Battery health state assessment method and device, equipment and storage medium
By extracting battery feature vectors and building a health status evaluation model, the problem of health status evaluation of sodium ion batteries is solved, accurate evaluation of battery performance and life extension are achieved, and safety and use efficiency are improved.
Patent Information
- Application Number
- CN202410901229.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-05
- Publication Date
- 2024-11-01
AI Technical Summary
It is difficult to accurately evaluate the health status of sodium ion batteries in actual applications, resulting in degradation of battery performance and aging accelerated, posing safety risks, and increasing maintenance costs.
By obtaining the operating data and historical health evaluation results of the target battery, the battery feature vector is extracted using a time series convolutional neural network, and a health status evaluation model is constructed based on traceless Kalman filtering to generate accurate battery health status evaluation results.
Improves battery efficiency, extends battery life, enhances battery safety, and reduces maintenance costs.
Smart Images

Figure CN118884232A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of battery evaluation technology, and in particular to a battery health status evaluation method, device, equipment and storage medium. Background Art
[0002] Sodium-ion batteries have become a strong competitor for the new generation of energy storage technology due to their abundant resources and low costs, and are becoming a viable alternative to lithium-ion batteries. However, the key issue facing sodium-ion batteries in practical applications is how to accurately and effectively evaluate their state of health (SOH). Otherwise, the battery performance will decline, and the battery will be overcharged or discharged, thereby accelerating the battery aging process and shortening the battery life. This may lead to safety risks such as battery overheating, fire or explosion, greatly reducing the safety of battery use. At the same time, due to the inability to accurately evaluate the battery status, problems such as premature battery replacement may occur, thereby increasing the battery maintenance cost. Summary of the invention
[0003] The main purpose of this application is to provide a battery health status assessment method, device, equipment and storage medium, aiming to efficiently and accurately assess the health status of the battery, thereby improving the battery efficiency and extending the service life, thereby effectively improving the safety of battery use and reducing battery maintenance costs.
[0004] To achieve the above objectives, the present application proposes a battery health status assessment method, the method comprising:
[0005] Acquire first operation data and historical health assessment results of a target battery;
[0006] Inputting the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model;
[0007] Inputting the battery feature vector into a battery health status assessment model to obtain current health assessment data output by the battery health status assessment model;
[0008] A battery health status assessment result is generated based on the current health assessment data and the historical health assessment results.
[0009] In one embodiment, the training process of the battery feature extraction model includes:
[0010] Acquire several groups of historical operation data, and pre-process each of the historical operation data;
[0011] The preprocessed historical operation data is input into an initial battery feature extraction model for iterative training to obtain the battery feature extraction model, wherein the initial battery feature extraction model is constructed based on a time series convolutional neural network.
[0012] In one embodiment, after inputting the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model, the method further includes:
[0013] Performing validity analysis on the battery characteristic vector to obtain a validity analysis result;
[0014] Determining a feature type corresponding to the battery feature vector;
[0015] A key feature list is generated based on the effectiveness analysis results and the feature types.
[0016] In one embodiment, after generating a key feature list based on the effectiveness analysis result and the feature type, the method further includes:
[0017] Determining a ranking of features of the key features list;
[0018] Based on the feature sorting and preset weights, the target features corresponding to the feature types are applied to the battery feature extraction model.
[0019] In one embodiment, the training process of the battery health status assessment model includes:
[0020] Acquire several groups of historical battery feature vectors, and preprocess each of the historical battery feature vectors;
[0021] The preprocessed historical battery feature vector is input into an initial battery health state assessment model for iterative training to obtain the battery health state assessment model, wherein the initial battery health state assessment model is constructed based on an unscented Kalman filter.
[0022] In one embodiment, after generating the battery health status assessment result based on the current health assessment data and the historical health assessment result, the method further includes:
[0023] Analyze the battery health status assessment result to generate a battery optimization strategy for the target battery;
[0024] Based on the battery optimization strategy, the target battery is optimized, and second operating data of the optimized target battery is obtained;
[0025] The battery optimization strategy is adjusted based on the second operating data.
[0026] In one embodiment, after generating the battery health status assessment result based on the current health assessment data and the historical health assessment result, the method further includes:
[0027] Obtaining a display device interface of a target battery;
[0028] Based on the display device interface, the battery health status assessment result is pushed to a target user for the target user to view.
