Method and device for estimating state of health of battery of electric vehicle
By using Gaussian process regression model and health factors to extract the optimal voltage interval, the problem of difficult estimation of health status caused by the aging complexity of lithium-ion batteries is solved, and the accurate prediction and management of battery health status is achieved.
Patent Information
- Application Number
- CN202411391425.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-08
- Publication Date
- 2024-12-06
AI Technical Summary
The existing battery health status estimation method is difficult to accurately predict the aging process of lithium-ion batteries in the actual engineering field, and there are many influencing factors and complexity, resulting in low estimation accuracy.
By obtaining the experimental data for training, selecting health factors, obtaining the optimal voltage interval, and using the Gaussian process regression model for training, input the working data of the battery to be estimated to obtain its health status.
Improves the accuracy of battery health status estimation and enables accurate SOH estimation in short charge and discharge cycles, suitable for the management of single-cell batteries and battery packs.
Smart Images

Figure CN119087273A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of electric vehicles, and in particular to a method and device for estimating the health status of an electric vehicle battery. Background Art
[0002] The power battery pack is the core component of new energy vehicles. It provides pollution-free power for the vehicle through cyclic charge and discharge. As the power battery is used, it will age and its capacity will gradually decay. The degree of decay is characterized by the battery state of health (SOH). Accurate prediction of the battery state of health can not only ensure the safe and reliable operation of the system, but also maximize the use of the battery's residual value, which is of great value to battery management and cascade utilization.
[0003] The aging process of lithium-ion batteries is affected by many factors, such as: loss of lithium ions due to the formation of electrolyte layers at the positive and negative electrodes and lithium ion deposition; loss of positive and negative electrode materials due to graphite exfoliation, dissolution of lithium metal in the electrolyte decomposition, loss of active substances due to current collector corrosion, decomposition of adhesives, etc.; loss of electrolyte due to electrolyte decomposition, etc.; increase in battery internal resistance, etc.
[0004] Since there are many factors that affect the aging of lithium-ion batteries, it is difficult to accurately estimate the health status of batteries. Currently, the commonly used prediction methods include model-based methods and data-driven methods. Model-based methods include electrochemical models, equivalent circuit models, and empirical degradation models; data-driven methods include support vector machine algorithms, relevance vector machine algorithms, neural network algorithms, and Gaussian process regression algorithms. Looking at the existing battery health status estimation methods, most of them cannot be widely used in actual engineering fields. Summary of the invention
[0005] The object of the present invention is to provide a method for estimating the health status of an electric vehicle battery to at least solve one of the above-mentioned technical problems.
[0006] The present invention provides the following scheme:
[0007] According to one aspect of the present invention, a method for estimating the health status of a battery in an electric vehicle is provided, and the method for estimating the health status of a battery in an electric vehicle comprises:
[0008] Obtain experimental data for training;
[0009] Select health factors based on experimental data for training;
[0010] Obtaining an optimal voltage range according to the training experimental data and the health factor;
[0011] Get the Gaussian process regression model;
[0012] The Gaussian process regression model is trained by using an optimal voltage interval, thereby obtaining a trained Gaussian process regression model;
[0013] Obtaining working data of the battery to be estimated;
[0014] The working data is input into the Gaussian process regression model to obtain the battery health state.
[0015] Optionally, the training experimental data includes voltage data, current data, temperature data, time data, cumulative charging capacity data, cumulative discharging capacity data, charging and discharging flag data, and charging calibration flag data.
[0016] Optionally, selecting health factors according to training experimental data includes:
[0017] Perform the following operations for each type of training experimental data:
[0018] Obtain the charging voltage-time versus battery aging curve during the constant current charging process of the battery to be estimated;
[0019] Obtaining a correlation curve of training experimental data during a constant current charging process of the battery to be estimated;
[0020] Whether the experimental data is used as a health factor is determined based on the charging voltage-time curve versus battery aging curve and the correlation curve of the training experimental data.
