A big data-based hybrid energy storage battery state monitoring method and system

Abstract

This invention discloses a method and system for monitoring the state of hybrid energy storage batteries based on big data, belonging to the field of battery state monitoring technology. The method includes: collecting battery state data and preprocessing the data; obtaining a high-dimensional feature vector based on the preprocessed data through dynamic weight adjustment and fusion; constructing a battery state prediction model based on a long short-time memory network model; obtaining a battery health value based on the high-dimensional feature vector through the battery state prediction model; and monitoring the battery health state in real time based on the battery health value. This invention significantly improves the accuracy of battery health value prediction by dynamically adjusting weights and fusing to generate a high-dimensional feature vector, achieving real-time monitoring and fault early warning of battery health state under complex operating conditions, and effectively improving the safety, reliability, and operational management efficiency of hybrid energy storage systems.

Description

Technical Field

[0001] This invention relates to the field of battery status monitoring technology, and in particular to a method and system for monitoring the status of hybrid energy storage batteries based on big data. Background Technology

[0002] With the development of energy storage technology, batteries, as the core component of energy storage systems, have been widely used in power systems, new energy vehicles, and smart grids. Especially in hybrid energy storage systems, batteries work in conjunction with other energy storage devices (such as supercapacitors) to provide more stable and efficient energy management for complex operating conditions. However, battery performance gradually degrades over time, and its operating status is affected by various factors, including electrical characteristics (such as voltage, current, and internal resistance), environmental conditions (such as temperature and humidity), and load changes. Therefore, real-time monitoring of battery operating status and prediction of its health status has become an important technical means to ensure the safety and reliability of energy storage systems. In recent years, battery status monitoring methods based on big data have gradually become a research hotspot. The core of these methods lies in utilizing large-scale operational data, through features extraction, data modeling, and status prediction techniques, to comprehensively analyze the battery's operating status and achieve health management.

[0003] Existing battery status monitoring methods have certain limitations. Traditional methods often rely on a single feature (such as voltage or temperature) for simple threshold judgments, which fails to comprehensively reflect the battery's operating status. Furthermore, while some methods incorporate multidimensional data analysis, the unreasonable weighting of different features leads to a failure to fully reflect the role of key influencing factors, reducing monitoring accuracy. Simultaneously, existing methods lack in-depth analysis of dynamic changes in time-series data when predicting battery health status, failing to effectively capture short-term and long-term trends in battery status. These shortcomings cause existing battery status monitoring technologies to exhibit certain lag and inaccuracies when dealing with complex operating conditions. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a hybrid energy storage battery status monitoring method based on big data, which solves the problems of insufficient accuracy in feature extraction and fusion and low accuracy in health status prediction.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for monitoring the state of hybrid energy storage batteries based on big data, comprising,

[0008] Battery status data is collected and preprocessed. Based on the preprocessed battery status data, a high-dimensional feature vector is obtained by dynamically adjusting weights and fusing the data. A battery status prediction model is constructed based on a long short-term memory network model. The battery health value is obtained based on the high-dimensional feature vector and the battery status prediction model. The battery health status is monitored in real time based on the battery health value.

[0009] As a preferred embodiment of the hybrid energy storage battery status monitoring method based on big data described in this invention, the battery status data includes electrical characteristic data, environmental parameters, and operating load information.

[0010] The preprocessing of battery status data includes outlier removal, missing value imputation, and normalization.

[0011] As a preferred embodiment of the big data-based hybrid energy storage battery status monitoring method of the present invention, the high-dimensional feature vector is obtained by dynamically adjusting weights and fusing preprocessed battery status data. The specific steps are as follows:

[0012] Battery state features are extracted from preprocessed battery state data using statistical analysis methods.

[0013] Correlation analysis was used to analyze the impact of preprocessed battery state data on battery performance and to extract the factors affecting battery performance.

[0014] The reliability of the preprocessed battery state data was evaluated using statistical methods.

[0015] The weights of battery state features are dynamically adjusted based on influencing factors and reliability, as expressed by:

[0016] Wi(s)=γ1×Ei(s)+γ2×Ri(s);

[0017] Where Wi(s) is the weight of the i-th battery state feature at time s after dynamic adjustment, Ei(s) represents the influencing factors of the i-th battery state feature at time s, Ri(s) represents the credibility of the i-th battery state feature at time s, γ1 is the weight coefficient of Ei(s), γ2 is the weight coefficient of Ri(s), s is the time index variable, and i is the battery state feature index variable.