[0029] In addition, to achieve the above purpose, the present application also proposes a battery health status assessment device, the battery health status assessment device comprising:
[0030] A data acquisition module, used to acquire first operating data and historical health assessment results of a target battery;
[0031] A first output module, used for inputting the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model;
[0032] A second output module, used to input the battery feature vector into a battery health status assessment model to obtain current health assessment data output by the battery health status assessment model;
[0033] An assessment generation module is used to generate a battery health status assessment result based on the current health assessment data and the historical health assessment results.
[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a battery health status assessment device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the battery health status assessment method as described above.
[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the battery health status assessment method described above are implemented.
[0036] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the battery health status assessment method described above are implemented.
[0037] The present application provides a battery health status assessment method, apparatus, device and storage medium. The battery health status assessment method obtains first operating data and historical health assessment results of a target battery, and then inputs the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model, and then inputs the battery feature vector into a battery health status assessment model to obtain current health assessment data output by the battery health status assessment model, and then generates a battery health status assessment result based on the current health assessment data and the historical health assessment results, thereby efficiently and accurately assessing the health status of the battery, thereby improving the battery's utilization efficiency and extending its service life, thereby effectively improving the safety of battery use and reducing battery maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0040] Figure 1 A flowchart of the first embodiment of the battery health status assessment method of the present application is provided;
[0041] Figure 2 A flowchart of the second embodiment of the battery health status assessment method of the present application is provided;
[0042] Figure 3 A flowchart of the third embodiment of the battery health status assessment method of the present application is provided;
[0043] Figure 4 A brief flowchart of the battery health status assessment method provided for this application;
[0044] Figure 5 This is a schematic diagram of the module structure of the battery health status assessment device according to an embodiment of the present application;
[0045] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the battery health status assessment method in the embodiment of the present application.
[0046] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0049] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a big data service platform, a battery health status evaluation system, etc. The following takes the battery health status evaluation system as an example to illustrate this embodiment and the following embodiments.
[0050] Based on this, the present application embodiment provides a battery health status assessment method, referring to Figure 1 , Figure 1 A flowchart of the first embodiment of the battery health status assessment method of the present application is provided.
[0051] In this embodiment, the battery health status assessment method includes steps S11 to S14:
[0052] Step S11, obtaining first operating data and historical health assessment results of the target battery;
[0053] It should be noted that the target battery includes sodium ion batteries and other batteries that require health assessment, which are not limited here. The first operating data refers to the data generated by the battery during actual operation. The data is the battery operating parameters collected in real time to reflect the current working status of the battery, including the battery voltage (V), current (I), temperature (T), charge and discharge state (SOC, State of Charge), charge and discharge rate (C-rate), battery energy (Wh), battery power (W), battery operating time, battery fault code, battery parasitic power consumption, battery charge and discharge cycle times, etc., which are not limited here.
[0054] It should be further explained that the historical health assessment results refer to the records of past battery performance and health status assessments to help analyze and predict the future performance and aging trends of the battery. The historical health assessment results include the battery's capacity decay history, the battery's maximum depth of discharge (DOD) history, the battery's charge and discharge cycle life, the battery's failure history, the battery's maintenance records, the battery's state of health (SOH) change history, the battery's performance test results, the battery's performance data under different temperatures and load conditions, etc., which are not limited here and can be set according to actual conditions to reflect the historical operating status of the target battery through the historical health assessment results.
[0055] Specifically, the first operating data of the target battery can be acquired in real time through the detection tool, and the historical health assessment results can be acquired through historical log records or a preset database, etc., without limitation here, and the acquisition method can be set according to actual conditions.
[0056] Step S12, inputting the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model;
[0057] It should be noted that the battery feature extraction model is used to extract feature data from the first operating data, wherein the battery feature extraction model can be trained by means of a convolutional neural network (CNN), a recurrent neural network (RNN), a long short-term memory network (LSTM), a variational autoencoder (VAE), an autoencoder (AE), etc. Preferably, in order to effectively capture the long-term dependencies in the battery data and automatically extract key features, the battery feature extraction model can be trained by means of a time series convolutional neural network (TCN). It should be further noted that the battery feature vector refers to the feature vector corresponding to the first operating data.
[0058] Step S13, inputting the battery feature vector into a battery health status assessment model to obtain current health assessment data output by the battery health status assessment model;
[0059] It should be noted that the battery health status assessment model is used to analyze the feature vector and output the current health assessment data. Preferably, the battery health status assessment model can be constructed based on the unscented Kalman filter (UKF), so that it is more accurate than the traditional Kalman filter method when processing the nonlinear dynamics of the battery and can provide a more reliable state estimation. In addition, the current health assessment data refers to data used to evaluate the current health status of the battery.
