Intelligent assessment method and system for health state of mobile energy storage power supply

Abstract

The invention discloses a mobile energy storage power supply health state intelligent assessment method and system, and the method comprises the steps: inputting the multi-parameter monitoring data of a power supply into a battery physical model for preliminary assessment, and obtaining a first assessment value; performing feature extraction and feature selection on the obtained monitoring data and environmental data, and inputting an obtained principal component matrix into a health state evaluation model for prediction to obtain a second evaluation value; comparing the first evaluation value with the second evaluation value, and adjusting parameters of the battery physical model by using the health state evaluation model to obtain an optimized battery physical model; obtaining a third evaluation value based on the optimized battery physical model; and obtaining a final battery health state evaluation result based on the third evaluation value and the second evaluation value. By collecting various monitoring data and environmental data in real time, the health state of the battery is comprehensively known, so that the evaluation accuracy is improved; and the established physical model and the health state evaluation model are combined, so that the precision and robustness of the evaluation result are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery management, and in particular to a method and system for intelligently evaluating the health status of a mobile energy storage power supply. Background Art

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

[0003] With the rapid development of portable electronic devices, renewable energy storage and electric vehicles, mobile energy storage power supplies are playing an increasingly important role in daily life and industrial applications. Efficient, safe and reliable mobile energy storage power supplies are not only the key to meeting user needs, but also an important foundation for promoting sustainable development.

[0004] However, the health status of mobile energy storage power directly affects its performance and safety. During use, the battery may be affected by a variety of factors such as charge and discharge cycles, ambient temperature, and usage habits, which may lead to problems such as battery capacity decay and increased internal resistance. If these problems are not identified in time, they may lead to battery failure, equipment damage, and even safety hazards, causing economic losses and safety risks to users. Therefore, it is particularly important to conduct accurate health status assessments.

[0005] There are many health status assessment methods in the prior art, such as simple monitoring methods based on parameters such as voltage, current and temperature. However, these methods often have defects such as insufficient monitoring accuracy, limited data analysis capabilities and failure to consider environmental factors, resulting in inaccurate and incomplete assessment results. For example, there are assessment methods based on statistical or empirical data assessment models. However, these methods lack the interpretability of assessment results. Summary of the invention

[0006] In order to overcome the shortcomings of the above-mentioned prior art, the present invention provides a method and system for intelligently evaluating the health status of a mobile energy storage power supply, which comprehensively understands the health status of the battery by collecting a variety of monitoring data and environmental data in real time, thereby improving the accuracy of the evaluation; and by combining the established physical model with the health status evaluation model, further improving the accuracy and robustness of the evaluation results.

[0007] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions: In a first aspect, the present invention provides a method for intelligently evaluating the health status of a mobile energy storage power supply, comprising: Obtain multi-parameter monitoring data of the mobile energy storage power source and input it into the battery physical model for preliminary evaluation to obtain the first evaluation value of the battery health status; Acquire multi-parameter monitoring data and environmental data of the mobile energy storage power supply, perform feature extraction and feature selection on the multi-parameter monitoring data and environmental data, and fuse the selected features using principal component analysis to obtain a principal component matrix; input the principal component matrix into a pre-trained health status assessment model for further prediction to obtain a second assessment value of the battery health status; Comparing the first evaluation value with the second evaluation value, and adjusting the parameters of the battery physical model using the health status evaluation model to obtain an optimized battery physical model; A re-evaluation is performed based on the optimized battery physical model to obtain a third evaluation value of the battery health state; the third evaluation value and the second evaluation value are weighted averaged to obtain a final battery health state evaluation result.

[0008] A further technical solution is to use a multi-scale isolation forest to identify and remove abnormal data points in the monitoring data, specifically: Performing data cleaning and noise removal on the monitoring data, and decomposing the monitoring data into different time scales; Train the isolation forest model at different time scales to obtain the anomaly score at each time scale; Fuse anomaly scores at different time scales to generate a comprehensive anomaly score; Dynamically adjust the threshold, mark and output abnormal data points that exceed the threshold, and remove the marked abnormal data points.