[0018] By using physical constraints, the weights Wi(s) of the dynamically adjusted i-th battery state features at time s are fused to obtain a high-dimensional feature vector.

[0019] As a preferred embodiment of the big data-based hybrid energy storage battery state monitoring method of the present invention, the following steps are taken: Through physical constraints, the weights Wi(s) of the dynamically adjusted i-th battery state feature at time s are fused to obtain a high-dimensional feature vector.

[0020] Physical constraint rules are defined based on battery operating mechanisms, operating conditions, safety thresholds, and experimental data.

[0021] Correction factors are defined based on physical constraint rules;

[0022] The dynamically adjusted weights are corrected using a correction factor;

[0023] The sliding window method is used to fuse the weights corrected for the current time point and historical time points to obtain a high-dimensional feature vector, expressed as follows:

[0024]

[0025] Where V(s) is a high-dimensional feature vector, Q i (sk) is the weight of the i-th battery state feature after correction at time sk, X i (sk) is the i-th battery state feature at time sk, k is the index variable with time lag, and N is the total number of included time points.

[0026] As a preferred embodiment of the hybrid energy storage battery state monitoring method based on big data described in this invention, the specific steps for constructing a battery state prediction model based on a long short-term memory network model are as follows:

[0027] The model is based on the Long Short-Term Memory (LSTM) network model.

[0028] Arrange the high-dimensional historical feature vectors in chronological order and use the sliding window method to create the input time series;

[0029] The input layer of an LSTM model accepts a time series input.

[0030] By using an LSTM multilayer structure to capture dynamic relationships in time series and extract time-dependent features;

[0031] Fully connected layers map the output temporal dependency features to the target feature dimension;

[0032] A battery state prediction model was constructed.

[0033] As a preferred embodiment of the hybrid energy storage battery status monitoring method based on big data described in this invention, the steps for obtaining battery health values ​​based on high-dimensional feature vectors and a battery status prediction model are as follows:

[0034] The high-dimensional feature vectors are organized into a sliding window format according to time order to form a time series input.

[0035] By using a multi-layer structure to capture short-term and long-term dynamic relationships, the first LSTM layer extracts the low-level dynamic characteristics of the time series, and the second LSTM layer further extracts the time-dependent features.

[0036] The time-dependent features of the LSTM output are passed to a fully connected layer to obtain battery health values, expressed as:

[0037]

[0038] Where Y(s) is the battery health value at time s, σ is the activation function, H is the total number of neurons in the fully connected layer, and w j Q is the weight of the j-th fully connected neuron, F is the dimension of the high-dimensional feature vector, and Q is the weight of the j-th fully connected neuron. i (s) is the weight of the i-th battery state feature after correction at time s, X i (s) is the i-th battery state feature at time s, α is a parameter, and b j is the bias term of the j-th fully connected layer neuron, c is the constant term, i is the battery state feature index variable, and j is the index variable of the fully connected layer neuron.

[0039] As a preferred embodiment of the big data-based hybrid energy storage battery status monitoring method of the present invention, the specific steps for real-time monitoring of battery health status based on battery health values ​​are as follows:

[0040] A threshold T is set based on the average battery health value.

[0041] The battery health value Y(s) is compared with the threshold T to monitor the battery health status in real time.

[0042] When Y(s) > T, the battery is in good health and continues to operate normally.

[0043] When Y(s)≤T, the battery health is poor, and corresponding measures should be taken immediately.

[0044] Secondly, this invention provides a hybrid energy storage battery status monitoring system based on big data, comprising a data acquisition and preprocessing module, a feature generation module, a model building module, a health value calculation module, and a status monitoring module. The data acquisition and preprocessing module is used to acquire battery status data and preprocess it. The feature generation module is used to obtain high-dimensional feature vectors based on the preprocessed battery status data by dynamically adjusting weights and fusing them. The model building module is used to construct a battery status prediction model based on a long short-term memory network model. The health value calculation module is used to obtain the battery health value based on the high-dimensional feature vectors through the battery status prediction model. The status monitoring module is used to monitor the battery health status in real time based on the battery health value.

[0045] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the hybrid energy storage battery state monitoring method based on big data as described in the first aspect of the present invention.

[0046] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the hybrid energy storage battery state monitoring method based on big data as described in the first aspect of the present invention.

