Predictive maintenance method and system based on energy state of lithium ion battery

Abstract

The invention belongs to the technical field of lithium ion batteries, and provides a predictive maintenance method and system based on the energy state of a lithium ion battery, and the technical scheme is as follows: obtaining the electrical data of the lithium ion battery; performing feature extraction on the electrical data of the lithium ion battery to obtain a feature data set of the lithium ion battery; obtaining a lithium ion battery energy state prediction result based on the characteristic data set of the lithium ion battery and the trained lithium ion battery energy state prediction regression model; and according to a preset lithium ion battery maintenance rule, matching the lithium ion battery energy state prediction result to generate a corresponding lithium ion maintenance scheme. On the basis of improving the accuracy of energy state prediction of the lithium ion battery, lithium electrons are predictively maintained, and the service life of the lithium battery is prolonged.

Description

Technical Field

[0001] The present invention belongs to the technical field of lithium-ion batteries, and in particular relates to a predictive maintenance method and system based on the energy state of lithium-ion batteries. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] As a type of battery with high energy density and long life, lithium-ion batteries are widely used in electric vehicles, portable devices, energy storage and other fields. In order to more effectively manage and utilize lithium-ion batteries, it is crucial to accurately predict their energy state. Traditional energy state prediction methods are usually based on current integration or open circuit voltage estimation. Although these methods are simple, they are limited in accuracy and long-term stability. In addition, there are currently no corresponding processing rules for different energy states of lithium-ion batteries, which is not conducive to the maintenance of lithium-ion batteries and leads to the loss of lithium battery life. Summary of the invention

[0004] In order to solve at least one technical problem existing in the above-mentioned background technology, the present invention provides a predictive maintenance method and system based on the energy state of a lithium-ion battery, which performs regression prediction based on an extracted feature data set of the lithium-ion battery to accurately obtain a prediction result of the energy state of the lithium-ion battery, and matches the prediction result of the energy state of the lithium-ion battery according to preset lithium-ion battery maintenance rules to generate a corresponding lithium-ion maintenance plan, which is beneficial to the maintenance of the lithium-ion battery.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A first aspect of the present invention provides a predictive maintenance method based on the energy state of a lithium-ion battery, comprising the following steps:

[0007] Get electrical data of lithium-ion batteries;

[0008] Extract features from the electrical data of the lithium-ion battery to obtain a feature data set of the lithium-ion battery;

[0009] Based on the characteristic data set of lithium-ion batteries and the trained lithium-ion battery energy state prediction regression model, the lithium-ion battery energy state prediction result is obtained; wherein the characteristic data set of lithium-ion batteries includes voltage characteristic data, current characteristic data, charge and discharge characteristic data and ambient temperature characteristic data; each characteristic is input into the lithium-ion battery energy state prediction regression model as an independent variable, and the lithium-ion battery energy state prediction result is obtained by combining the regression coefficient of the influence strength and direction of each independent variable on the prediction variable;

[0010] According to the preset lithium-ion battery maintenance rules, the lithium-ion battery energy state prediction results are matched to generate the corresponding lithium-ion maintenance plan.

[0011] Furthermore, the process of extracting the voltage characteristic data, the current characteristic data and the charge and discharge characteristic data includes:

[0012] Calculate the voltage mean value according to the voltage data in the electrical data of the lithium-ion battery to obtain voltage characteristic data;

[0013] Calculate the current mean value according to the current data in the electrical data of the lithium-ion battery to obtain the current characteristic data;

[0014] The charge and discharge rate is calculated based on the charge and discharge time in the electrical data of the lithium-ion battery to obtain the charge and discharge characteristic data.

[0015] Furthermore, the lithium-ion battery energy state prediction regression model is:

[0016] Y=β0+β1X1+β2X2+β3X3+β4X4+μ,

[0017] Among them, Y is the prediction result of lithium-ion battery energy state, X1 is voltage characteristic data, X2 is current characteristic data, X3 is charge and discharge characteristic data, X4 is ambient temperature characteristic data, β j (j=1, 2, ..., k) is called the regression coefficient. Each coefficient represents the strength and direction of the influence of the corresponding independent variable on the predicted variable Y. β0 is the intercept, which represents the predicted value of Y when all independent variables are zero. μ is the error term.