[0021] Optionally, the correlation is obtained by the following formula:
[0022] in,
[0023] R 2 It is the coefficient of determination, which indicates how much of the variation in the dependent variable can be explained by the variation in the independent variable. It is a measure of the degree of correlation between the actual value and the predicted value. The value range is usually between 0 and 1. The closer the value is to 1, the higher the correlation. i is the i-th actual observation value; is the predicted value of the ith model; is the average of all observations.
[0024] Optionally, the charging voltage-time at each time point in the constant current charging process of the battery to be estimated is obtained using the following formula:
[0025] in,
[0026] t k At the kth moment in the charge / discharge process, t si Indicates the si-th moment of charge / discharge; V k and Vsi are the battery voltage values corresponding to the kth moment and the sith moment respectively.
[0027] Optionally, when the health factor is one, acquiring the optimal voltage interval according to the experimental data and the health factor includes:
[0028] The health factor is obtained in multiple voltage segments during the correlation calculation process, wherein the determination coefficient corresponding to each voltage point in each voltage segment exceeds a first preset threshold.
[0029] The present application also provides a device for estimating the health status of a battery in an electric vehicle, the device comprising:
[0030] A training experimental data acquisition module, wherein the training experimental data acquisition module is used to acquire training experimental data;
[0031] A health factor selection module, wherein the health factor selection module is used to select health factors according to training experimental data;
[0032] An optimal voltage interval acquisition module, the optimal voltage interval acquisition module is used to acquire an optimal voltage interval according to the training experimental data and the health factor;
[0033] A model acquisition module, wherein the model acquisition module is used to acquire a Gaussian process regression model;
[0034] A training module, wherein the training module is used to train the Gaussian process regression model through an optimal voltage interval, thereby obtaining a trained Gaussian process regression model;
[0035] A working data acquisition module, the working data acquisition module is used to acquire working data of the battery to be estimated;
[0036] A battery health status acquisition module is used to input the working data into the Gaussian process regression model to obtain the battery health status.
[0037] The electric vehicle battery health status estimation method of the present application extracts the optimal voltage range that has a strong correlation with battery life decay through experimental data and health factors, and makes predictions based on the optimal voltage range, thereby having more accurate precision. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 It is a flow chart of a method for estimating the health status of an electric vehicle battery in one embodiment of the present application.
[0039] Figure 2 It is used to realize Figure 1An electronic device schematic diagram of an electric vehicle battery health status estimation method is shown.
[0040] Figure 3 4 is a schematic diagram of the time-voltage differential analysis result of the voltage in one embodiment of the present application.
[0041] Figure 4 It is a schematic diagram of the time-voltage difference analysis results and the health characteristic correlation analysis results in one embodiment of the present application.
[0042] Figure 5 It is a structural diagram of a battery health status estimation test device in one embodiment of the present application. DETAILED DESCRIPTION
[0043] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0044] Figure 1 It is a flow chart of a method for estimating the health status of an electric vehicle battery in one embodiment of the present application.
[0045] like Figure 1 The electric vehicle battery health status estimation method shown includes:
[0046] Step 1: Obtain experimental data for training;
[0047] Step 2: Select health factors based on training experimental data;
[0048] Step 3: Obtaining an optimal voltage range according to the training experimental data and the health factor;
[0049] Step 4: Obtain the Gaussian process regression model;
[0050] Step 5: training the Gaussian process regression model using an optimal voltage interval, thereby obtaining a trained Gaussian process regression model;
[0051] Step 6: Obtain the working data of the battery to be estimated;
[0052] Step 7: Input the working data into the Gaussian process regression model to obtain the battery health status.
[0053] The electric vehicle battery health status estimation method of the present application extracts the optimal voltage range that has a strong correlation with battery life decay through experimental data and health factors, and makes predictions based on the optimal voltage range, thereby having more accurate precision.