[0009] According to a further technical solution, the battery physical model includes an internal resistance model, a capacity decay model and an open circuit voltage model.

[0010] A further technical solution is to obtain multi-parameter monitoring data of the mobile energy storage power supply and input it into the battery physical model for preliminary evaluation to obtain the first evaluation value of the battery health state: the calculation results of the internal resistance model, the capacity decay model and the open circuit voltage model are weighted and integrated to obtain the first evaluation value of the battery health state, which is expressed by the following formula:

[0011] in, is the first evaluation value; , , is the weight coefficient; is the current internal resistance; is the initial internal resistance; is the current capacity; is the initial capacity; is the current temperature; is the maximum safe operating temperature.

[0012] A further technical solution is that the feature selection adopts a dynamic feature selection mechanism, specifically: The filtering method is used for preliminary feature screening to select features with high relevance; Recursive feature elimination is used to further refine the selected features and gradually remove features with low importance; Dynamic feature selection is performed in the changes of real-time multi-parameter monitoring data and environmental data, and the feature set is adjusted according to the changes in data distribution.

[0013] A further technical solution is that the health status assessment model adopts an improved long short-term memory network LSTM model, including an input layer, a multi-layer perceptron layer, multiple LSTM layers and an output layer connected in sequence, and residual connections are added between each LSTM layer.

[0014] A further technical solution is to use the health status assessment model to correct the parameters in the battery physical model through loss function and optimization algorithm, and iteratively update the model.

[0015] In a second aspect, the present invention provides a mobile energy storage power supply health status intelligent assessment system, comprising: A physical model evaluation module is configured to: obtain multi-parameter monitoring data of a mobile energy storage power source, and input the data into a battery physical model for preliminary evaluation to obtain a first evaluation value of the battery health status; The network model evaluation module is configured to: obtain multi-parameter monitoring data and environmental data of the mobile energy storage power supply, perform feature extraction and feature selection on the multi-parameter monitoring data and environmental data, and fuse the selected features using the principal component analysis method to obtain a principal component matrix; input the principal component matrix into a pre-trained health status evaluation model for further prediction to obtain a second evaluation value of the battery health status; A physical model optimization module, configured to: compare the first evaluation value with the second evaluation value, and adjust the parameters of the battery physical model using the health status evaluation model to obtain an optimized battery physical model; The health status assessment module is configured to: perform a re-assessment based on the optimized battery physical model to obtain a third battery health status assessment value; and perform a weighted average of the third assessment value and the second assessment value to obtain a final battery health status assessment result.

[0016] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the intelligent assessment of the health status of a mobile energy storage power source as described in the first aspect.

[0017] In a fourth aspect, the present invention provides a computer device comprising 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 intelligent assessment of the health status of a mobile energy storage power source as described in the first aspect are implemented.

[0018] One or more of the above technical solutions have the following beneficial effects: The present invention improves the accuracy and robustness of the evaluation results by combining the physical model and the health status assessment model. The physical model can provide basic mechanism information of the battery, while the data-driven model can capture complex patterns and nonlinear relationships in real-time data, and adjust the parameters in the physical model through the health status assessment model, thereby showing higher accuracy and adaptability in the real environment. In addition, the physical model provides a transparent and interpretable foundation, which, when combined with the health status assessment model, can provide more interpretability for the evaluation results. For example, through the physical model, it is possible to clearly analyze how factors such as temperature, charge and discharge cycles, and voltage changes affect the performance of the battery, thereby providing more accurate theoretical support for health status assessment.

