Battery remaining life prediction method, device, equipment and medium

Abstract

The present application relates to the field of lithium battery technology, and specifically provides a method, device, equipment and medium for predicting the remaining service life of a battery, aiming to solve the technical problem of low accuracy of the predicted remaining service life of the battery. To this end, the present application includes: obtaining the early charge and discharge data of the battery; obtaining the later charge and discharge data based on the early charge and discharge data; combining the early charge and discharge data and the later charge and discharge data to obtain the full cycle charge and discharge data; training the life prediction algorithm based on the full cycle charge and discharge data to obtain a prediction model; obtaining real-time charge and discharge data; inputting the real-time charge and discharge data into the prediction model to obtain the remaining service life of the battery.

Description

Technical Field

[0001] The present application relates to the field of lithium battery technology, and in particular to a method, device, equipment and medium for predicting remaining battery life. Background Art

[0002] With the rapid development of renewable energy technology, lithium batteries are increasingly used in power grid energy storage, electric vehicles, smart homes and other fields. As the remaining life of lithium batteries will continue to shorten with the increase in the number of charge and discharge cycles, when it is shortened to a certain extent, the conversion efficiency of the battery will decrease, and there is a risk of spontaneous combustion. Therefore, predicting the remaining life of lithium batteries has important practical value and realistic significance. However, due to factors such as temperature fluctuations and aging during the use of lithium batteries, it is difficult to accurately predict the remaining service life of lithium batteries, which brings challenges to the safe use and maintenance of lithium batteries.

[0003] In the prior art, since the life of lithium batteries is 3 to 5 years, it is difficult to obtain the status data of lithium batteries throughout their entire life. Therefore, the data of early charge and discharge cycles are usually analyzed to predict the remaining life of lithium batteries. However, in the early stage of the charge and discharge cycle, the health of lithium batteries is better, and the life prediction based on the data of early charge and discharge cycles results in the remaining service life being longer than the actual remaining service life, which in turn leads to the technical problem of low accuracy of the predicted remaining service life of the battery. Summary of the invention

[0004] In order to overcome the above-mentioned defects, the present application is proposed to provide a solution or at least partially solve the technical problem of low accuracy in predicting the remaining service life of a battery.

[0005] In a first aspect, the present application provides a method for predicting remaining battery life, comprising:

[0006] Obtain the battery's early charge and discharge data;

[0007] According to the early charge and discharge data, late charge and discharge data are obtained;

[0008] Combining the early charge and discharge data with the late charge and discharge data to obtain full cycle charge and discharge data;

[0009] According to the full cycle charge and discharge data, a life prediction algorithm is trained to obtain a prediction model;

[0010] Get real-time charging and discharging data;

[0011] The real-time charge and discharge data is input into the prediction model to obtain the remaining life of the battery.

[0012] In a technical solution of the above-mentioned method for predicting the remaining life of a battery, obtaining the later charging and discharging data according to the earlier charging and discharging data includes:

[0013] According to the previous charge and discharge data, a data expansion algorithm is trained to obtain a data expansion model;

[0014] According to the number of later charge and discharge times, the earlier charge and discharge data are extended using the data extension model to obtain later charge and discharge data.

[0015] In a technical solution of the above-mentioned method for predicting the remaining life of a battery, the obtaining of the early charge and discharge data of the battery includes:

[0016] Obtain original early charge and discharge data;

[0017] Cleaning the original early stage charge and discharge data to obtain cleaned early stage charge and discharge data;

[0018] The charge and discharge data in the early stage of cleaning are normalized to obtain the charge and discharge data in the early stage.

[0019] In a technical solution of the above-mentioned method for predicting the remaining life of a battery, the life prediction algorithm is trained according to the full cycle charge and discharge data to obtain a prediction model, including:

[0020] Obtaining charge and discharge characteristic data according to the full cycle charge and discharge data;

[0021] The prediction algorithm is trained using the charge and discharge characteristic data to obtain the prediction model.

[0022] In a technical solution of the above-mentioned method for predicting the remaining life of a battery, the charging and discharging characteristic data is obtained according to the full-cycle charging and discharging data, including:

[0023] Screening the full-cycle charge and discharge data to obtain screened charge and discharge data;

[0024] Feature extraction is performed on the screened charge and discharge data to obtain the charge and discharge feature data.