[0018] Furthermore, when training the lithium-ion battery energy state prediction regression model, the historical feature data set of the lithium-ion battery is divided into a training set and a test set, the lithium-ion battery energy state prediction regression model is trained based on the training set data, and the lithium-ion battery energy state prediction regression model is tested based on the test set, until the prediction accuracy of the lithium-ion battery energy state prediction regression model meets a preset accuracy threshold or reaches a preset number of times, then the testing of the lithium-ion battery energy state prediction regression model is stopped.

[0019] Furthermore, electrical data of the lithium-ion battery is obtained, and the electrical data is preprocessed, including noise removal, data resampling, and data normalization.

[0020] Furthermore, according to the preset lithium-ion battery maintenance rules, the lithium-ion battery energy state prediction result is matched to generate corresponding lithium-ion battery processing suggestions, including:

[0021] When the predicted temperature value of the lithium-ion battery is greater than the set temperature threshold, a cooling system start instruction is generated to cool the lithium-ion battery;

[0022] When the charge and discharge rate of the lithium-ion battery is less than the set rate threshold, a segmented charge and discharge command is generated to start the segmented charge and discharge mode until the charge and discharge level of the lithium-ion battery reaches a preset value;

[0023] Determine whether the lithium-ion battery is in a high capacity decay state according to the self-discharge rate of the lithium-ion battery. When the self-discharge rate of the lithium-ion battery increases, it is in a high capacity decay state, and generate a discharge depth limit instruction to reduce the number of deep discharges or adjust the charging rate;

[0024] Determine whether the lithium-ion battery is in a high cycle number state according to the charge and discharge depth of the lithium-ion battery. When the charge and discharge depth of the lithium-ion battery reaches a preset charge and discharge depth threshold, generate a user reminder signal and determine whether to close the high-load application according to the user's frequency of using the application;

[0025] Determining whether the lithium-ion battery is in an overcharge state according to the voltage value of the lithium-ion battery, and reducing the voltage of the lithium-ion battery when the voltage value of the lithium-ion battery reaches a preset voltage value;

[0026] According to the current value of the lithium-ion battery, it is determined whether the lithium-ion battery is in an overcharge state, and when the current value of the lithium-ion battery reaches a preset current value, a power cut-off and early warning alarm command signal is generated. A second aspect of the present invention provides a predictive maintenance system based on the energy state of a lithium-ion battery, comprising:

[0027] A data acquisition module, which is used to acquire electrical data of the lithium-ion battery;

[0028] A feature extraction module is used to extract features from the electrical data of the lithium-ion battery to obtain a feature data set of the lithium-ion battery;

[0029] A state prediction module is used to obtain a lithium-ion battery energy state prediction result based on a lithium-ion battery feature data set and a trained lithium-ion battery energy state prediction regression model; wherein the lithium-ion battery feature data set includes voltage feature data, current feature data, charge and discharge feature data, and ambient temperature feature data; each feature is input as an independent variable into the lithium-ion battery energy state prediction regression model, and the lithium-ion battery energy state prediction result is obtained by combining the regression coefficient of the intensity and direction of the influence of each independent variable on the prediction variable;

[0030] The maintenance plan generation module is used to match the lithium-ion battery energy state prediction result according to the preset lithium-ion battery maintenance rules to generate a corresponding lithium-ion maintenance plan.

[0031] A third aspect of the present invention provides a computer-readable storage medium.

[0032] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the above-mentioned predictive maintenance method based on the energy state of a lithium-ion battery.

[0033] A fourth aspect of the present invention provides a computer device.

[0034] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the above-mentioned predictive maintenance method based on the energy state of a lithium-ion battery are implemented.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention combines characteristic data sets of lithium-ion batteries including voltage characteristic data, current characteristic data, charge and discharge characteristic data and ambient temperature characteristic data, performs regression prediction to accurately obtain lithium-ion battery energy state prediction results, and then matches the lithium-ion battery energy state prediction results according to preset lithium-ion battery maintenance rules to generate corresponding lithium-ion maintenance plans, thereby predictively maintaining lithium-ion batteries on the basis of improving the accuracy of lithium-ion battery energy state prediction and avoiding lithium battery life loss.