[0060] Step S14: Generate a battery health status assessment result based on the current health assessment data and the historical health assessment results.
[0061] It should be noted that the battery health status assessment result refers to the health assessment status of the target battery under the current operating state to characterize the health of the battery, including the assessment conclusion and corresponding assessment data, battery health prediction analysis, etc., which is not limited here.
[0062] Specifically, the current health assessment data and the historical health assessment results are integrated and analyzed to generate a battery health status assessment result, for example, the current health assessment data is compared and analyzed with the historical health assessment results, the historical trend and the current status are integrated, and the results after the integrated analysis are interpreted, wherein the interpretation can be performed using a language analysis model, such as a support vector machine model (SVM), a random forest model (RF), and a gradient boosting machine model (GBM), etc., so as to generate a battery health status assessment result. In order to obtain a more comprehensive battery health status assessment, such as the battery's state of health (SOH), remaining service life prediction, possible health problems, etc.
[0063] In addition, by combining the battery feature extraction model with the battery feature extraction model, a powerful monitoring and prediction framework is formed, which enhances the model's adaptability to changes in battery operating conditions and improves the estimation accuracy and robustness of the health state.
[0064] This embodiment obtains the first operating data and historical health assessment results of the target battery, and then inputs the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model, and then inputs the battery feature vector into a battery health status assessment model to obtain current health assessment data output by the battery health status assessment model, and then generates a battery health status assessment result based on the current health assessment data and the historical health assessment results, so as to efficiently and accurately assess the health status of the battery, thereby improving the battery's utilization efficiency and extending its service life, thereby effectively improving the safety of battery use and reducing battery maintenance costs.
[0065] In a feasible implementation manner, the training process of the battery feature extraction model includes:
[0066] Step S21, obtaining several groups of historical operation data, and preprocessing each of the historical operation data;
[0067] It should be noted that the historical operating data refers to the operating data generated by multiple batteries, including the battery voltage (V), current (I), temperature (T), charge and discharge state (SOC, State of Charge), charge and discharge rate (C-rate), battery energy (Wh), battery power (W), battery operating time, battery fault code, battery parasitic power consumption, battery charge and discharge cycle times and other data, without limitation here.
[0068] Specifically, several groups of historical operation data are obtained, and each of the historical operation data is preprocessed, including data cleaning, normalization, and removal of outliers, etc., to ensure data quality and consistency.
[0069] Step S22, inputting the preprocessed historical operation data into the initial battery feature extraction model for iterative training to obtain the battery feature extraction model, wherein the initial battery feature extraction model is constructed based on a time series convolutional neural network.
[0070] It should be noted that, because traditional technologies usually ignore the time series characteristics of battery data, they are not sufficient to provide accurate predictions in dynamically changing usage environments. For example, it is difficult for traditional methods to capture battery performance fluctuations caused by factors such as temperature changes and charge and discharge rate changes in real time, resulting in a lack of effective processing of the long-term dependency of battery parameters over time in the battery health status assessment, resulting in the assessment results being unable to fully reflect the actual battery usage. Therefore, in order to solve this problem, the dilated convolution structure in the time series convolutional neural network is used to optimize information transmission, effectively capture long-term dependencies in battery data, and automatically extract key features.
[0071] Specifically, the preprocessed historical operation data and the sample labels corresponding to the historical operation data are input into the initial battery feature extraction model to obtain the predicted value output by the initial battery feature extraction model, and then based on the predicted value and the sample label, the model loss value is calculated using the loss function. In this embodiment, the loss function can be set according to actual needs and is not specifically limited here. After the model loss value is calculated, the training process ends, and the error back propagation algorithm is used to update the model parameters in the initial battery feature extraction model, and then the next training is carried out. During the training process, it is determined whether the updated initial battery feature extraction model meets the preset training end conditions. If it does, the updated initial battery feature extraction model is used as the battery feature extraction model. If it does not, the model continues to be trained, wherein the preset training end conditions include loss convergence and reaching the maximum number of iterations. At the same time, the model's hyperparameters, such as the learning rate, the number of layers, and the number of hidden units, can be adjusted and optimized to further improve the accuracy and generalization ability of the model.
[0072] Furthermore, the trained model is verified on an independent test set to evaluate the performance of the model on unknown data and ensure the accuracy and reliability of the model.
[0073] Furthermore, in order to maintain the high timeliness of battery health status assessment, the historical operating data for model training needs to be continuously updated, wherein the updated historical operating data can be added to the original model for iterative training, or a new round of model training can be directly performed based on the updated historical operating data, without any restriction here.