[0025] In a technical solution of the above-mentioned method for predicting the remaining life of a battery, the prediction algorithm is trained using the charge and discharge characteristic data to obtain the prediction model, including:

[0026] Inputting the charge and discharge characteristic data into a local feature extraction algorithm to obtain local feature data;

[0027] The preset sequence algorithm is trained using local feature data to obtain the prediction model.

[0028] In a technical solution of the above-mentioned method for predicting the remaining life of a battery, the charging and discharging data includes:

[0029] Voltage, current, temperature, capacity, health status.

[0030] In a second aspect, the present application provides a battery remaining life prediction device, comprising:

[0031] An acquisition module is used to obtain the early charge and discharge data of the battery;

[0032] An analysis module, used to obtain later charging and discharging data based on the earlier charging and discharging data;

[0033] A combining module, used for combining the early charge and discharge data with the late charge and discharge data to obtain full cycle charge and discharge data;

[0034] A training module, used to train a life prediction algorithm according to the full cycle charge and discharge data to obtain a prediction model;

[0035] A processing module, used to obtain real-time charging and discharging data;

[0036] The prediction module is used to input the real-time charge and discharge data into the prediction model to obtain the remaining life.

[0037] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the method as described in any one of the first aspects through the computer program.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium storing a plurality of program codes, wherein the program codes are suitable for being loaded and run by a processor to execute the method as described in any one of the first aspects.

[0039] The present application provides a method, device, equipment and medium for predicting the remaining life of a battery. The method specifically comprises: obtaining early charge and discharge data of a battery; obtaining late charge and discharge data based on the early charge and discharge data; combining the early charge and discharge data with the late charge and discharge data to obtain full-cycle charge and discharge data; training a life prediction algorithm based on the full-cycle charge and discharge data to obtain a prediction model; obtaining real-time charge and discharge data; inputting the real-time charge and discharge data into the prediction model to obtain the remaining life of the battery, thereby improving the prediction accuracy of the remaining life of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The disclosure of the present application will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present application. In addition, similar numbers in the drawings are used to represent similar components, among which:

[0041] Figure 1 A schematic diagram of the structure of a battery remaining life prediction system embodiment 1 provided in the present application;

[0042] Figure 2 A flowchart of a method for predicting remaining battery life according to an embodiment of the present application;

[0043] Figure 3 A schematic diagram of a flow chart of a second embodiment of a method for predicting remaining battery life provided in an embodiment of the present application;

[0044] Figure 4 A flowchart of a third embodiment of a method for predicting remaining battery life provided in an embodiment of the present application;

[0045] Figure 5 A flowchart of a fourth embodiment of a method for predicting remaining battery life provided in an embodiment of the present application;

[0046] Figure 6 A flowchart of a fifth embodiment of a method for predicting remaining battery life provided in an embodiment of the present application;

[0047] Figure 7 A flowchart of a sixth embodiment of a method for predicting remaining battery life provided in an embodiment of the present application;

[0048] Figure 8 A flowchart of a seventh embodiment of a method for predicting remaining battery life provided in an embodiment of the present application;

[0049] Fig. 9 A schematic diagram of the structure of a first embodiment of a battery remaining life prediction device provided in an embodiment of the present application;

[0050] Fig.10 A schematic diagram of the structure of an electronic device embodiment 1 provided in an embodiment of the present application;

[0051] Fig.11 This is the battery remaining life prediction result diagram.

[0052] Reference numerals list :

[0053] 11: Data acquisition module; 12: Data preprocessing module; 13: Data expansion module; 14: Model training module; 15: Prediction module; 16: Prediction data feedback module; 21: Acquisition module; 22: Analysis module; 23: Combination module; 24: Training module; 25: Processing module; 26: Prediction module; 31: Processor; 32: Memory. DETAILED DESCRIPTION

[0054] Some embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.

[0055] In the description of the present application, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, memory, and may also include software parts, such as program code, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program code, such as a disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B" and may include only A, only B or A and B. The singular terms "one" and "the" may also include plural forms.

[0056] In the prior art, since the life cycle of lithium batteries is 3 to 5 years, it takes a long time to obtain the full life cycle data of lithium batteries. In addition, in the early stage of lithium battery use, its condition is good. The remaining life of the lithium battery is predicted based on the early operation data of the lithium battery. The predicted remaining life is longer than the actual remaining life, which leads to the technical problem of low accuracy of the predicted remaining life of the lithium battery.