[0037] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0039] Figure 1 It is a flow chart of a predictive maintenance method based on the energy state of a lithium-ion battery provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0041] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0042] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0043] Embodiment 1

[0044] like Figure 1 As shown, this embodiment provides a predictive maintenance method based on the energy state of a lithium-ion battery, comprising the following steps:

[0045] S101, acquiring electrical data of a lithium-ion battery, and preprocessing the electrical data to obtain first electrical data;

[0046] In this embodiment, the electrical data of the lithium-ion battery includes voltage, current, charge and discharge, ambient temperature data, etc., which are acquired through real-time monitoring by sensors. These sensors are connected to the battery management system to continuously track the working status of the battery. The collected raw data is usually preprocessed for further analysis or control.

[0047] The preprocessing steps include:

[0048] Filtering: Remove noise from the data. In this embodiment, a low-pass filter is used to filter out high-frequency noise, making the current and voltage readings smoother.

[0049] Correct the data to remove sensor bias and ensure accurate readings. Resample the data to ensure data points are evenly spaced in time.

[0050] Normalize the voltage or current data to a certain range to facilitate subsequent processing.

[0051] The preprocessed data serves as the first electrical data, which is used for further data analysis, condition monitoring or to provide input to control algorithms to predict the health of the battery or upcoming maintenance needs.

[0052] At preset moments, electrical data, including voltage, current and other parameters, are automatically collected from the management system of the lithium-ion battery every 10 minutes or according to the battery usage status. These data reflect the immediate working status of the battery. The original collected electrical data contains noise or incomplete values, so data cleaning includes correcting erroneous data and removing abnormal values, and data alignment ensures that data collected from different sensors or at different time points can be neatly combined for unified processing. Voltage data is extracted from the second electrical data after cleaning and alignment. For example, if the data shows that the voltage is recorded as 3.7V, 3.71V, 3.69V, 3.72V, and 3.70V over a period of time, the average value of these voltage values ​​is calculated, that is, (3.7+3.71+3.69+3.72+3.70) / 5=3.704V. The obtained voltage mean is the voltage characteristic data, which provides a representative level of the battery voltage during this period of time.

[0053] S102, extracting features from the first electrical data to obtain a feature data set of a lithium-ion battery;

[0054] The characteristics of the lithium-ion battery include voltage characteristic data, current characteristic data, charge and discharge characteristic data and ambient temperature characteristic data;

[0055] The process of extracting voltage characteristic data and current characteristic data includes:

[0056] Performing data cleaning and alignment processing on the first battery data to obtain second electrical data;

[0057] Calculate the voltage mean value according to the voltage data in the second electrical data to obtain voltage characteristic data;

[0058] Calculate the current mean value according to the current data in the second electrical data to obtain current characteristic data;

[0059] The process of extracting charge and discharge characteristic data includes:

[0060] Performing data cleaning and alignment processing on the first battery data to obtain second electrical data;

[0061] Calculate the charge and discharge rate according to the charge and discharge time in the second electrical data to obtain charge and discharge characteristic data;

[0062] Current data is extracted from the second electrical data. In the same time period, the current is recorded as (1.2A, 1.25A, 1.18A, 1.22A, 1.19A), and the average of these current values ​​is calculated, that is, (1.2+1.25+1.18+1.22+1.19) / 5=1.208A. This average value becomes the current characteristic data, which reflects the normal state of the battery current in this time period. These characteristic data of voltage and current are the basis for battery health monitoring and performance evaluation. They help technicians understand the performance of the battery in actual use and provide a basis for further battery maintenance or fault diagnosis. In this way, the battery life can be effectively predicted and extended while ensuring the safety and reliability of the battery.

[0063] Analyze and determine the start and end time of each charge and discharge from the second electrical data, which can be achieved by detecting the change in the direction of the current and the rise or fall of the voltage. According to the charge and discharge time, calculate the charging rate and discharge rate, which is usually calculated by dividing the average value of the current by the time during the charge and discharge. Obtain the charge and discharge characteristic data: Finally, combined with parameters such as charge and discharge rate and time, detailed charge and discharge characteristic data are formed; these data are very useful for understanding the battery's service life, performance degradation, and charging efficiency. Through the above steps, the battery management system can effectively monitor and analyze the performance of the battery and provide data support for battery maintenance and optimization.