[0019] The present invention can fully understand the health status of the battery by collecting a variety of monitoring data (such as voltage, current, temperature, internal resistance and number of charge and discharge cycles) and environmental data in real time, thereby improving the accuracy of the assessment; the improved isolation forest is used to identify abnormal points in the monitoring data, and the abnormal characteristics of the data can be captured at different time scales, which is more suitable for the complex, multi-dimensional characteristics and real-time requirements of mobile energy storage power supplies. In particular, in real-time data, multi-scale detection helps to improve the accuracy of abnormal detection and reduce false positives and missed reports; the use of a variety of feature extraction methods (such as statistical features, time attenuation features, frequency domain features, etc.) can effectively capture battery state changes and enhance the prediction ability of the model; and the use of an improved feature selection method, namely a dynamic feature selection mechanism and a real-time update mechanism, can dynamically adjust the feature set according to changes in new data to ensure that the health status assessment model always remains effective in a changing environment.

[0020] The present invention inputs the principal component matrix into the health status assessment model, and the output health status score can provide users with clear battery health status information to help users make maintenance or replacement decisions. The system can provide maintenance suggestions in a timely manner based on the health status of the battery, improve the safety and reliability of users' use of batteries, and reduce failure rates and maintenance costs and improve safety by optimizing the use of mobile energy storage power supplies. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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.

[0022] Figure 1 is a flow chart of an evaluation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] It should be noted that the following detailed descriptions are exemplary and are 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.

[0024] 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.

[0025] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0026] During the use of mobile energy storage power supplies, their monitoring data will change dynamically with the changes in time, load and environmental conditions. These changes have an important impact on battery health. For example, mobile energy storage power supplies can charge a variety of loads. Excessive loads or frequent load changes will cause excessive discharge of the battery and damage battery health. In recent years, the rapid development of artificial intelligence and big data analysis technologies has provided new solutions for health status assessment. Data-driven intelligent assessment methods can comprehensively consider multiple influencing factors and achieve more accurate health status assessment. Therefore, the development of an efficient and intelligent mobile energy storage power health status assessment method and system has become an urgent need to improve equipment performance, ensure user safety and promote market development.

[0027] Embodiment 1 like Figure 1 As shown, this embodiment discloses a method for intelligently evaluating the health status of a mobile energy storage power supply, including: S1: Obtain multi-parameter monitoring data of the mobile energy storage power supply and input it into the battery physical model for preliminary evaluation to obtain the first evaluation value of the battery health status.

[0028] S101: Collect multi-parameter monitoring data of the mobile energy storage power supply and perform pre-processing.

[0029] A variety of sensors are installed on the battery cells of the mobile energy storage power supply to collect real-time monitoring data on parameters such as voltage, current, temperature, internal resistance, number of charge and discharge cycles, and remaining power. A comprehensive monitoring system is formed by combining different types of sensors (such as temperature sensors, voltage sensors, internal resistance sensors, charge and discharge cycle counters, etc.) to obtain more comprehensive battery status data.

[0030] Dynamically adjust the data collection frequency according to the operating status of the battery. For example, increase the sampling frequency during peak charging or discharging, and reduce the frequency during steady-state operation to optimize data collection efficiency.

[0031] Since the acquired monitoring data may contain noise, missing values ​​or outliers, data preprocessing is required. Data preprocessing is performed on the collected data, including data cleaning, noise removal and outlier removal to ensure data accuracy. When removing outliers, multi-scale isolation forests are used to effectively identify abnormal data points, providing strong support for the health assessment of mobile energy storage power supplies.

[0032] By improving the isolation forest, we can obtain a multi-scale isolation forest, which can capture abnormal characteristics of data at different time scales. It is more suitable for the complex, multi-dimensional characteristics and real-time requirements of mobile energy storage power sources. Especially in real-time data, multi-scale detection helps to improve the accuracy of anomaly detection and reduce false positives and false negatives, which will better support the accurate assessment of battery health status. The multi-scale isolation forest is used to detect abnormal data points, including: (1) Clean and remove noise from the collected data (i.e., monitoring data) to ensure data quality; decompose the time series data (i.e., monitoring data) into different time scales to capture short-term and long-term trends; select appropriate parameters for the isolation forest model, such as voltage, current, temperature, etc., and calculate characteristics such as sliding mean and standard deviation in short-term and long-term time windows.

[0033] (2) Train the isolation forest model at different time scales to obtain the anomaly score at each time scale.