[0057] Based on this, in order to solve the above technical problems, the present application provides a new method for predicting the remaining life of a battery, so as to improve the accuracy of predicting the remaining life of a lithium battery.

[0058] Figure 1 A battery remaining life prediction system is provided according to an embodiment of the present application, such as Figure 1As shown, the system includes: a data acquisition module 11, a data preprocessing module 12, a data expansion module 13, a model training module 14, a prediction module 15, and a prediction data feedback module 16.

[0059] Among them, the data acquisition device 11 obtains the original preliminary charge and discharge data of the battery, and sends the original preliminary charge and discharge data to the data preprocessing module 12. The data preprocessing module 12 receives and cleans and normalizes the preliminary charge and discharge data to obtain the preliminary charge and discharge data. The data expansion module 13 obtains the later charge and discharge data based on the preliminary charge and discharge data, and combines the preliminary charge and discharge data with the later charge and discharge data to obtain the full-cycle charge and discharge data. The model training module 14 trains the life prediction algorithm based on the full-cycle charge and discharge data to obtain a prediction model. During the operation of the lithium battery, the data acquisition module 11 obtains real-time charge and discharge data, and sends the real-time charge and discharge data to the prediction module 15. The prediction module 15 obtains the remaining life of the battery based on the real-time charge and discharge data using the prediction model. The prediction data feedback module 16 sends the remaining life of the battery to the data acquisition module 11.

[0060] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0061] Figure 2 The following is a flow chart of a method for predicting the remaining battery life provided in the present application. Figure 2 As shown, specifically, the method includes:

[0062] Step S201: Acquire the previous charge and discharge data of the battery.

[0063] In this embodiment, the early charge and discharge data of the battery are acquired through a data acquisition device.

[0064] In this embodiment, for example, the data of the battery during the charging and discharging process is collected in real time through the energy storage battery management system in the data collection device.

[0065] In this embodiment, the early charge and discharge data include: voltage, current, temperature, capacity, and health status.

[0066] Step S202: obtaining later charge and discharge data according to earlier charge and discharge data.

[0067] In this embodiment, the early operation data and operating environment data of the battery are obtained based on the early charge and discharge data, and then the later charge and discharge data are predicted based on the battery parameters, the early operation data and the operating environment data.

[0068] Step S203: combining the early charge and discharge data and the late charge and discharge data to obtain full cycle charge and discharge data.

[0069] In this embodiment, the early charge and discharge data and the late charge and discharge data are combined in chronological order to obtain the full cycle charge and discharge data.

[0070] Step S204: training the life prediction algorithm according to the full cycle charge and discharge data to obtain a prediction model.

[0071] In this embodiment, a life prediction algorithm is preset, and the full cycle charge and discharge data is input into the life prediction algorithm to obtain a prediction model.

[0072] Step S205: Acquire real-time charge and discharge data.

[0073] In this embodiment, during the operation of the lithium battery, the charge and discharge data are collected in real time.

[0074] Step S206: input the real-time charge and discharge data into the prediction model to obtain the remaining life of the battery.

[0075] In this embodiment, the real-time charge and discharge data is input into the prediction model to obtain the remaining life of the battery, wherein the remaining life of the battery can be the remaining number of charge and discharge cycles or the remaining operating time.

[0076] In this embodiment, early charge and discharge data of the battery are obtained; late charge and discharge data are obtained based on the early charge and discharge data; the early charge and discharge data and the late charge and discharge data are combined to obtain full-cycle charge and discharge data; the life prediction algorithm is trained based on the full-cycle charge and discharge data to obtain a prediction model; real-time charge and discharge data are obtained; the real-time charge and discharge data are input into the prediction model to obtain the remaining life of the battery. Compared with the prior art, the remaining life of the lithium battery is predicted by analyzing the data of the early charge and discharge cycles, which leads to low accuracy in the predicted remaining service life of the battery. In this application, the early charge and discharge data are expanded to obtain late charge and discharge data, and the early charge and discharge data and the late charge and discharge data are combined to obtain full-cycle charge and discharge data, and the life prediction algorithm is trained based on the full-cycle charge and discharge data to obtain a prediction model, so that after obtaining the real-time charge and discharge data, the remaining service life of the battery is predicted based on the prediction model, so as to improve the prediction accuracy and reliability of the remaining service life of the battery.