[0064] S103, obtaining a lithium-ion battery energy state prediction result based on a lithium-ion battery feature data set and a trained lithium-ion battery energy state prediction regression model;

[0065] Specifically:

[0066] The voltage characteristic data, the current characteristic data, the charge and discharge characteristic data and the ambient temperature characteristic data are input into the lithium-ion battery energy state prediction regression model, so that the lithium-ion battery energy state prediction regression model outputs a lithium-ion battery energy state prediction result.

[0067] In this embodiment, the lithium-ion battery energy state prediction regression model is:

[0068] Y=β0+β1X1+β2X2+β3X3+β4X4+μ,

[0069] Among them, Y is the prediction result of lithium-ion battery energy state, X1 is voltage characteristic data, X2 is current characteristic data, X3 is charge and discharge characteristic data, X4 is ambient temperature characteristic data, β j(j=1, 2, ..., k) are called regression coefficients. Each coefficient represents the strength and direction of the influence of the corresponding independent variable on the predicted variable Y. β0 is the intercept, which represents the predicted value of Y when all independent variables are zero. μ is the error term, which represents the random variation that the model cannot explain, and can be understood as the deviation between the observed value and the model predicted value.

[0070] The training process of the lithium-ion battery energy state prediction regression model includes:

[0071] The historical feature data set of the lithium-ion battery is divided into a training set and a test set, the lithium-ion battery energy state prediction regression model is trained based on the training set data, and the lithium-ion battery energy state prediction regression model is tested based on the test set, until the prediction accuracy of the lithium-ion battery energy state prediction regression model meets a preset accuracy threshold or reaches a preset number of times, and then the testing of the lithium-ion battery energy state prediction regression model is stopped.

[0072] Voltage data: average voltage for each charge and discharge cycle;

[0073] Current data: average current during charging and discharging;

[0074] Charge and discharge data: duration and completion of each charge and discharge;

[0075] Ambient temperature data: The ambient temperature recorded during the charging and discharging process. The 1000 sets of data are randomly divided into two parts: 800 sets of data are used to train the model, and 200 sets of data are used to test the model. A multivariate linear regression model is selected to predict the energy of the battery.

[0076] Use the training set data to train the model and adjust the model parameters until the training error is minimized.

[0077] For example, during the training process, it was found that the average error of the model was 2% of the energy state deviation. On the test set, the average error of the model was 2.5% of the energy state deviation, which shows that the model still has good accuracy on unseen data. If the preset accuracy threshold is that the model prediction error does not exceed 3%, the model has met this condition and does not need to be tested further. The goal of this process is to develop a model that can accurately predict the remaining energy of lithium-ion batteries, which is crucial for optimizing battery management systems, extending battery life, and improving the safety and efficiency of battery use.

[0078] S104, based on the preset lithium-ion battery processing rules, matching the lithium-ion battery energy state prediction result to generate corresponding lithium-ion battery processing suggestions, specifically including:

[0079] When the predicted temperature value of the lithium-ion battery is greater than the set temperature threshold, a cooling system start instruction is generated to cool the lithium-ion battery; cooling can prevent the battery temperature from being too high, protect the battery safety and extend its service life;

[0080] When the charge and discharge rate of the lithium-ion battery is less than the set rate threshold, a segmented charge and discharge command is generated to start the segmented charge and discharge mode until the charge and discharge level of the lithium-ion battery reaches the preset value; segmented charge and discharge can optimize the charging efficiency and life of the battery and avoid battery stress and thermal decay caused by continuous charge and discharge;

[0081] Determine whether the lithium-ion battery is in a high capacity decay state based on the self-discharge rate of the lithium-ion battery. When the self-discharge rate of the lithium-ion battery increases, it is in a high capacity decay state. Generate a discharge depth limit instruction to reduce the number of deep discharges or adjust the charging rate. Both deep discharge and excessively fast charging rate may cause excessive battery consumption and rapid capacity decline. By adjusting these parameters, capacity decay can be slowed down.

[0082] Determine whether the lithium-ion battery is in a high cycle count state based on the charge and discharge depth of the lithium-ion battery. When the charge and discharge depth of the lithium-ion battery reaches the preset charge and discharge depth threshold, remind the user and determine whether to close high-load applications based on the frequency of the user's use of applications; a high cycle count indicates that the battery has been used frequently, and high-load applications may further accelerate battery aging. By managing the use of applications, the battery life can be effectively extended.