[0074] In addition, the initial battery feature extraction model is constructed based on a time series convolutional neural network (TCN), wherein TCN is capable of processing long time series data, capturing the time dependency of battery status, and effectively dealing with time intervals and delays in the data, thereby capturing long-term dependencies in the data through its dilated convolution structure, that is, accurately characterizing the time dependency and dynamic changes in battery data, and then accurately extracting key features related to the battery health status, thereby accurately mapping the actual working status and health degradation trajectory of the battery.
[0075] This embodiment obtains several groups of historical operation data, preprocesses each of the historical operation data, and then inputs the preprocessed historical operation data into an initial battery feature extraction model for iterative training to obtain the battery feature extraction model, wherein the initial battery feature extraction model is constructed based on a time series convolutional neural network, so as to accurately extract key features related to the battery health status and accurately map the actual working status and health degradation trajectory of the battery.
[0076] Based on this, the present application embodiment provides a battery health status assessment method, referring to Figure 2 , Figure 2 A flowchart of the second embodiment of the battery health status assessment method of the present application is provided.
[0077] In a feasible implementation manner, after inputting the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model, the method further includes:
[0078] Step S31, performing validity analysis on the battery characteristic vector to obtain a validity analysis result;
[0079] It should be noted that the validity analysis results refer to the results of evaluating the importance of battery feature vectors for predicting the battery state of health (State of Health, SOH) to determine which features have the greatest impact on battery health, so that the battery performance and life can be predicted more accurately. The validity analysis results include: feature importance (evaluating the contribution of each feature to the prediction of battery health status), correlation analysis (analyzing the correlation between features to avoid multicollinearity problems), statistical tests, prediction ability evaluation (evaluating the ability of features to predict battery performance), etc., which are not limited here and can be set according to actual conditions.
[0080] Specifically, the battery feature vector is subjected to validity analysis. For example, the feature importance is determined through various statistical methods or built-in functions of the machine learning model. Statistical tests (such as t-test, chi-square test, etc.) are used to determine whether there are significant differences in the features. The prediction ability is evaluated by calculating indicators such as the prediction accuracy, recall rate, and area under the ROC curve (AUC) of the features, thereby integrating and analyzing the analysis results to obtain validity analysis results. In addition, the validity analysis results need to be not only expressed in numerical values, but also need to be interpretable, that is, they can explain how the features affect the health status of the battery, thereby effectively improving professionalism and credibility.
[0081] Step S32, determining the feature type corresponding to the battery feature vector;
[0082] It should be noted that the feature type refers to the feature type of the feature corresponding to the battery feature vector, such as current, voltage, and temperature, etc., which is not limited here and can be set according to actual conditions.
[0083] Specifically, the feature type corresponding to the battery feature vector may be determined by query matching or the like, which is not limited here.
[0084] Step S33: Generate a key feature list based on the effectiveness analysis result and the feature type.
[0085] It should be noted that the key feature list refers to the most critical and effective feature list for battery health status assessment, including feature names, feature valid values, and validity descriptions, etc., and is not limited here.
[0086] Specifically, the validity analysis results and the feature types are associated and combined to generate a key feature list. In addition, the key feature list can be pushed to the security management personnel for secondary confirmation by the security management personnel, and the key features therein can be tested and applied.
[0087] This embodiment performs validity analysis on the battery feature vector to obtain a validity analysis result, and then determines the feature type corresponding to the battery feature vector, and then generates a key feature list based on the validity analysis result and the feature type, and then determines which features are most critical and effective for battery health status assessment, so as to integrate high-effectiveness features with the model and improve the accuracy and precision of battery health status assessment.
[0088] In a feasible implementation manner, after generating a key feature list based on the effectiveness analysis result and the feature type, the method further includes:
[0089] Step S41, determining the feature ranking of the key feature list;
[0090] It should be noted that the feature ranking refers to the ranking of the effective values of each target feature in the key feature list to characterize the importance of each feature for the battery health status assessment.
[0091] Specifically, the valid values of each target feature in the key feature list are sorted in reverse order, so as to determine the feature sorting of the key feature list.
[0092] Step S42: Based on the feature sorting and preset weights, the target features corresponding to the feature types are applied to a battery feature extraction model.
[0093] It should be noted that the preset weight refers to a pre-set weight value related to the attention of the target feature in the model. The preset weight can be adjusted according to the importance of the feature, and can also be set according to prior knowledge or through cross-validation, etc., and there is no limitation here.