[0077] Figure 3 The flowchart of the second embodiment of the method for predicting the remaining battery life provided in the present application is based on the above embodiment. Figure 3 As shown, specifically, a specific method of step S202 is:

[0078] Step S301: training a data expansion algorithm based on previous charge and discharge data to obtain a data expansion model.

[0079] In this embodiment, for example, a Gaussian regression algorithm is used to perform training using previous charge and discharge data to obtain a Gaussian regression model.

[0080] Step S302: according to the number of later charge and discharge times, the data expansion model is used to expand the earlier charge and discharge data to obtain later charge and discharge data.

[0081] In this embodiment, for example, a Gaussian regression model is used to expand the early charge and discharge data according to the number of late charge and discharge times to obtain late charge and discharge data.

[0082] In this embodiment, the early charge and discharge data may be data generated during the operation of the first 100 charge and discharge cycles of the lithium battery.

[0083] In this embodiment, the data expansion algorithm is trained based on the early charge and discharge data to obtain the data expansion model; according to the later charge and discharge times, the early charge and discharge data is expanded using the data expansion model to obtain the later charge and discharge data, and the battery data for the entire life cycle can be obtained.

[0084] Figure 4 The flowchart of the third embodiment of the method for predicting the remaining battery life provided in the present application is based on the above embodiment. Figure 4 As shown, specifically, one implementation of step S201 includes:

[0085] Step S401: obtaining original early charge and discharge data.

[0086] In this embodiment, for example, the data collected in real time by the energy storage battery management system during the charging and discharging process of the battery is the original early charging and discharging data.

[0087] Step S402: cleaning the original early stage charge and discharge data to obtain cleaned early stage charge and discharge data.

[0088] In this embodiment, abnormal values ​​and repeated values ​​in the original early charge and discharge data are processed, mainly by deleting the abnormal values ​​and removing the repeated values.

[0089] Step S403: normalizing the charge and discharge data in the early stage of cleaning to obtain the charge and discharge data in the early stage.

[0090] In this embodiment, the charge and discharge data before cleaning is mapped to a specific interval to obtain the charge and discharge data before cleaning.

[0091] In this embodiment, for example, the charge and discharge data before cleaning can be mapped to a range from 0 to 1.

[0092] In this embodiment, original early stage charge and discharge data are obtained; the original early stage charge and discharge data are cleaned to obtain cleaned early stage charge and discharge data; and the cleaned early stage charge and discharge data are normalized to obtain early stage charge and discharge data, thereby improving data quality.

[0093] Figure 5 The flowchart of the fourth embodiment of the method for predicting the remaining battery life provided in the present application is based on the above embodiment. Figure 5 As shown, specifically, one implementation of step S204 includes:

[0094] Step S501: obtaining charge and discharge characteristic data according to the full cycle charge and discharge data.

[0095] In this embodiment, the data in the full cycle charge and discharge data are sorted according to the importance of affecting the battery life, and the data with high importance is obtained as the charge and discharge characteristic data.

[0096] In this embodiment, the charge and discharge characteristic data may be the battery capacity attenuation rate, the internal resistance change rate, and the temperature fluctuation range, which may reflect the aging degree and performance changes of the battery.

[0097] Step S502: Use the charge and discharge characteristic data to train the prediction algorithm to obtain a prediction model.

[0098] In this embodiment, for example, the prediction algorithm may be a neural network algorithm.

[0099] In this embodiment, the charge and discharge characteristic data are used to train the neural network algorithm to obtain a neural network model.

[0100] In this embodiment, charge and discharge characteristic data are obtained based on the full cycle charge and discharge data; the charge and discharge characteristic data are used to train the prediction algorithm to obtain a prediction model to improve the robustness of the prediction model.

[0101] Figure 6 The flowchart of the fifth embodiment of the method for predicting the remaining battery life provided in the present application is based on the above embodiment. Figure 6 Specifically, one implementation of step S501 includes:

[0102] Step S601: screening the full cycle charge and discharge data to obtain screened charge and discharge data.

[0103] In this embodiment, the full-cycle charge and discharge data are screened according to the data category to obtain screened charge and discharge data.

[0104] Step S602: extracting features from the screened charge and discharge data to obtain charge and discharge feature data.