[0083] Whether the lithium-ion battery is in an overcharged state is determined according to the voltage value of the lithium-ion battery. When the voltage value of the lithium-ion battery reaches a preset voltage value, the voltage of the lithium-ion battery is reduced based on an intelligent control system. Overcharging may cause battery safety risks. By reducing the voltage through intelligent control, battery overcharging and potential safety problems can be avoided.

[0084] Determine whether the lithium-ion battery is in an overcharged state based on the current value of the lithium-ion battery. When the current value of the lithium-ion battery reaches the preset current value, immediately cut off the power supply and issue a warning alarm. Under-discharge or short circuit is extremely harmful to the battery. Quickly cutting off the power supply and issuing an alarm can prevent the damage from expanding and avoid safety accidents. Through the intelligent system, specific response measures are provided according to the battery status, aiming to optimize battery performance, ensure safety, and extend the battery life. This approach is crucial to improving battery efficiency and dependence, especially in high-tech applications that require delicate battery management, such as electric vehicles and large-scale energy storage systems.

[0085] Embodiment 2

[0086] This embodiment provides a predictive maintenance system based on the energy state of a lithium-ion battery, including:

[0087] A data acquisition module, which is used to acquire electrical data of the lithium-ion battery;

[0088] A feature extraction module is used to extract features from the electrical data of the lithium-ion battery to obtain a feature data set of the lithium-ion battery;

[0089] A state prediction module is used to obtain a lithium-ion battery energy state prediction result based on a lithium-ion battery feature data set and a trained lithium-ion battery energy state prediction regression model; wherein the lithium-ion battery feature data set includes voltage feature data, current feature data, charge and discharge feature data, and ambient temperature feature data; each feature is input as an independent variable into the lithium-ion battery energy state prediction regression model, and the lithium-ion battery energy state prediction result is obtained by combining the regression coefficient of the intensity and direction of the influence of each independent variable on the prediction variable;

[0090] The maintenance plan generation module is used to match the lithium-ion battery energy state prediction result according to the preset lithium-ion battery maintenance rules to generate a corresponding lithium-ion maintenance plan.

[0091] Embodiment 3

[0092] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the predictive maintenance method based on the energy state of a lithium-ion battery as described above are implemented.

[0093] Embodiment 4

[0094] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the predictive maintenance method based on the energy status of a lithium-ion battery as described above are implemented.

[0095] Embodiment 5

[0096] This embodiment provides a program product, which is a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the steps in the predictive maintenance method based on the energy status of a lithium-ion battery as described above are implemented.

[0097] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0098] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0101] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0102] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A predictive maintenance method based on the energy state of a lithium-ion battery, characterized in that: The steps include: Get electrical data of lithium-ion batteries; Extract features from the electrical data of the lithium-ion battery to obtain a feature data set of the lithium-ion battery; Based on the characteristic data set of lithium-ion batteries and the trained lithium-ion battery energy state prediction regression model, the lithium-ion battery energy state prediction result is obtained; wherein the characteristic data set of lithium-ion batteries includes voltage characteristic data, current characteristic data, charge and discharge characteristic data and ambient temperature characteristic data; each characteristic is input into the lithium-ion battery energy state prediction regression model as an independent variable, and the lithium-ion battery energy state prediction result is obtained by combining the regression coefficient of the influence strength and direction of each independent variable on the prediction variable; According to the preset lithium-ion battery maintenance rules, the lithium-ion battery energy state prediction results are matched to generate the corresponding lithium-ion maintenance plan.

2. A predictive maintenance method based on lithium-ion battery energy status as claimed in claim 1, characterized in that: The extraction process of voltage characteristic data, current characteristic data and charge and discharge characteristic data includes: Calculate the voltage mean value according to the voltage data in the electrical data of the lithium-ion battery to obtain voltage characteristic data; Calculate the current mean value according to the current data in the electrical data of the lithium-ion battery to obtain the current characteristic data; The charge and discharge rate is calculated based on the charge and discharge time in the electrical data of the lithium-ion battery to obtain the charge and discharge characteristic data.