[0047] The beneficial effects of this invention are as follows: This invention solves the problem of inaccurate multidimensional feature analysis and fusion by dynamically adjusting weights and generating high-dimensional feature vectors. Based on a Long Short-Term Memory (LSTM) network, it constructs a battery state prediction model, deeply explores the dynamic change patterns in the time series, significantly improves the accuracy of battery health value prediction, realizes real-time monitoring and fault early warning of battery health status under complex operating conditions, and effectively improves the safety, reliability and operation management efficiency of hybrid energy storage systems. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart of the hybrid energy storage battery status monitoring method based on big data in Example 1.

[0050] Figure 2 This is a system diagram of the hybrid energy storage battery status monitoring system based on big data in Example 1. Detailed Implementation

[0051] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0052] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0054] Example 1, referring to Figure 1 and Figure 2 This is the first embodiment of the present invention, which provides a method for monitoring the state of hybrid energy storage batteries based on big data, including the following steps:

[0055] S1. The battery status data includes electrical characteristic data, environmental parameters, and operating load information.

[0056] S1.1 The preprocessing of battery status data includes removing outliers, imputing missing values, and normalization.

[0057] It should be noted that outlier removal is achieved by using rule-based detection to identify abnormal data points in the battery status data that deviate from the normal range (such as sudden changes in voltage, current, or temperature values), and then removing or replacing them.

[0058] Missing value imputation is a method of filling in missing values ​​in data that is missing due to equipment failure or transmission problems during the data acquisition process, by using interpolation methods (such as mean imputation, linear imputation, or time series forecasting methods) to restore the integrity of the data.

[0059] Normalization is a process that normalizes different physical quantities (such as voltage, current, temperature, etc.) to a uniform numerical range (such as [0,1] or [-1,1]) to eliminate the influence of differences in feature dimensions on model training.

[0060] S2. Based on the preprocessed battery state data, high-dimensional feature vectors are obtained by dynamically adjusting weights and fusing data.

[0061] S2.1 Extract battery state features from the preprocessed battery state data using statistical analysis methods.

[0062] It should be noted that battery state characteristics include central tendency characteristics, dispersion characteristics, and distribution pattern characteristics;

[0063] It should also be noted that, based on the preprocessed battery state data, the mean is obtained by summing all the data points and then dividing the sum by the number of data points.

[0064] Sort the data points by numerical value. If the number of data points is odd, the median is the middle data point; if the number of data points is even, the median is the average of the two middle data points.

[0065] By using the mean and median, we can obtain the central tendency characteristics that reflect the location of the center of the dataset;

[0066] Calculate the square of the difference between each data point and the mean, and then calculate the average of these squared differences to obtain the variance;

[0067] The positive square root of the variance is the standard deviation;

[0068] The range is obtained by subtracting the minimum value from the maximum value in the data.

[0069] By using variance, standard deviation, and range, we can obtain the dispersion characteristics that reflect the degree of data dispersion.

[0070] Calculate the difference between each data point and the mean, standardize it (divide by the standard deviation), then cube the standardized difference and calculate its average to obtain the skewness;

[0071] The kurtosis is obtained by raising the standardized difference to the fourth power, taking its average, and then subtracting 3.

[0072] By using skewness and kurtosis, we can obtain the distribution morphology characteristics that reflect the shape of the data distribution.

[0073] S2.2. Using correlation analysis, analyze the impact of preprocessed battery state data on battery performance and extract the factors affecting battery performance.

[0074] It should be noted that the factors affecting battery performance are extracted as follows:

[0075] The Pearson correlation coefficient between the preprocessed battery state data and another preprocessed battery state data is calculated using the following expression:

[0076]

[0077] Where, r xy It is the Pearson correlation coefficient, x z It is the value of the z-th preprocessed battery state data, y zIt is the z-th value of another preprocessed battery state data. It is all x z The mean of the values, It is all y z The mean of the data points, where n is the total number of observed data points (x0, x z and y z (combined into a single observation data point), where z is the index variable of the observation data point;

[0078] The calculated correlation coefficient r xy The value of x ranges from [-1, 1], evaluate x z and y z Linear correlation between them;

[0079] When r xy When x > 0, it means x z and y z Positive correlation;

[0080] When r xy When <0, it means x z and y z Negative correlation;

[0081] When r xy When x = 0, it means x z and y z There is no obvious linear relationship;

[0082] Based on Pearson correlation coefficient r xy The p-value is determined using the t-test method to judge x. z and y z The significance of the correlation is expressed as:

[0083]

[0084] Where t is the value used to determine the significance of the correlation, n is the total number of observed data points, and n-2 is the degree of freedom;

[0085] The p-value is determined using a t-distribution table. If the p-value is less than the significance level (usually 0.05), then x is considered normal. z and y z The correlation is significant;

[0086] It should be noted that the p-value is a probability value used to determine the significance of the hypothesis test result;

[0087] Significantly relevant variables are considered as factors influencing battery performance.