[0094] Specifically, based on the feature sorting and preset weights, the target features corresponding to the feature types are applied to the battery feature extraction model. For example, according to the feature sorting, a weight is assigned to each feature, and then the top-ranked features are selected as target features, and the selected target features and corresponding weights are used to construct a battery feature extraction model, which aims to directly extract features useful for battery health status assessment from the raw data, thereby helping to simplify the data preprocessing process, that is, there is no need for complex transformation or standardization of unimportant features, and reduces the demand for resource computing, speeding up model training and evaluation, while ensuring the accuracy of model evaluation.
[0095] This embodiment determines the feature ranking of the key feature list, and then based on the feature ranking and preset weights, applies the target features corresponding to the feature types to the battery feature extraction model, thereby building a more efficient model and reducing the complexity of the model. At the same time, it clarifies the validity of each key feature, making it easier to understand and trust the evaluation results of the model.
[0096] In a feasible implementation manner, the training process of the battery health status assessment model includes:
[0097] Step S51, obtaining several groups of historical battery feature vectors, and preprocessing each of the historical battery feature vectors;
[0098] It should be noted that the historical battery feature vector refers to the feature vector obtained after feature extraction of operating data generated by multiple batteries, including the battery voltage (V), current (I), temperature (T), charge and discharge state (SOC, State of Charge), charge and discharge rate (C-rate), battery energy (Wh), battery power (W), battery operating time, battery fault code, battery parasitic power consumption, battery charge and discharge cycle times and other data feature vectors, without limitation here.
[0099] Specifically, several groups of historical battery feature vectors are obtained, and each of the historical battery feature vectors is preprocessed, including data cleaning, normalization processing, and removal of outliers, etc., to ensure data quality and consistency.
[0100] Step S52, inputting the preprocessed historical battery feature vector into an initial battery health state assessment model for iterative training to obtain the battery health state assessment model, wherein the initial battery health state assessment model is constructed based on an unscented Kalman filter.
[0101] It should be noted that since traditional methods often rely on simplified empirical models, such as electrochemical impedance spectroscopy (EIS) and open circuit voltage (OCV), these models are inefficient when processing non-standardized or nonlinear data with complex changes, resulting in the inability to accurately map the actual working state and health degradation trajectory of the battery. Therefore, in order to solve this problem, an initial battery health state assessment model is constructed by generating Sigma points in the unscented Kalman filter (UKF) to approximate the true state distribution, so as to achieve accurate dynamic prediction of battery performance degradation, thereby improving the dimension and accuracy of data processing, enhancing the model's ability to identify and adapt to the nonlinear behavior of the battery, and significantly improving the accuracy, reliability and practicality of battery health state assessment.
[0102] Specifically, the preprocessed historical battery feature vector and the sample label corresponding to the historical battery feature vector are input into the initial battery health state assessment model to obtain the predicted value output by the initial battery health state assessment model, and then based on the predicted value and the sample label, the model loss value is calculated using the loss function. In this embodiment, the loss function can be set according to actual needs and is not specifically limited here. After the model loss value is calculated, the training process ends, and the error back propagation algorithm is used to update the model parameters in the initial battery health state assessment model, and then the next training is performed. During the training process, it is determined whether the updated initial battery health state assessment model meets the preset training end condition. If it meets the condition, the updated initial battery health state assessment model is used as the battery health state assessment model. If it does not meet the condition, the model training continues, wherein the preset training end condition includes loss convergence and reaching the maximum number of iterations threshold, etc. At the same time, the accuracy and generalization ability of the model can be further improved by adjusting the network structure and optimizing the hyperparameters of the model, such as the learning rate and the number of iterations.
[0103] Furthermore, the trained model is verified on an independent test set to evaluate the performance of the model on unknown data and ensure the accuracy and reliability of the model.
[0104] Furthermore, in order to maintain the high timeliness of battery health status assessment, the historical battery feature vectors used for model training need to be continuously updated, wherein the updated historical battery feature vectors can be added to the original model for iterative training, or a new round of model training can be performed directly based on the updated historical battery feature vectors, without any restriction here.
[0105] This embodiment obtains several groups of historical operation data, preprocesses each of the historical operation data, and then inputs the preprocessed historical operation data into an initial battery health status assessment model for iterative training to obtain the battery health status assessment model, wherein the initial battery health status assessment model is constructed based on unscented Kalman filtering, thereby improving the dimension and accuracy of data processing, thereby significantly improving the accuracy, reliability and practicality of battery health status assessment.
[0106] Based on this, the present application embodiment provides a battery health status assessment method, referring to Figure 3 , Figure 3 A flowchart of the third embodiment of the battery health status assessment method of the present application is provided.