[0034] 1) Construct isolation forest models for different time scales, such as short-term and long-term; 2) Each Isolation Forest Model Will data Calculating an anomaly score , For the Isolation forest model trained on time scales, For time scale The isolation forest model for data points The abnormal score.

[0035] (3) The weighted average method is used to fuse the anomaly scores of different time scales to generate a comprehensive anomaly score, thereby improving the robustness of abnormal data point detection.

[0036] (4) Dynamically adjust the threshold to adapt to the real-time fluctuations of multi-parameter monitoring data and further reduce the false positive and false negative rates. The threshold can be set dynamically based on the historical statistical characteristics of the anomaly score. For example, the threshold can be defined using the mean and standard deviation of the recent anomaly score.

[0037] (5) Abnormal data points that exceed the threshold are marked and output for use by the subsequent health status assessment module.

[0038] By generating anomaly scores at different time scales and fusing detection results with dynamically adjusted thresholds, multi-scale isolation forests can better adapt to the complexity in real-time monitoring of battery health status.

[0039] At the same time, it is also necessary to ensure that the data from different sensors are synchronized in time. Interpolation methods (such as linear interpolation) can be used to align data of different frequencies to a unified time point for subsequent analysis.

[0040] S102: Establish a battery physical model, including an internal resistance model, a capacity decay model, and an open circuit voltage model.

[0041] Internal resistance model: The internal resistance of the battery will increase with the change of usage time, number of charge and discharge cycles and temperature. The internal resistance model can be expressed by the following formula:

[0042] in, is the initial internal resistance of the battery, It is the change of internal resistance over time, which can be modeled by factors such as the number of charge and discharge cycles and temperature.

[0043] Capacity attenuation model: The capacity attenuation of the battery is mainly affected by the number of charge and discharge cycles and the use environment (especially temperature). The capacity attenuation model can be expressed by the following formula:

[0044] in, is the capacity of the battery at time t; is the initial capacity of the battery; is the capacity attenuation coefficient, which depends on the type of battery, etc.; The number of charge and discharge cycles of the battery.

[0045] Open circuit voltage model: Open circuit voltage is another important indicator for evaluating battery health, which is usually proportional to the remaining capacity of the battery. According to the chemical reaction of the battery and the characteristics of the electrolyte, the open circuit voltage can be expressed by the following relationship:

[0046] in, is the open circuit voltage of the battery, is the capacity of the battery, is the battery temperature, It represents a mathematical function that depends on battery capacity and temperature. It is used to reflect the combined effect of battery capacity and temperature on open circuit voltage and is used to predict the open circuit voltage of the battery.

[0047] S103: Calculate using the above physical model, and weight the calculation results of the internal resistance model, the capacity decay model, and the open circuit voltage model to obtain a first evaluation value of the battery health status. It can be expressed by the following formula:

[0048] in, The health status score calculated by the physical model is the first evaluation value; , , is the weight coefficient, which is set according to the actual situation; is the current internal resistance; is the initial internal resistance; is the current capacity; is the initial capacity; is the current temperature; is the maximum safe operating temperature.

[0049] The battery physical model comprehensively considers the influence of factors such as internal resistance, capacity, and temperature to evaluate the health status of the battery. Through multi-factor modeling, it can more accurately reflect the true state of the battery and avoid the deviation caused by a single parameter, especially in complex usage environments, providing a framework and basis for preliminary evaluation.

[0050] S2: Acquire multi-parameter monitoring data and environmental data of the mobile energy storage power supply, perform feature extraction and feature selection on the multi-parameter monitoring data and environmental data, and fuse the selected features using principal component analysis to obtain a principal component matrix; input the principal component matrix into a pre-trained health status assessment model for further prediction to obtain a second assessment value of the battery health status.

[0051] S201: Obtain the multi-parameter monitoring data pre-processed in S1, and collect external factors that affect battery performance, such as temperature, humidity, and air pressure in the environment where the mobile energy storage power source is located. When collecting environmental data, each sensor can be placed near the battery casing or outside the device to ensure that it can reflect changes in the surrounding environment.