[0088] S2.3. The preprocessed battery state data is evaluated using statistical methods to obtain its reliability.

[0089] It should be noted that the following steps are taken to obtain credibility:

[0090] Based on Pearson correlation coefficient r xy To assess the stability of the correlation, calculate the 95% confidence interval of the correlation coefficient, expressed as:

[0091]

[0092] Where CI is the confidence interval, t α / 2,n-2 α is the critical value of the t-distribution, α is the significance level, and n-2 is the degrees of freedom;

[0093] When x z and y z When the correlation is significant and the confidence interval (CI) is narrow, the correlation between variables is considered to have high reliability.

[0094] S2.4. Based on influencing factors and confidence level, the weights of battery state features are dynamically adjusted, as expressed in the following expression:

[0095] Wi(s)=γ1×Ei(s)+γ2×Ri(s);

[0096] Where Wi(s) is the weight of the i-th battery state feature at time s after dynamic adjustment, Ei(s) represents the influencing factors of the i-th battery state feature at time s, Ri(s) represents the credibility of the i-th battery state feature at time s, γ1 is the weight coefficient of Ei(s), γ2 is the weight coefficient of Ri(s), s is the time index variable, and i is the battery state feature index variable.

[0097] S3. By applying physical constraints, the weights Wi(s) of the dynamically adjusted i-th battery state features at time s are fused to obtain a high-dimensional feature vector.

[0098] S3.1 Define physical constraint rules based on battery operating mechanism, operating conditions, safety thresholds and experimental data.

[0099] It should be noted that the battery operating mechanism, operating conditions, safety thresholds, and experimental data are derived from the battery manufacturer's technical specifications, industry standards, actual operating data, and laboratory test results.

[0100] It should also be noted that the specific physical constraint rules are as follows:

[0101] Temperature: The importance (weight) of temperature should be increased in high-rate discharge or extreme environments;

[0102] Voltage: The importance of voltage should be increased during battery fast charging;

[0103] Current: During steady-state operation, the current weight may decrease.

[0104] Specifically, this involves analyzing the inherent physical relationships between battery state data (such as voltage, current, and temperature) and their impact on battery performance by understanding the battery's operating mechanism; assessing the importance of each battery state data under different operating conditions (such as high-rate discharge, fast charging, and rest); setting physical limits for key parameters (such as temperature, voltage, and current) based on safety thresholds to avoid abnormal operation; and finally, through experimental data verification and summarization, establishing weight adjustment rules for each battery state data under different conditions to form a complete set of physical constraint rules.

[0105] S3.2, Define correction factors based on physical constraint rules.

[0106] It should be noted that statistical analysis methods are used to analyze these physical constraint rules, identify key factors affecting battery state characteristics, and set correction factors accordingly.

[0107] S3.3, Correct the dynamically adjusted weights using a correction factor.

[0108] It should be noted that the dynamically adjusted weights are corrected using a correction factor, expressed as follows:

[0109] Q i (s)=W i (s)×L;

[0110] Among them, Q i (s) is the corrected weight, and L is the correction factor.

[0111] S3.4. Use the sliding window method to fuse the corrected weights from the current time point and historical time points to obtain a high-dimensional feature vector. The expression is:

[0112]

[0113] Where V(s) is a high-dimensional feature vector, Q i (sk) is the weight of the i-th battery state feature after correction at time sk, X i (sk) is the i-th battery state feature at time sk, k is the index variable with time lag, and N is the total number of included time points.

[0114] S4. Construct a battery state prediction model based on a long short-term memory network model.

[0115] S4.1, Based on the Long Short-Term Memory Network model;

[0116] Arrange the high-dimensional historical feature vectors in chronological order and use the sliding window method to create the input time series;

[0117] The input layer of an LSTM model accepts a time series input.

[0118] By using an LSTM multilayer structure to capture dynamic relationships in time series and extract time-dependent features;

[0119] Fully connected layers map the output temporal dependency features to the target feature dimension;

[0120] A battery state prediction model was constructed.