[0107] In a feasible implementation manner, after generating the battery health status assessment result based on the current health assessment data and the historical health assessment result, the method further includes:
[0108] Step S61, analyzing the battery health status assessment result to generate a battery optimization strategy for the target battery;
[0109] It should be noted that the battery optimization strategy refers to a series of strategies for optimizing battery performance and extending its service life, which usually involve aspects such as battery charge and discharge management, temperature control, battery health monitoring and maintenance. For example, by intelligently managing the battery charge and discharge process, overcharging and discharging of the battery can be avoided, thereby extending the battery life. Among them, the independent strategies in the battery optimization strategy can be used alone or in combination to adapt to different battery application scenarios and performance requirements. There is no restriction here and it can be set according to actual conditions.
[0110] Specifically, the battery health status assessment results are analyzed to generate a battery optimization strategy for the target battery. For example, if the battery health status assessment results show that the optimal operating temperature range of the target battery is between 24 and 30 degrees Celsius, a temperature sensor and a heat dissipation system can be used to ensure that the target battery is within the optimal operating temperature range to avoid overheating or overcooling of the ambient temperature, which would affect battery performance.
[0111] Step S62, optimizing the target battery based on the battery optimization strategy, and acquiring second operating data of the optimized target battery;
[0112] It should be noted that the second operating data refers to the data generated when the battery is actually running after optimization. The data is the battery operating parameters collected in real time to reflect the current working status of the battery, including the battery voltage (V), current (I), temperature (T), charge and discharge state (SOC, State of Charge), charge and discharge rate (C-rate), battery energy (Wh), battery power (W), battery operating time, battery fault code, battery parasitic power consumption, battery charge and discharge cycle times and other data, which are not limited here.
[0113] Specifically, according to the battery optimization strategy, the target battery is optimized, wherein the battery optimization strategy can be pushed to the safety management personnel for strategy evaluation to ensure the accuracy, professionalism and safety of the battery optimization strategy, and then optimized according to the battery optimization strategy positively evaluated by the safety management personnel, so as to obtain the second operating data of the optimized target battery, wherein the second operating data of the target battery can be obtained through a real-time detection tool, and there is no restriction on the acquisition method, which can be set according to actual conditions.
[0114] Step S63: adjusting the battery optimization strategy based on the second operating data.
[0115] Specifically, the second operation data is analyzed to determine the implementation effect of the battery optimization strategy, and then the battery optimization strategy is adjusted according to the implementation effect. For example, after adopting the battery optimization strategy of "maintaining the operating temperature range of the target battery at 24-30 degrees Celsius", if the second operation data has an improvement effect compared with the operation data before the battery optimization strategy is adopted, such as the battery power decline rate is slowed down by 5%, then the battery optimization strategy is determined to be effective. If the second operation data has an opposite effect compared with the operation data before the battery optimization strategy is adopted, such as the battery power decline rate increases by 5%, then the battery optimization strategy is determined to be invalid, and then the implementation effect is associated with the battery optimization strategy to generate strategy adjustment information, so that the strategy adjustment information is pushed to the security manager for the security manager to adjust, or the adjustment strategy is determined by large model and big data analysis, which is not limited here, so that the battery optimization strategy can be continuously adjusted and adapted according to the new data and environment, so as to maintain the timeliness and accuracy of battery management, and then effectively improve the battery efficiency and extend the service life, improve resource utilization, and thus improve user satisfaction.
[0116] This embodiment analyzes the battery health status assessment result to generate a battery optimization strategy for the target battery, and then optimizes the target battery based on the battery optimization strategy, and obtains second operating data of the optimized target battery, and then adjusts the battery optimization strategy based on the second operating data, and then takes measures to optimize the battery health status, thereby extending battery life, improving energy conversion and utilization efficiency, and reducing energy waste. At the same time, adjusting the optimization strategy based on real-time data can ensure that the battery system always operates in the best performance state, thereby improving the performance of the overall system.
[0117] In a feasible implementation manner, after generating the battery health status assessment result based on the current health assessment data and the historical health assessment result, the method further includes:
[0118] Step S71, obtaining a display device interface of a target battery;
[0119] It should be noted that the display device interface refers to a physical connector or communication protocol used to connect the battery and the display device, thereby ensuring that information such as the real-time status of the battery can be smoothly transmitted to the display device, and controlling the display device to display information such as relevant functions of the battery.
[0120] Specifically, the interface name or the interface address may be used to query to obtain the display device interface of the target battery, which is not limited here and may be set according to actual conditions.
[0121] Step S72: Based on the display device interface, push the battery health status assessment result to the target user for the target user to view.