[0054] In this embodiment, the training experimental data includes voltage data, current data, temperature data, time data, cumulative charging capacity data, cumulative discharging capacity data, charging and discharging flag data, and charging calibration flag data.
[0055] In this embodiment, selecting health factors according to training experimental data includes:
[0056] Perform the following operations for each type of training experimental data:
[0057] Obtain the charging voltage-time versus battery aging curve during the constant current charging process of the battery to be estimated;
[0058] Obtaining a correlation curve of training experimental data during a constant current charging process of the battery to be estimated;
[0059] Whether the experimental data is used as a health factor is determined based on the charging voltage-time curve versus battery aging curve and the correlation curve of the training experimental data.
[0060] In this embodiment, the correlation is obtained by the following formula:
[0061] in,
[0062] R 2 It is the coefficient of determination, which indicates how much of the variation in the dependent variable can be explained by the variation in the independent variable. It is a measure of the degree of correlation between the actual value and the predicted value. The value range is usually between 0 and 1. The closer the value is to 1, the higher the correlation. i is the i-th actual observation value; is the predicted value of the ith model; is the average of all observations.
[0063] See also Figure 3 In this embodiment, the charging voltage-time at each time point in the constant current charging process of the battery to be estimated is obtained using the following formula:
[0064] in,
[0065] t k At the kth moment in the charge / discharge process, t si Indicates the si-th moment of charge / discharge; V k and V si are the battery voltage values corresponding to the kth moment and the sith moment respectively.
[0066] In this embodiment, when the health factor is one, obtaining the optimal voltage interval according to the training experimental data and the health factor includes:
[0067] The health factor is obtained in multiple voltage segments during the correlation calculation process, wherein the determination coefficient corresponding to each voltage point in each voltage segment exceeds a first preset threshold.
[0068] In this embodiment, when there are multiple health factors, obtaining the optimal voltage interval according to the training experimental data and the health factors includes:
[0069] A plurality of voltage segments are obtained for each health factor in the correlation calculation process, respectively, wherein the determination coefficient corresponding to each voltage point in each voltage segment exceeds a second preset threshold, and the second preset threshold is greater than the first preset threshold.
[0070] The present application is further described in detail below by way of examples. It should be understood that the examples do not constitute any limitation to the present application.
[0071] Since the current measurement error is generally large in practice, the incremental capacity analysis can be replaced by the differential analysis of the battery time-voltage curve. The specific calculation is as follows:
[0072]
[0073] The time-voltage differential analysis results of the voltage can be obtained, such as Figure 3 shown.
[0074] It can be seen that the time-voltage evolution laws corresponding to different voltage intervals may be different, so the correlation analysis method is used here to study the correlation between the evolution laws of different voltage intervals and battery capacity. The linear regression determination coefficient is used here for correlation analysis, as shown in the formula:
[0075] in,
[0076] R 2 It is the coefficient of determination, which indicates how much of the variation in the dependent variable can be explained by the variation in the independent variable. It is a measure of the degree of correlation between the actual value and the predicted value. The value range is usually between 0 and 1. The closer the value is to 1, the higher the correlation. i is the i-th actual observation value; is the predicted value of the ith model; is the average value of all observed values. In this embodiment, the observed value is the battery capacity change information obtained during the experiment, which is a set of vectors; is the calculated IC value, which is also a set of vectors. is the average value of the capacity change.
[0077] The analysis results are as follows Figure 4As shown, the horizontal axis of the differential analysis of the time-voltage curve and the correlation analysis results are uniformly aligned to voltage, which is convenient for locating characteristic points. According to the analysis results, it can be seen that the evolution laws of HF in different voltage intervals are different, but it can be seen that there are some voltage intervals, and the HF extracted from them has a strong correlation with the battery life decay. These intervals correspond to different modes of battery aging in the time-voltage differential analysis (lithium inventory loss, positive and negative electrode active material loss, etc.). And a simple conclusion can be drawn: selecting a voltage interval containing the highest peak range of IC can obtain better SOH estimation accuracy, and for NMC batteries, selecting a voltage interval greater than 3.8V, the SOH estimation accuracy is poor.