[0052] S202: Extract and enhance features of the preprocessed multi-parameter monitoring data and environmental data to obtain enhanced features.

[0053] In this embodiment, feature extraction specifically includes: Extract the statistical features of voltage, current, temperature, and internal resistance from the multi-parameter monitoring data. The statistical features include mean, variance, maximum value, minimum value, peak value, skewness, etc.; extract the time attenuation features of the multi-parameter monitoring data, i.e., each time series data, using the weighted average attenuation feature extraction, which is specifically expressed as:

[0054] in, is the observed value at the latest n moments, is the corresponding weight, usually using exponential decay weight to give more weight to recent data, is the attenuation factor (selected as 0.9 in this embodiment).

[0055] Extract the frequency domain features of multi-parameter monitoring data, that is, each time series data, use fast Fourier transform FFT to convert the time series data into frequency domain, extract the main frequency components, and extract the main frequency and corresponding amplitude from the fast Fourier results.

[0056] Specifically expressed as:

[0057] in, Indicates that the signal is at frequency The amplitude and phase of Represents the nth sample value of the time domain signal, N represents the number of data points, represents frequency, j represents imaginary unit, and represents complex number operation; is a complex exponential function, representing the phase rotation in the frequency domain.

[0058] Extract the frequency and stability characteristics of the charge and discharge cycle. The cycle frequency is specifically expressed as:

[0059] in, is the number of charge and discharge cycles per unit time, is the length of the time window.

[0060] The cyclic stability is specifically expressed as:

[0061] in, is the maximum value of the number of charge and discharge cycles, is the minimum number of charge and discharge cycles, The average number of charge and discharge cycles.

[0062] Extract environmental factor characteristics of environmental data, including temperature fluctuation range and humidity impact characteristics. The temperature fluctuation range is specifically expressed as: .

[0063] The humidity impact characteristics can be obtained through the regression model, which is specifically expressed as:

[0064] in, The degree of influence of humidity on the health status of the battery; is the intercept of the regression model, indicating the basic effect of humidity when humidity H and temperature T are 0; is the regression coefficient of humidity, indicating the change in the effect of humidity on health status when humidity H increases by one unit; H is the value of the current ambient humidity; is the regression coefficient of temperature, which indicates the change in the impact of temperature on health status when the temperature T increases by one unit; T is the value of the current ambient temperature.

[0065] The present invention designs a flexible and dynamic feature selection mechanism, which combines filtering, recursive feature elimination (RFE) and dynamic feature selection to ensure the effectiveness and accuracy of the model in a changing data environment. The specific steps are as follows: (1) Use the filtering method to perform preliminary feature screening and select features with high correlation. Use statistical methods (such as correlation analysis, variance threshold, chi-square test, etc.) to remove irrelevant or low-variance features to reduce the number of features.

[0066] (2) Recursive feature elimination is used to further refine the selected features and gradually remove features with low importance.

[0067] 1. Select the linear regression model as the basic model and train it on the filtered feature set; 2. Evaluate the importance of the features, either using the model's coefficients or importance scores; 3. Remove the least important features and retrain the model; repeat steps 2 and 3 until the required number of features is reached. For the linear regression model, feature importance is expressed as regression coefficients.

[0068] (3) Perform dynamic feature selection in real-time or periodic mobile energy storage power data changes, and adjust the feature set according to changes in data distribution to maintain the adaptability and accuracy of the health status assessment model.

[0069] Regularly monitor the distribution of monitoring data and environmental data of mobile energy storage power sources (such as changes in mean and variance). If the change exceeds a certain threshold, dynamic feature selection is triggered; when the data changes significantly, reapply filtering and recursive feature elimination to generate an updated feature set; automatically adjust the feature selection frequency and selection method according to data changes. For example, the feature selection frequency can be increased when real-time data changes significantly.

