristics of the target battery; The target feature is input into a pre-trained battery health status determination model to obtain battery health status information of the target battery output by the battery health status determination model, wherein the battery health status information is used to characterize the safety information and usage time of the target battery.
2. The method according to claim 1, characterized in that The processing of the plurality of current data, the plurality of voltage data, and the plurality of cycle number data to obtain target characteristics of the target battery includes: Performing data preprocessing on the plurality of current data, the plurality of voltage data, and the plurality of cycle number data to obtain a first feature of the target battery; The first characteristic of the target battery is standardized to obtain a target characteristic of the target battery.
3. The method according to claim 2, characterized in that The preprocessing of the plurality of current data, the plurality of voltage data, and the plurality of cycle number data to obtain the first characteristic of the target battery includes: The plurality of current data, the plurality of voltage data and the plurality of cycle number data are respectively averaged to obtain a current mean value, a voltage mean value and a cycle number mean value; Performing standard deviation processing on the plurality of current data, the plurality of voltage data and the plurality of cycle number data respectively to obtain a current standard deviation, a voltage standard deviation and a cycle number standard deviation; The current mean, the voltage mean, the cycle number mean, the current standard deviation, the voltage standard deviation, and the cycle number standard deviation are determined as first characteristics of the target battery.
4. The method according to claim 3, characterized in that The standardizing the first feature of the target battery to obtain the target feature of the target battery includes: Substituting the current mean and the current standard deviation into a preset algorithm to obtain the current characteristics of the target battery; Substituting the voltage mean and the voltage standard deviation into the preset algorithm to obtain the voltage characteristic of the target battery; Substituting the cycle number mean and the cycle number standard deviation into the preset algorithm to obtain the cycle number characteristics of the target battery; The current characteristic, the voltage characteristic, and the cycle number characteristic are determined as target characteristics of the target battery.
5. The method according to claim 1, characterized in that The training method of the battery health status determination model includes: Performing a charge and discharge cycle experiment on a test battery to obtain training data, wherein the training data includes test battery data and test battery health status information, wherein the test battery and the target battery are of the same type of battery, and the test battery data includes a plurality of test current data, a plurality of test voltage data, and a plurality of test cycle number data corresponding to a plurality of cycles of the test battery during a constant current discharge process; An initial battery health state determination model is trained based on the training data to obtain the battery health state determination model.
6. The method according to claim 5, characterized in that The method further comprises: After training the initial battery health state determination model for a preset number of times based on the training data, obtaining prediction accuracy change information of the initial battery health state determination model; In a case where the prediction accuracy change information indicates that the prediction accuracy of the initial battery health state determination model is reduced, determining a target number of times from the preset number of times according to the prediction accuracy change information; The initial battery health state determination model after training the initial battery health state determination model for the target number of times based on the training data is determined as the battery health state determination model.
7. A battery health status prediction device, characterized in that: The device comprises: An acquisition module, used for acquiring battery data of a target battery, wherein the battery data includes a plurality of current data, a plurality of voltage data, and a plurality of cycle number data corresponding to a plurality of cycles of the target battery during a constant current discharge process; A first execution module, configured to perform data processing on the plurality of current data, the plurality of voltage data, and the plurality of cycle number data to obtain target characteristics of the target battery; The second execution module is used to input the target feature into a pre-trained battery health status determination model to obtain the battery health status information of the target battery output by the battery health status determination model, and the battery health status information is used to characterize the safety information and usage time of the target battery.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
Citation Information
Patent Citations
Battery health state determination method and device, battery management system and storage medium
CN117007997A
Battery health state determination method and device, equipment and storage medium
CN117761563A
Lithium battery end-to-end residual service life prediction method
CN118311461A
Method and battery management system for ascertaining a state of health of a secondary battery
US20210181263A1