[0078] The present application also provides a set of equipment for testing the battery to be tested. The test equipment includes a bidirectional power supply, a communication module, a data acquisition module, a router, a signal conversion module, etc. The entire device can realize battery charging and discharging, BMS communication, and data acquisition functions. The collected data is used as estimated data to estimate the battery health status SOH. The structural diagram of the battery health status estimation test equipment is shown in Figure 5 .
[0079] In this embodiment, the software is developed using the LabVIEW language, and the SOH algorithm is developed using the Python program. The LabVIEW software indirectly implements the battery health status estimation by calling the algorithm program implemented in Python. The Python algorithm program uses the Numpy scientific computing module, the Pandas data analysis module, and the Pytorch neural network algorithm module. Since Python calls multiple modules, the entire algorithm program needs to be run in a virtual environment where these modules are installed, and the virtual environment configuration uses Anaconda3.
[0080] The LabVIEW software program can communicate directly with the CAN communication module, control the bidirectional power supply and communicate with the battery BMS through the CAN communication module. The software can realize the battery charging and discharging function, the data acquisition function of the charging and discharging process, the SOH estimation program calling function, and the fault monitoring function of the charging and discharging process.
[0081] The battery health status estimation algorithm designed in this application realizes the SOH estimation of single cells and battery packs, and the estimation data only requires a few battery charge and discharge cycles;
[0082] The battery pack test process can match different battery protocols by fine-tuning the internal conversion module of the program;
[0083] CAN communication is used for control, with a maximum baud rate of 500K and adjustable baud rate;
[0084] The neural network algorithm is used to extract data features, and the data calculation accuracy is high; as the data in the model increases, the prediction becomes more accurate, and the model has growth potential;
[0085] Realize 8-channel voltage channel acquisition, resolution: 16 bits; input range: 0~±1000V; full range absolute error: ≤1%; sampling rate: 250KS / s;
[0086] Realize 8-way current channel acquisition, input range: ±100A; full range absolute error: ≤1%; sampling rate: 250KS / s;
[0087] Realize 4-channel temperature acquisition, measuring range: -50℃~300℃.
[0088] In this embodiment, firstly, based on the experimental data of the power battery, the evolution law of the charging voltage-time with battery aging during the constant current charging process of the battery is excavated. Based on this evolution law, the capacity-related health feature - charging capacity is extracted within a fixed voltage range to estimate the SOH value related to the battery capacity. However, since the actual charging process is not as stable and complete as the experimental charging process, it is necessary to extract health features and calculate the battery SOH value within different voltage ranges. Therefore, based on the experimental data, a voltage-time / capacity differential analysis is performed, and the correlation analysis results of the health features and the battery capacity are combined to study the SOH estimation accuracy of the extracted health features within different voltage ranges, and a universal optimal voltage range selection law is obtained. According to this law, the optimal voltage range in the actual charging process of the battery can be selected to achieve the purpose of accurately estimating the battery SOH.
[0089] In this embodiment, after obtaining the experimental data, data mining is first performed to extract valuable data. Then different charging and discharging schemes are selected, and the voltage range in which the training set analysis features are located is selected. Then, according to the screening rules, the optimal voltage interval is selected, the relevant features of the capacity are extracted, and then the SOH related to the capacity is calculated.
[0090] In this embodiment, the parameters such as voltage, current, temperature, time, cumulative charge / discharge capacity, charge / discharge flag, and charge calibration flag required in the SOH calculation process are input by the "monitoring module" and the data is saved in the corresponding file. LabVIEW is used to call the Python interpreter to indirectly call the interface program. The Python interpreter calls the SOH interface program and inputs the parameter file to realize the SOH calculation.