[0070] The present invention combines filtering, recursive feature elimination and dynamic feature selection, and can update the feature set in real time or periodically according to data changes, thereby maintaining the robustness of the model in a dynamic environment and avoiding the degradation of model performance due to changes in data distribution; this feature selection mechanism can reduce the number of features while ensuring the model effect, thereby reducing the computing cost; the above improvements help to improve the applicability and accuracy of the health status assessment model in the health status assessment of mobile energy storage systems, and adapt to complex dynamic changes in data.

[0071] The principal component analysis method PCA is used to fuse and enhance the selected features, which can effectively fuse the selected features into principal components to improve the prediction effect of the health status assessment model. The specific steps are as follows: 1) Before performing principal component analysis, the data must first be standardized to ensure that each feature is on the same scale.

[0072] 2) Calculate the covariance matrix of the standardized feature matrix to evaluate the linear relationship between features. It can be expressed as:

[0073] in, is the covariance matrix, n is the number of samples, is the standardized feature matrix.

[0074] 3) Perform eigenvalue decomposition on the covariance matrix to find the eigenvalues ​​and eigenvectors. It can be expressed as:

[0075] in, represents the feature vector, is the eigenvalue, which represents the variance of the corresponding eigenvector.

[0076] 4) According to the size of the eigenvalue, select the eigenvectors with the largest eigenvalues ​​among the first k. The number of principal components to be selected is usually determined by the Cumulative Explained Variance.

[0077] 5) Use the selected eigenvectors to transform the standardized feature data into the new principal component space and obtain the principal component matrix. It can be expressed as:

[0078] Among them, Z is the principal component matrix, is a matrix containing the first k eigenvectors.

[0079] S203: Input the principal component matrix into a pre-trained health status assessment model for prediction, and output a second battery health status assessment value.

[0080] In this embodiment, the health status assessment model adopts an improved long short-term memory network LSTM model structure. The health status of the battery is affected by long-term use and historical data. LSTM can effectively capture the long-term battery health change trend.

[0081] The improved long short-term memory network LSTM model includes an input layer, a fully connected layer (MLP), multiple LSTM layers and an output layer connected in sequence. In the battery health status assessment, it can effectively capture the long-term dependencies in time series data. The input layer receives the principal component matrix; the fully connected layer (using a multi-layer perceptron MLP) is used to perform nonlinear mapping on the principal components and extract potential features; multiple LSTM layers are connected in series to capture the time dependency of battery health data. Multi-layer LSTM can extract complex features in the battery health status at a deeper level, improve the model's fitting ability and generalization ability, and is particularly suitable for data with high dimensions and complex nonlinear relationships; the output layer outputs the battery health status assessment value, which is the second assessment value.

[0082] Add residual connections between each LSTM layer in multiple LSTM layers to avoid gradient flow difficulties caused by too deep networks; through residual connections, the health status assessment model can be trained more easily because the gradient can be transmitted more effectively, which can reduce the overfitting phenomenon in deep networks and enhance the generalization ability of the model. At the same time, add a Dropout layer after the LSTM layer and the fully connected layer to prevent the model from over-relying on specific nodes during training; add L2 regularization between the LSTM layer and the fully connected layer to punish larger weights during training, thereby preventing the model from overfitting the training data.

[0083] Through the input of the principal component matrix, the dimension of the input data is effectively reduced, while the most important features are retained, noise and redundancy are reduced. First, a multi-layer perceptron (MLP) is used for feature mapping, and the reduced-dimensional data is further mapped to a new feature space through MLP to make the model easier to understand and learn; a multi-layer LSTM network is used to capture the time dependency, local features, and long-time span changes in the battery health data, and finally the battery health status assessment value is output, so that the battery health status can be more accurately assessed, providing more explanatory prediction results, and enhancing the robustness and reliability of the system. Therefore, in addition to the features extracted from multi-parameter monitoring data, the health status assessment model also combines the features extracted from environmental data (external features) as input features to capture the changes of the battery in different environments. It can further enhance the model's understanding of the battery health status, help the model more accurately predict the health status of the battery in a complex environment, and is suitable for health status assessment affected by multiple factors.