3. A predictive maintenance method based on lithium-ion battery energy status as claimed in claim 1, characterized in that: The lithium-ion battery energy state prediction regression model is: Y=β0+β1X1+β2X2+β3X3+β4X4+μ, Among them, Y is the prediction result of lithium-ion battery energy state, X1 is voltage characteristic data, X2 is current characteristic data, X3 is charge and discharge characteristic data, X4 is ambient temperature characteristic data, β j (j=1, 2, ..., k) is called the regression coefficient. Each coefficient represents the strength and direction of the influence of the corresponding independent variable on the predicted variable Y. β0 is the intercept, which represents the predicted value of Y when all independent variables are zero. μ is the error term.

4. A predictive maintenance method based on lithium-ion battery energy status as claimed in claim 1, characterized in that: When training the lithium-ion battery energy state prediction regression model, the historical feature data set of the lithium-ion battery is divided into a training set and a test set, the lithium-ion battery energy state prediction regression model is trained based on the training set data, and the lithium-ion battery energy state prediction regression model is tested based on the test set, until the prediction accuracy of the lithium-ion battery energy state prediction regression model meets a preset accuracy threshold or reaches a preset number of times, then the testing of the lithium-ion battery energy state prediction regression model is stopped.

5. A predictive maintenance method based on lithium-ion battery energy status as claimed in claim 1, characterized in that: Obtain electrical data of lithium-ion batteries and preprocess the electrical data, including noise removal, data resampling, and data normalization.

6. A predictive maintenance method based on lithium-ion battery energy status as claimed in claim 1, characterized in that: According to the preset lithium-ion battery maintenance rules, the lithium-ion battery energy state prediction results are matched to generate corresponding lithium-ion battery processing suggestions, including: When the predicted temperature value of the lithium-ion battery is greater than the set temperature threshold, a cooling system start instruction is generated to cool the lithium-ion battery; When the charge and discharge rate of the lithium-ion battery is less than the set rate threshold, a segmented charge and discharge command is generated to start the segmented charge and discharge mode until the charge and discharge level of the lithium-ion battery reaches a preset value; Determine whether the lithium-ion battery is in a high capacity decay state according to the self-discharge rate of the lithium-ion battery. When the self-discharge rate of the lithium-ion battery increases, it is in a high capacity decay state, and generate a discharge depth limit instruction to reduce the number of deep discharges or adjust the charging rate; Determine whether the lithium-ion battery is in a high cycle number state according to the charge and discharge depth of the lithium-ion battery. When the charge and discharge depth of the lithium-ion battery reaches a preset charge and discharge depth threshold, generate a user reminder signal and determine whether to close the high-load application according to the user's frequency of using the application; Determining whether the lithium-ion battery is in an overcharge state according to the voltage value of the lithium-ion battery, and reducing the voltage of the lithium-ion battery when the voltage value of the lithium-ion battery reaches a preset voltage value; Whether the lithium-ion battery is in an overcharge state is determined according to the current value of the lithium-ion battery. When the current value of the lithium-ion battery reaches a preset current value, a power cut-off and early warning alarm command signal is generated.

7. A predictive maintenance system based on lithium-ion battery energy status, characterized in that: include: A data acquisition module, which is used to acquire electrical data of the lithium-ion battery; A feature extraction module is used to extract features from the electrical data of the lithium-ion battery to obtain a feature data set of the lithium-ion battery; A state prediction module is used to obtain a lithium-ion battery energy state prediction result based on a lithium-ion battery feature data set and a trained lithium-ion battery energy state prediction regression model; wherein the lithium-ion battery feature data set includes voltage feature data, current feature data, charge and discharge feature data, and ambient temperature feature data; each feature is input as an independent variable into the lithium-ion battery energy state prediction regression model, and the lithium-ion battery energy state prediction result is obtained by combining the regression coefficient of the intensity and direction of the influence of each independent variable on the prediction variable; The maintenance plan generation module is used to match the lithium-ion battery energy state prediction result according to the preset lithium-ion battery maintenance rules to generate a corresponding lithium-ion maintenance plan.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in a predictive maintenance method based on the energy status of a lithium-ion battery as described in any one of claims 1 to 7 are implemented.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the predictive maintenance method based on the energy status of a lithium-ion battery as described in any one of claims 1 to 7 are implemented.

10. A program product, the program product being a computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps in the predictive maintenance method based on the energy status of a lithium-ion battery as described in any one of claims 1 to 7 are implemented.

Images