[0105] In this embodiment, features in the charge and discharge data are extracted and screened to obtain charge and discharge feature data.

[0106] In this embodiment, for example, a principal component analysis algorithm may be used to extract features from the screened charge and discharge data.

[0107] In this embodiment, the full cycle charge and discharge data are screened to obtain screened charge and discharge data; feature extraction is performed on the screened charge and discharge data to obtain charge and discharge feature data, and further data with a high degree of influence on the remaining life of the battery can be obtained.

[0108] Figure 7 The flowchart of the sixth embodiment of the method for predicting the remaining battery life provided in the present application is based on the above embodiment. Figure 7 As shown, specifically, one implementation of step S502 includes:

[0109] Step S701: inputting the charge and discharge characteristic data into a local feature extraction algorithm to obtain local feature data.

[0110] In this embodiment, for example, the charge and discharge characteristic data are input into a one-dimensional convolutional neural network to obtain local characteristic data.

[0111] Step S702: Use local feature data to train a preset sequence algorithm to obtain a prediction model.

[0112] In this embodiment, for example, local feature data is input into a long short-term memory network for training, and the model is verified using test charge and discharge data during the training process, and the model parameters are adjusted according to the verification results to obtain a prediction model.

[0113] In this embodiment, the charge and discharge characteristic data are input into the local feature extraction algorithm to obtain local feature data; the preset sequence algorithm is trained using the local feature data to obtain a prediction model, so as to improve the ability to capture the nonlinear degradation characteristics and long-cycle dependencies of the battery, and to improve the accuracy and robustness of the battery remaining life prediction.

[0114] Figure 8A flowchart of a method for predicting the remaining battery life according to an embodiment of the present application is shown in FIG. Figure 8 As shown, including:

[0115] Step S801: Acquire and use previous charge and discharge data to train a data expansion algorithm to obtain a data expansion model.

[0116] Step S802: according to the number of later charge and discharge times, the data expansion model is used to expand the earlier charge and discharge data to obtain later charge and discharge data.

[0117] Step S803: combining the early charge and discharge data and the late charge and discharge data to obtain full cycle charge and discharge data.

[0118] Step S804: training the life prediction algorithm according to the full cycle charge and discharge data to obtain a prediction model.

[0119] Step S805: input the real-time charge and discharge data into the prediction model to obtain the remaining life of the battery.

[0120] In this embodiment, the early charge and discharge data are obtained and used to train the data expansion algorithm to obtain a data expansion model; according to the number of later charge and discharge times, the early charge and discharge data are expanded using the data expansion model to obtain later charge and discharge data; the early charge and discharge data and the later charge and discharge data are combined to obtain full-cycle charge and discharge data; based on the full-cycle charge and discharge data, the life prediction algorithm is trained to obtain a prediction model; the real-time charge and discharge data is input into the prediction model to obtain the remaining life of the battery.

[0121] Furthermore, the present application also provides a battery remaining life prediction device.

[0122] Fig. 9 This is a schematic diagram of the structure of a battery remaining life prediction device embodiment 1 provided in the present application. Fig. 9As shown, the battery remaining life prediction device in the embodiment of the present application mainly includes an acquisition module 21, an analysis module 22, a combination module 23, a training module 24, a processing module 25, and a prediction module 26, wherein one or more of the above modules can be combined into one module. In some embodiments, the acquisition module 21 can be configured to obtain the early charge and discharge data of the battery. The analysis module 22 can be configured to obtain the later charge and discharge data based on the early charge and discharge data. The combination module 23 can be configured to combine the early charge and discharge data and the later charge and discharge data to obtain the full-cycle charge and discharge data. The training module 24 can be configured to train the life prediction algorithm according to the full-cycle charge and discharge data to obtain a prediction model. The processing module 25 can be configured to obtain real-time charge and discharge data. The prediction module 26 can be configured to input the real-time charge and discharge data into the prediction model to obtain the remaining life.

[0123] The battery remaining life prediction device is used to perform Figures 1 to 8 The battery remaining life prediction method embodiment shown in the figure has similar technical principles, technical problems solved and technical effects produced. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process and related instructions of the battery remaining life prediction device can refer to the contents described in the embodiment of the battery remaining life prediction method whose execution subject is the battery remaining life prediction device, and will not be repeated here.