[0084] S3: Compare the first evaluation value with the second evaluation value, and use the health status evaluation model to adjust the parameters of the battery physical model to obtain an optimized battery physical model.

[0085] The health status assessment model is used to correct the parameters in the battery physical model through loss functions and optimization algorithms, and the model is iteratively updated to improve the overall assessment accuracy.

[0086] S301: Define a loss function: In battery health status assessment, the loss function is used to measure the difference between the output of the battery physical model and the prediction result of the health status assessment model.

[0087] Assumptions is the output of the battery physical model for the i-th sample, is the predicted output of the health status assessment model of the i-th sample, then the loss function is expressed as:

[0088] Where N is the number of samples, are the battery physical model parameters that need to be optimized.

[0089] S302: Use the gradient descent method to minimize the loss function to correct the parameters in the battery physical model. Calculate the gradient of the loss function for each parameter, and use the gradient descent method to update the parameters in the battery physical model based on the calculated gradient. Multiple iterations are required until the loss function converges.

[0090] S4: re-evaluate based on the optimized battery physical model to obtain a third battery health status evaluation value; and perform weighted average of the third evaluation value and the second evaluation value to obtain a final battery health status evaluation result.

[0091] Combining the re-evaluation results of the optimized battery physical model and the prediction results of the health status evaluation model, the final health status evaluation result is obtained by weighted average. It can be expressed as:

[0092] in, The final health status assessment result is This is the re-evaluation result of the optimized battery physical model. is the prediction result of the health status assessment model, is the weighting coefficient, which controls the influence weight of the physical model and the health status assessment model.

[0093] The present invention improves the accuracy and robustness of the evaluation results by combining the physical model and the health status assessment model. The physical model can reflect the basic physical properties of the battery and provide a preliminary framework, while the health status assessment model can learn complex nonlinear relationships from historical data and adjust the parameters in the physical model according to the health status assessment model, thereby showing higher accuracy and adaptability in the real environment, and the physical model provides a transparent and explainable foundation.

[0094] Embodiment 2 This embodiment discloses a mobile energy storage power supply health status intelligent assessment system, including: A physical model evaluation module is configured to: obtain multi-parameter monitoring data of a mobile energy storage power source, and input the data into a battery physical model for preliminary evaluation to obtain a first evaluation value of the battery health status; The network model evaluation module is configured to: obtain multi-parameter monitoring data and environmental data of the mobile energy storage power supply, perform feature extraction and feature selection on the multi-parameter monitoring data and environmental data, and fuse the selected features using the principal component analysis method to obtain a principal component matrix; input the principal component matrix into a pre-trained health status evaluation model for further prediction to obtain a second evaluation value of the battery health status; A physical model optimization module, configured to: compare the first evaluation value with the second evaluation value, and adjust the parameters of the battery physical model using the health status evaluation model to obtain an optimized battery physical model; The health status assessment module is configured to: perform a re-assessment based on the optimized battery physical model to obtain a third battery health status assessment value; and perform a weighted average of the third assessment value and the second assessment value to obtain a final battery health status assessment result.

[0095] Embodiment 3 The purpose of this embodiment is to provide a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of embodiment 1 when executing the program.

[0096] Embodiment 4 The purpose of this embodiment is to provide a computer-readable storage medium, a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of the method of embodiment 1 are performed.

[0097] The steps involved in the apparatus of the above embodiments 3 and 4 correspond to the method embodiment 1, and the specific implementation method can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0098] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0099] 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.

[0100] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A method for intelligently evaluating the health status of a mobile energy storage power supply, characterized in that: include: Obtain multi-parameter monitoring data of the mobile energy storage power source and input it into the battery physical model for preliminary evaluation to obtain the first evaluation value of the battery health status; Acquire multi-parameter monitoring data and environmental data of the mobile energy storage power supply, perform feature extraction and feature selection on the multi-parameter monitoring data and environmental data, and fuse the selected features using principal component analysis to obtain a principal component matrix; input the principal component matrix into a pre-trained health status assessment model for further prediction to obtain a second assessment value of the battery health status; Comparing the first evaluation value with the second evaluation value, and adjusting the parameters of the battery physical model using the health status evaluation model to obtain an optimized battery physical model; A re-evaluation is performed based on the optimized battery physical model to obtain a third evaluation value of the battery health state; the third evaluation value and the second evaluation value are weighted averaged to obtain a final battery health state evaluation result.