[0091] In this embodiment, the entire device includes a communication module, a conversion module, an acquisition module, a bidirectional power supply, etc. The communication module realizes the communication between the BMS and the bidirectional power supply, and uploads the BMS data message to the software. The conversion module converts high-voltage signals such as voltage and current into small signals below 10V for acquisition by the acquisition module. The acquisition module sends the collected small signals to the software, and the acquisition module can select LAN or CAN or other communication methods. The bidirectional power supply has a power of 30KW and is programmable and controlled for battery charging and discharging testing.
[0092] In this embodiment, the figure introduces 380V power supply, 220V power supply, LAN interface, emergency stop, collection terminal wiring, etc.
[0093] In this embodiment, the battery health status estimation software control logic design mainly includes several parts such as status parameter monitoring, charge and discharge control, and battery high voltage power-on and power-off. The status parameter monitoring part is used to monitor voltage extremes, battery capacity extremes, current, BMS faults, single cell voltage and other parameters in real time. When the parameters exceed the boundaries, the software will control the device to make corresponding response actions. The charge and discharge control part is used to control the parameter setting, start, stop, etc. of the bidirectional power supply. When the monitoring part detects a fault, the bidirectional power supply will automatically shut down. The high voltage power-on and high voltage power-off parts are used to send CAN message instructions to the battery BMS to control the battery power-on and power-off.
[0094] The present application also provides an electric vehicle battery health status estimation device, which includes an experimental data acquisition module for the battery to be estimated, a health factor selection module, an optimal voltage range acquisition module, a health feature acquisition module, a model acquisition module, and a battery health status acquisition module, wherein:
[0095] The experimental data acquisition module of the battery to be estimated is used to acquire the experimental data of the battery to be estimated;
[0096] The health factor selection module is used to select health factors based on experimental data;
[0097] The optimal voltage interval acquisition module is used to acquire the optimal voltage interval according to the experimental data and the health factor;
[0098] The health feature acquisition module is used to acquire health features;
[0099] The model acquisition module is used to obtain the trained Gaussian process regression model;
[0100] The battery health status acquisition module is used to input the health feature into the Gaussian process regression model to acquire the battery health status.
[0101] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, the above-mentioned electric vehicle battery health status estimation method is implemented.
[0102] The present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can implement the above-mentioned electric vehicle battery health status estimation method.
[0103] Figure 2 It is an exemplary structural diagram of an electronic device capable of implementing the electric vehicle battery health status estimation method provided according to an embodiment of the present application.
[0104] like Figure 2 As shown, the electronic device includes an input device 501, an input interface 502, a central processor 503, a memory 504, an output interface 505, and an output device 506. The input interface 502, the central processor 503, the memory 504, and the output interface 505 are interconnected through a bus 507, and the input device 501 and the output device 506 are connected to the bus 507 through the input interface 502 and the output interface 505, respectively, and then connected to other components of the electronic device. Specifically, the input device 501 receives input information from the outside, and transmits the input information to the central processor 503 through the input interface 502; the central processor 503 processes the input information based on the computer executable instructions stored in the memory 504 to generate output information, temporarily or permanently stores the output information in the memory 504, and then transmits the output information to the output device 506 through the output interface 505; the output device 506 outputs the output information to the outside of the electronic device for use by the user.
[0105] That is to say, Figure 2 The electronic device shown can also be implemented as comprising: a memory storing computer executable instructions; and one or more processors, which can implement the combination when executing the computer executable instructions. Figure 1 Described is a method for estimating the state of health of electric vehicle batteries.
[0106] In one embodiment, Figure 2 The electronic device shown can be implemented to include: a memory 504 configured to store executable program code; and one or more processors configured to run the executable program code stored in the memory 504 to execute the electric vehicle battery health status estimation method in the above embodiment.
[0107] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0108] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0109] Computer readable media include permanent and non-permanent, removable and non-removable, and the media can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), data versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.