[0121] It should be noted that the advantage of the Long Short-Term Memory (LSTM) network model as the base model lies in its ability to effectively capture long-term dependencies and dynamic changes in time series data. By processing high-dimensional historical feature vectors through a multi-layer structure, it extracts time-dependent features. The LSTM model is particularly suitable for processing data with time sequence, as it can remember past information and use it for future predictions, thereby improving the accuracy and robustness of battery state prediction.

[0122] S5. Based on high-dimensional feature vectors, obtain battery health values ​​through a battery state prediction model.

[0123] S5.1 Organize the high-dimensional feature vectors into a sliding window format according to the time order to form a time series input.

[0124] S5.2. By using a multi-layer structure to capture the dynamic relationship between short-term and long-term changes, the first layer LSTM extracts the low-level dynamic characteristics of the time series, and the second layer LSTM further extracts the time-dependent features.

[0125] S5.3 The time-dependent features of the LSTM output are passed to the fully connected layer to obtain the battery health value, expressed as:

[0126]

[0127] Where Y(s) is the battery health value at time s, σ is the activation function, H is the total number of neurons in the fully connected layer, and w j Q is the weight of the j-th fully connected neuron, F is the dimension of the high-dimensional feature vector, and Q is the weight of the j-th fully connected neuron. i (s) is the weight of the i-th battery state feature after correction at time s, X i (s) is the i-th battery state feature at time s, α is a parameter, and b j is the bias term of the j-th fully connected layer neuron, c is the constant term, i is the battery state feature index variable, and j is the index variable of the fully connected layer neuron.

[0128] It should be noted that the evaluation process of the expression is as follows:

[0129] For each input feature Qi (s) and X i (s), calculate its value after nonlinear transformation, sum these transformed values, and add the bias term b. j Then, activation is performed using the hyperbolic tangent function, and each activated result is multiplied by the corresponding weight w. j The results of all neurons are summed, and this summation is then passed through an activation function for nonlinear transformation. A constant term c is added to obtain the final output Y(s).

[0130] S6. Monitor battery health status in real time based on battery health values.

[0131] S6.1. Set a threshold T based on the average value of the battery health value.

[0132] S6.2. Compare the battery health value Y(s) with the threshold T to monitor the battery health status in real time;

[0133] When Y(s) > T, the battery is in good health and continues to operate normally.

[0134] When Y(s)≤T, the battery health is poor, and corresponding measures should be taken immediately.

[0135] It should be noted that the corresponding measures include reducing the load, adjusting operating conditions, and replacing the battery.

[0136] This embodiment also provides a hybrid energy storage battery status monitoring system based on big data, including: a data acquisition and preprocessing module, a feature generation module, a model building module, a health value calculation module, and a status monitoring module;

[0137] The data acquisition and preprocessing module is used to acquire battery status data and preprocess the battery status data.

[0138] The feature generation module is used to obtain high-dimensional feature vectors based on preprocessed battery state data by dynamically adjusting weights and fusing them.

[0139] The model building module is used to build a battery state prediction model based on the long short-term memory network model.

[0140] The health value calculation module is used to obtain the battery health value based on the high-dimensional feature vector and the battery state prediction model.

[0141] The status monitoring module is used to monitor the battery health status in real time based on the battery health value.

[0142] This embodiment also provides a computer device applicable to the hybrid energy storage battery status monitoring method based on big data, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the hybrid energy storage battery status monitoring method based on big data as proposed in the above embodiment.

[0143] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0144] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the method for monitoring the state of a hybrid energy storage battery based on big data as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0145] In summary, this invention solves the problem of inaccurate multidimensional feature analysis and fusion by dynamically adjusting weights and generating high-dimensional feature vectors. Furthermore, it constructs a battery state prediction model based on a Long Short-Term Memory (LSTM) network to deeply explore the dynamic changes in time series, significantly improving the accuracy of battery health value prediction. This enables real-time monitoring and fault warning of battery health status under complex operating conditions, effectively enhancing the safety, reliability, and operational management efficiency of hybrid energy storage systems.