[0124] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above-mentioned embodiment of the present application can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. 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 storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0125] Furthermore, the present application also provides an electronic device.

[0126] Fig.10 This is a schematic diagram of the structure of an electronic device embodiment 1 provided in the present application. Fig.10 As shown, the electronic device includes at least one processor 31 and a memory 32, and the memory 32 can be configured to store and execute the above Figures 1 to 8 The processor 31 may be configured to execute a program in the memory 32, the program including but not limited to a program for executing a method for predicting the remaining life of a battery in the above-mentioned method embodiment. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The electronic device may be a control device device including various electronic devices.

[0127] Fig.11 This is a diagram of the battery remaining life prediction result. It can be seen from the figure that the predicted remaining life obtained by a battery remaining life prediction method proposed in the present application is basically the same as the actual remaining life.

[0128] Furthermore, the present application also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present application, the computer-readable storage medium may be configured to store the execution method Figures 1 to 8 The program of the battery remaining life prediction method of the illustrated embodiment can be loaded and run by a processor to implement the above-mentioned battery remaining life prediction method. For ease of explanation, only the parts related to the embodiment of the present application are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present application. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present application is a non-temporary computer-readable storage medium.

[0129] Further, it should be understood that since the setting of each module is only for illustrating the functional units of the device of the present application, the physical devices corresponding to these modules may be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only schematic.

[0130] It is understood by those skilled in the art that each module in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principle of the present application, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present application.

[0131] So far, the technical solutions of the present application have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principles of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present application.

Claims

1. A method for predicting remaining battery life, characterized in that: include: Obtain the battery's early charge and discharge data; According to the early charge and discharge data, late charge and discharge data are obtained; Combining the early charge and discharge data with the late charge and discharge data to obtain full cycle charge and discharge data; According to the full cycle charge and discharge data, a life prediction algorithm is trained to obtain a prediction model; Get real-time charging and discharging data; The real-time charge and discharge data is input into the prediction model to obtain the remaining life of the battery.

2. The method according to claim 1, characterized in that The step of obtaining the later charging and discharging data according to the earlier charging and discharging data includes: According to the previous charge and discharge data, a data expansion algorithm is trained to obtain a data expansion model; According to the number of later charge and discharge times, the earlier charge and discharge data are extended using the data extension model to obtain later charge and discharge data.

3. The method according to claim 1, characterized in that The obtaining of the early charge and discharge data of the battery includes: Obtain original early charge and discharge data; Cleaning the original early stage charge and discharge data to obtain cleaned early stage charge and discharge data; The charge and discharge data in the early stage of cleaning are normalized to obtain the charge and discharge data in the early stage.

4. The method according to any one of claims 1 to 3, characterized in that The life prediction algorithm is trained according to the full cycle charge and discharge data to obtain a prediction model, including: Obtaining charge and discharge characteristic data according to the full cycle charge and discharge data; The prediction algorithm is trained using the charge and discharge characteristic data to obtain the prediction model.

5. The method according to claim 4, characterized in that The charging and discharging characteristic data is obtained according to the full cycle charging and discharging data, including: Screening the full-cycle charge and discharge data to obtain screened charge and discharge data; Feature extraction is performed on the screened charge and discharge data to obtain the charge and discharge feature data.

6. The method according to claim 4, characterized in that The method of training the prediction algorithm using the charge and discharge characteristic data to obtain the prediction model includes: Inputting the charge and discharge characteristic data into a local feature extraction algorithm to obtain local feature data; The preset sequence algorithm is trained using local feature data to obtain the prediction model.

7. The method according to claim 1, characterized in that The previous charge and discharge data include: Voltage, current, temperature, capacity, health status.

8. A battery remaining life prediction device, characterized in that: include: An acquisition module is used to obtain the early charge and discharge data of the battery; An analysis module, used to obtain later charging and discharging data based on the earlier charging and discharging data; A combining module, used for combining the early charge and discharge data with the late charge and discharge data to obtain full cycle charge and discharge data; A training module, used to train a life prediction algorithm according to the full cycle charge and discharge data to obtain a prediction model; A processing module, used to obtain real-time charging and discharging data; The prediction module is used to input the real-time charge and discharge data into the prediction model to obtain the remaining life.

9. An electronic device, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and executed by a processor to execute the method according to any one of claims 1 to 7.

Images