[0110] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and a module, a program segment or a part of a code includes one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes identified in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or the total flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0111] The processor referred to in this embodiment may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
[0112] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the device / terminal equipment by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0113] In this embodiment, if the module / unit integrated in the device / terminal equipment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. Although the present application is disclosed as above in terms of a preferred embodiment, it is not actually intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.
[0114] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0115] In addition, it is obvious that the word "comprising" does not exclude other units or steps. Multiple units, modules or devices stated in the device claim can also be implemented by one unit or the overall device through software or hardware.
[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for estimating the health status of electric vehicle batteries, It is characterized in that The electric vehicle battery health status estimation method comprises: Obtain experimental data for training; Select health factors based on experimental data for training; Obtaining an optimal voltage range according to the training experimental data and the health factor; Get the Gaussian process regression model; The Gaussian process regression model is trained by using an optimal voltage interval, thereby obtaining a trained Gaussian process regression model; Obtaining working data of the battery to be estimated; The working data is input into the Gaussian process regression model to obtain the battery health state.
2. The method for estimating the health status of an electric vehicle battery according to claim 1, It is characterized in that The training experimental data includes voltage data, current data, temperature data, time data, cumulative charging capacity data, cumulative discharging capacity data, charging and discharging flag data, and charging calibration flag data.
3. The method for estimating the health status of an electric vehicle battery as claimed in claim 2, It is characterized in that The selecting of health factors according to the training experimental data includes: Perform the following operations for each type of training experimental data: Obtain the charging voltage-time versus battery aging curve during the constant current charging process of the battery to be estimated; Obtaining a correlation curve of training experimental data during a constant current charging process of the battery to be estimated; Whether the experimental data is used as a health factor is determined based on the charging voltage-time curve versus battery aging curve and the correlation curve of the training experimental data.
4. The method for estimating the health status of an electric vehicle battery according to claim 3, It is characterized in that The correlation is obtained by the following formula: in, R 2 is the coefficient of determination, which indicates how much of the variation in the dependent variable can be explained by the variation in the independent variable. It is a measure of the degree of correlation between the actual value and the predicted value. Its value range is usually between 0 and 1. The closer the value is to 1, the higher the correlation. yi is the ith actual observation value; is the predicted value of the ith model; is the average of all observations.
5. The method for estimating the health status of an electric vehicle battery according to claim 4, It is characterized in that The charging voltage-time at each time point in the constant current charging process of the battery to be estimated is obtained using the following formula: in, t k At the kth moment in the charge / discharge process, t si Indicates the si-th moment of charge / discharge; V k and V si are the battery voltage values corresponding to the kth moment and the sith moment respectively.
6. The method for estimating the health status of an electric vehicle battery according to claim 5, It is characterized in that When the health factor is one, obtaining the optimal voltage range according to the training experimental data and the health factor includes: The health factor is obtained in multiple voltage segments during the correlation calculation process, wherein the determination coefficient corresponding to each voltage point in each voltage segment exceeds a first preset threshold.
7. An electric vehicle battery health status estimation device, It is characterized in that The electric vehicle battery health status estimation device comprises: A training experimental data acquisition module, wherein the training experimental data acquisition module is used to acquire training experimental data; A health factor selection module, wherein the health factor selection module is used to select health factors according to training experimental data; An optimal voltage interval acquisition module, the optimal voltage interval acquisition module is used to acquire an optimal voltage interval according to the training experimental data and the health factor; A model acquisition module, wherein the model acquisition module is used to acquire a Gaussian process regression model; A training module, wherein the training module is used to train the Gaussian process regression model through an optimal voltage interval, thereby obtaining a trained Gaussian process regression model; A working data acquisition module, the working data acquisition module is used to acquire working data of the battery to be estimated; A battery health status acquisition module is used to input the working data into the Gaussian process regression model to obtain the battery health status.