2. A method for intelligently evaluating the health status of a mobile energy storage power supply according to claim 1, characterized in that: Multi-scale isolation forest is used to identify abnormal data points of the monitoring data and remove them, specifically: Performing data cleaning and noise removal on the monitoring data, and decomposing the monitoring data into different time scales; Train the isolation forest model at different time scales to obtain the anomaly score at each time scale; Fuse anomaly scores at different time scales to generate a comprehensive anomaly score; Dynamically adjust the threshold, mark and output abnormal data points that exceed the threshold, and remove the marked abnormal data points.

3. A method for intelligently evaluating the health status of a mobile energy storage power supply according to claim 1, characterized in that: The battery physical model includes an internal resistance model, a capacity decay model and an open circuit voltage model.

4. A method for intelligently evaluating the health status of a mobile energy storage power supply according to claim 3, characterized in that: The multi-parameter monitoring data of the mobile energy storage power supply is obtained and input into the battery physical model for preliminary evaluation to obtain the first evaluation value of the battery health status. Specifically, the calculation results of the internal resistance model, the capacity decay model and the open circuit voltage model are weighted and integrated to obtain the first evaluation value of the battery health status, which is expressed by the following formula: in, is the first evaluation value; , , is the weight coefficient; is the current internal resistance; is the initial internal resistance; is the current capacity; is the initial capacity; is the current temperature; is the maximum safe operating temperature.

5. A method for intelligently evaluating the health status of a mobile energy storage power supply according to claim 1, characterized in that: The feature selection adopts a dynamic feature selection mechanism, specifically: The filtering method is used for preliminary feature screening to select features with high relevance; Recursive feature elimination is used to further refine the selected features and gradually remove features with low importance; Dynamic feature selection is performed in the changes of real-time multi-parameter monitoring data and environmental data, and the feature set is adjusted according to the changes in data distribution.

6. A method for intelligently evaluating the health status of a mobile energy storage power supply according to claim 1, characterized in that: The health status assessment model adopts an improved long short-term memory network LSTM model, including an input layer, a multi-layer perceptron layer, multiple LSTM layers and an output layer connected in sequence, and a residual connection is added between each LSTM layer.

7. A method for intelligently evaluating the health status of a mobile energy storage power supply according to claim 6, characterized in that: The health status assessment model is used to correct the parameters in the battery physical model through the loss function and optimization algorithm, and the model is updated iteratively.

8. A mobile energy storage power supply health status intelligent assessment system, characterized in that: include: A physical model evaluation module is configured to: obtain multi-parameter monitoring data of a mobile energy storage power source, and input the data into a battery physical model for preliminary evaluation to obtain a first evaluation value of the battery health status; The network model evaluation module is configured to: obtain multi-parameter monitoring data and environmental data of the mobile energy storage power supply, perform feature extraction and feature selection on the multi-parameter monitoring data and environmental data, and fuse the selected features using the principal component analysis method to obtain a principal component matrix; input the principal component matrix into a pre-trained health status evaluation model for further prediction to obtain a second evaluation value of the battery health status; A physical model optimization module, configured to: compare the first evaluation value with the second evaluation value, and adjust the parameters of the battery physical model using the health status evaluation model to obtain an optimized battery physical model; The health status assessment module is configured to: perform a re-assessment based on the optimized battery physical model to obtain a third battery health status assessment value; and perform a weighted average of the third assessment value and the second assessment value to obtain a final battery health status assessment result.

9. 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 the method for intelligently evaluating the health status of a mobile energy storage power supply as described in any one of claims 1 to 7 are implemented.

10. 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 method for intelligently evaluating the health status of a mobile energy storage power supply as described in any one of claims 1-7 are implemented.

Images