[0122] Specifically, the display device interface is connected to push the battery health status assessment result to the target user for the target user to view, wherein the target user can select a preset push template for push to achieve personalized push, and the preset push template refers to a pre-set push template, including style, font size, push status type (such as battery level, current health status, etc.) and graphic display, etc., which are not restricted here and can be set according to actual conditions.
[0123] In addition, real-time push notifications can be set up to allow users to view the health and operating conditions of the battery in real time, thereby realizing real-time monitoring and prediction functions, enabling them to adjust management strategies in a timely manner, helping target users make more reasonable battery use and maintenance decisions, optimizing battery efficiency, extending battery life and ensuring safe system operation.
[0124] This embodiment obtains the display device interface of the target battery, and then based on the display device interface, pushes the battery health status assessment result to the target user for the target user to view, thereby helping the user to promptly discover potential battery problems, such as overcharging, over-discharging, performance degradation, etc., and then take measures to prevent battery failure and extend battery life, thereby achieving real-time monitoring of battery health status, and effectively improving user satisfaction while avoiding potential safety risks.
[0125] For example, to help understand the implementation process of the article generation method, please refer to Figure 4 , Figure 4 A brief flowchart of the battery health status assessment method provided in this application.
[0126] It should be noted that the examples in the figure are only used to understand the present application and do not constitute a limitation on the method for generating articles in the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0127] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0128] This application also provides a battery health status assessment device, please refer to Figure 5 , the battery health status assessment device comprises:
[0129] A data acquisition module 51 is used to acquire first operating data and historical health assessment results of a target battery;
[0130] A first output module 52, configured to input the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model;
[0131] A second output module 53 is used to input the battery feature vector into a battery health status assessment model to obtain current health assessment data output by the battery health status assessment model;
[0132] The evaluation generation module 54 is used to generate a battery health status evaluation result based on the current health evaluation data and the historical health evaluation results.
[0133] The battery health status assessment device is also used for:
[0134] Acquire several groups of historical operation data, and pre-process each of the historical operation data;
[0135] The preprocessed historical operation data is input into an initial battery feature extraction model for iterative training to obtain the battery feature extraction model, wherein the initial battery feature extraction model is constructed based on a time series convolutional neural network.
[0136] The battery health status assessment device is also used for:
[0137] Performing validity analysis on the battery characteristic vector to obtain a validity analysis result;
[0138] Determining a feature type corresponding to the battery feature vector;
[0139] A key feature list is generated based on the effectiveness analysis results and the feature types.
[0140] The battery health status assessment device is also used for:
[0141] Determining a ranking of features of the key features list;
[0142] Based on the feature sorting and preset weights, the target features corresponding to the feature types are applied to the battery feature extraction model.
[0143] The battery health status assessment device is also used for:
[0144] Acquire several groups of historical battery feature vectors, and preprocess each of the historical battery feature vectors;
[0145] The preprocessed historical battery feature vector is input into an initial battery health state assessment model for iterative training to obtain the battery health state assessment model, wherein the initial battery health state assessment model is constructed based on an unscented Kalman filter.
[0146] The battery health status assessment device is also used for:
[0147] Analyze the battery health status assessment result to generate a battery optimization strategy for the target battery;
[0148] Based on the battery optimization strategy, the target battery is optimized, and second operating data of the optimized target battery is obtained;
[0149] The battery optimization strategy is adjusted based on the second operating data.
[0150] The battery health status assessment device is also used for:
[0151] Obtaining a display device interface of a target battery;
[0152] Based on the display device interface, the battery health status assessment result is pushed to a target user for the target user to view.
[0153] The battery health status assessment device provided by the present application adopts the battery health status assessment method in the above embodiment, which can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the battery health status assessment device provided by the present application are the same as the beneficial effects of the battery health status assessment method provided by the above embodiment, and the other technical features in the battery health status assessment device are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0154] The present application provides a battery health status assessment device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the battery health status assessment method in the above-mentioned embodiment one.
[0155] Reference below Figure 6 , which shows a schematic diagram of the structure of a battery health status assessment device suitable for implementing an embodiment of the present application. The battery health status assessment device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6The battery health status assessment device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0156] like Figure 6 As shown, the battery health status evaluation device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the battery health status evaluation device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the battery health status assessment device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a battery health status assessment device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.
[0157] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0158] The battery health status assessment device provided by the present application adopts the battery health status assessment method in the above embodiment, which can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the battery health status assessment device provided by the present application are the same as the beneficial effects of the battery health status assessment method provided by the above embodiment, and the other technical features in the battery health status assessment device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0159] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0160] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0161] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the battery health status assessment method in the above-mentioned embodiment.