[0146] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for monitoring the state of hybrid energy storage batteries based on big data, characterized in that: include, Collect battery status data and preprocess the battery status data; The battery status data includes electrical characteristic data, environmental parameters, and operating load information; The preprocessing includes outlier removal, missing value imputation, and normalization. Based on the preprocessed battery state data, a high-dimensional feature vector is obtained by dynamically adjusting weights and fusing the data. The specific steps are as follows. Battery state features are extracted from preprocessed battery state data using statistical analysis methods. Correlation analysis was used to analyze the impact of preprocessed battery state data on battery performance and to extract the factors affecting battery performance. The reliability of the preprocessed battery state data was evaluated using statistical methods. The weights of battery state features are dynamically adjusted based on influencing factors and reliability, as expressed by: ； in, It is the dynamically adjusted number 1 Individual battery state characteristics in time The weight, Indicates the first Individual battery state characteristics in time Influencing factors Indicates the first Individual battery state characteristics in time Credibility, yes The weighting coefficients, yes The weighting coefficients, It is a time index variable. It is a battery state characteristic index variable; Through physical constraints, the dynamically adjusted first... Individual battery state characteristics in time weight The features are fused to obtain a high-dimensional feature vector. A battery state prediction model is constructed based on a long short-term memory network model. Battery health values ​​are obtained through a battery state prediction model based on high-dimensional feature vectors. Based on battery health values, monitor battery health status in real time.

2. The method for monitoring the state of hybrid energy storage batteries based on big data as described in claim 1, characterized in that: Through physical constraints, the dynamically adjusted first... Individual battery state characteristics in time weight The following steps are involved in fusing the features to obtain a high-dimensional feature vector. Physical constraint rules are defined based on battery operating mechanisms, operating conditions, safety thresholds, and experimental data. Correction factors are defined based on physical constraint rules; The dynamically adjusted weights are corrected using a correction factor; The sliding window method is used to fuse the weights corrected for the current time point and historical time points to obtain a high-dimensional feature vector, expressed as follows: ； in, It is a high-dimensional feature vector. It is the first Individual battery state characteristics in time The corrected weights, It is the first In time Battery state characteristics at the location, It is a time-lagging index variable. This represents the total number of time points included.

3. The method for monitoring the state of hybrid energy storage batteries based on big data as described in claim 1, characterized in that: The battery state prediction model based on the Long Short-Term Memory (LSTM) network model is constructed using the following specific steps. The model is based on the Long Short-Term Memory (LSTM) network model. Arrange the high-dimensional historical feature vectors in chronological order and use the sliding window method to create the input time series. The input layer of an LSTM model accepts a time series input. By using an LSTM multilayer structure to capture dynamic relationships in time series and extract time-dependent features; Fully connected layers map the output temporal dependency features to the target feature dimension; A battery state prediction model was constructed.

4. The method for monitoring the state of hybrid energy storage batteries based on big data as described in claim 1, characterized in that: The battery health value is obtained based on a high-dimensional feature vector and a battery state prediction model. The specific steps are as follows: By using a multi-layer structure to capture short-term and long-term dynamic relationships, the first LSTM layer extracts the low-level dynamic characteristics of the time series, and the second LSTM layer further extracts the time-dependent features. The time-dependent features of the LSTM output are passed to a fully connected layer to obtain battery health values, expressed as: ； in, It is time Battery health value, It is an activation function. It is the total number of neurons in the fully connected layer. It is the first The weights of neurons in a fully connected layer It is the dimension number of the high-dimensional feature vector. It is the first Individual battery state characteristics in time The corrected weights, It is the first In time Battery state characteristics at the location, It is a parameter. It is the first Bias terms for neurons in a fully connected layer, It is a constant term. It is a battery state characteristic index variable. It is the index variable of the fully connected layer neurons.

5. The method for monitoring the state of hybrid energy storage batteries based on big data as described in claim 4, characterized in that: The process of monitoring battery health status in real time based on battery health values ​​involves the following steps. A threshold is set based on the average battery health value. ; Battery health value With threshold Compare and monitor battery health status in real time; when At that time, the battery was in good health and continued to operate normally; when If the battery is in poor health, take appropriate measures immediately.

6. A hybrid energy storage battery status monitoring system based on big data, based on the hybrid energy storage battery status monitoring method based on big data as described in any one of claims 1 to 5, characterized in that: It includes a data acquisition and preprocessing module, a feature generation module, a model building module, a health value calculation module, and a status monitoring module; The data acquisition and preprocessing module is used to acquire battery status data and preprocess the battery status data. The feature generation module is used to obtain high-dimensional feature vectors based on preprocessed battery state data by dynamically adjusting weights and fusing them. The model building module is used to build a battery state prediction model based on the long short-term memory network model. The health value calculation module is used to obtain the battery health value based on the high-dimensional feature vector and the battery state prediction model. The status monitoring module is used to monitor the battery health status in real time based on the battery health value.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the big data-based hybrid energy storage battery status monitoring method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the big data-based hybrid energy storage battery status monitoring method as described in any one of claims 1 to 5.

Images