[0162] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0163] The computer-readable storage medium may be included in the battery health status evaluation device; or may exist independently without being assembled into the battery health status evaluation device.
[0164] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the battery health status evaluation device, the battery health status evaluation device:
[0165] Acquire first operation data and historical health assessment results of a target battery;
[0166] Inputting the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model;
[0167] Inputting the battery feature vector into a battery health status assessment model to obtain current health assessment data output by the battery health status assessment model;
[0168] A battery health status assessment result is generated based on the current health assessment data and the historical health assessment results.
[0169] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0170] 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 the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, 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 represented 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 flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0171] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0172] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned battery health status assessment method, and can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the battery health status assessment method provided in the above-mentioned embodiment, and will not be repeated here.
[0173] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the battery health status assessment method as described above when the computer program is executed by a processor.
[0174] The computer program product provided in this application can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of this application are the same as the beneficial effects of the battery health status assessment method provided in the above embodiment, which will not be repeated here.
[0175] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A battery health status assessment method, characterized in that: include: Acquire first operation data and historical health assessment results of a target battery; Inputting the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model; Inputting the battery feature vector into a battery health status assessment model to obtain current health assessment data output by the battery health status assessment model; A battery health status assessment result is generated based on the current health assessment data and the historical health assessment results.
2. The battery health status assessment method according to claim 1, characterized in that: The training process of the battery feature extraction model includes: Acquire several groups of historical operation data, and pre-process each of the historical operation data; The preprocessed historical operation data is input into an initial battery feature extraction model for iterative training to obtain the battery feature extraction model, wherein the initial battery feature extraction model is constructed based on a time series convolutional neural network.
3. The battery health status assessment method according to claim 1, characterized in that: After inputting the first operation data into the battery feature extraction model to obtain the battery feature vector output by the battery feature extraction model, the method further includes: Performing validity analysis on the battery characteristic vector to obtain a validity analysis result; Determining a feature type corresponding to the battery feature vector; A key feature list is generated based on the effectiveness analysis results and the feature types.
4. The battery health status assessment method according to claim 3, characterized in that: After generating a key feature list based on the effectiveness analysis result and the feature type, the method further includes: Determining the feature ranking of the key feature list; Based on the feature sorting and preset weights, the target features corresponding to the feature types are applied to the battery feature extraction model.
5. The battery health status assessment method according to claim 1, characterized in that: The training process of the battery health status assessment model includes: Acquire several groups of historical battery feature vectors, and preprocess each of the historical battery feature vectors; The preprocessed historical battery feature vector is input into an initial battery health state assessment model for iterative training to obtain the battery health state assessment model, wherein the initial battery health state assessment model is constructed based on an unscented Kalman filter.
6. The battery health status assessment method according to claim 1, characterized in that: After generating the battery health status assessment result based on the current health assessment data and the historical health assessment result, the method further includes: Analyze the battery health status assessment result to generate a battery optimization strategy for the target battery; Based on the battery optimization strategy, the target battery is optimized, and second operating data of the optimized target battery is obtained; The battery optimization strategy is adjusted based on the second operating data.
7. The battery health status assessment method according to claim 1, characterized in that: After generating the battery health status assessment result based on the current health assessment data and the historical health assessment result, the method further includes: Obtaining a display device interface of a target battery; Based on the display device interface, the battery health status assessment result is pushed to a target user for the target user to view.
8. A battery health status assessment device, characterized in that: include: A data acquisition module, used to acquire first operating data and historical health assessment results of a target battery; A first output module, used for inputting the first operating data into a battery feature extraction model to obtain a battery feature vector output by the battery feature extraction model; A second output module, used to input the battery feature vector into a battery health status assessment model to obtain current health assessment data output by the battery health status assessment model; An assessment generation module is used to generate a battery health status assessment result based on the current health assessment data and the historical health assessment results.
9. A battery health status assessment device, characterized in that: The battery health status assessment device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the battery health status assessment method according to any one of claims 1 to 7.
10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the battery health status assessment method according to any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Battery state evaluation method and device
CN119064797A
Battery running state monitoring and evaluating method and system, electronic equipment and storage medium
CN119780750A
Battery operating status monitoring and evaluation method, system, electronic device and storage medium
CN119780750B
Battery management method, device and equipment and computer readable storage medium
CN121324983A
Battery equipment state performance evaluation and early warning method and system in smart energy station microgrid
CN122715359A
