A method and system for monitoring the performance of energy storage batteries based on a big data model

Abstract

The present invention discloses a method and system for monitoring the performance of energy storage batteries based on a big data model. The method includes: collecting real-time data of various operating parameters of the energy storage battery; analyzing the change trend of the battery performance, calculating the trend factor of the historical data of the energy storage battery for identifying the long-term change trend of the battery performance; using a big data model based on a neural network to model the real-time data and the trend factor to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery; predicting the battery performance according to the performance degradation prediction factor to generate a corresponding performance evaluation score for realizing the performance monitoring of the energy storage battery. By using the embodiments of the present invention, it is possible to collect various operating parameters in real time, combine with the trend factor of historical data, and use advanced machine learning technology for modeling and prediction, providing an innovative solution for the efficient management and maintenance of energy storage batteries.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage, and particularly relates to a method and system for monitoring the performance of energy storage batteries based on a big data model. Background Art

[0002] With the rapid development of renewable energy, energy storage batteries are increasingly widely used in fields such as power systems, smart grids, and electric vehicles. The performance of energy storage batteries directly affects the efficiency, service life, and safety of energy storage. Therefore, it is particularly important to effectively monitor and manage the performance of energy storage batteries. Traditional methods for monitoring the performance of energy storage batteries mainly rely on manual inspections and simple parameter recordings, making it difficult to achieve real-time monitoring of the battery state. These methods may lead to data lags or omissions, thus failing to timely reflect the true state of the battery. Summary of the Invention

[0003] The object of the present invention is to provide a method and system for monitoring the performance of energy storage batteries based on a big data model to address the deficiencies in the prior art. It can collect various operating parameters in real time, combine the trend factors of historical data, and use advanced machine learning techniques for modeling and prediction, providing an innovative solution for the efficient management and maintenance of energy storage batteries.

[0004] An embodiment of the present application provides a method for monitoring the performance of energy storage batteries based on a big data model, the method comprising:

[0005] Collecting real-time data of various operating parameters of the energy storage battery, wherein the operating parameters include: voltage, current, temperature, internal resistance, and charge and discharge state;

[0006] Analyzing the change trend of battery performance and calculating the trend factor of the historical data of the energy storage battery for identifying the long-term change trend of battery performance;

[0007] Using a big data model based on a neural network to model the real-time data and the trend factor to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery;

[0008] Predicting the battery performance according to the performance degradation prediction factor to generate a corresponding performance evaluation score to achieve the performance monitoring of the energy storage battery.

[0009] Optionally, the analyzing the change trend of battery performance and calculating the trend factor of the historical data of the energy storage battery includes:

[0010] Determining the size of the analysis time window and extracting historical data of voltage, current, and internal resistance covering the analysis time window from the database;

[0011] Calculate the average power output by the battery within the analysis time window, and determine an internal resistance correction value for correcting the power loss caused by the internal resistance;

[0012] Calculate the trend factor of the historical data of the energy storage battery according to the average power and the internal resistance correction value.

[0013] Optionally, using a big data model based on a neural network to model the real-time data and the trend factor to generate a performance degradation prediction factor, including:

[0014] Use an adaptive recurrent neural network to train and generate a big data model for the performance degradation prediction factor. Among them, the model generates the performance degradation prediction factor by learning the weight parameters corresponding to the preset first non-linear characteristic function and the second non-linear characteristic function. And the first non-linear characteristic function is used to comprehensively evaluate the overall impact of battery voltage, current, temperature and trend factor on battery performance, and the second non-linear characteristic function is used to evaluate the degradation impact of charge and discharge state and internal resistance on the battery.

[0015] Optionally, predicting the battery performance according to the performance degradation prediction factor to generate a corresponding performance evaluation score, including:

[0016] Calculate the average temperature and the temperature correction factor in the real-time data within the acquisition time period;

[0017] Calculate the performance evaluation score for predicting the future battery performance according to the performance degradation prediction factor, the average temperature and the temperature correction factor.

[0018] Another embodiment of the present application provides an energy storage battery performance monitoring system based on a big data model, and the system includes:

[0019] An acquisition module for acquiring real-time data of various operating parameters of the energy storage battery, where the operating parameters include: voltage, current, temperature, internal resistance and charge and discharge state;

[0020] An analysis module for analyzing the change trend of the battery performance and calculating the trend factor of the historical data of the energy storage battery for identifying the long-term change trend of the battery performance;

[0021] A generation module for using a big data model based on a neural network to model the real-time data and the trend factor to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery;

[0022] A monitoring module for predicting the battery performance according to the performance degradation prediction factor to generate a corresponding performance evaluation score to realize the performance monitoring of the energy storage battery.

[0023] Another embodiment of the present application provides a storage medium, in which a computer program is stored, and the computer program is configured to execute the method described in any one of the above when running.

[0024] Another embodiment of the present application provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method described in any one of the above.

[0025] Compared with the prior art, a method for monitoring the performance of an energy storage battery based on a big data model provided by the present invention collects real-time data of various operating parameters of the energy storage battery; analyzes the change trend of the battery performance, calculates the trend factor of the historical data of the energy storage battery for identifying the long-term change trend of the battery performance; uses a big data model based on a neural network to model the real-time data and the trend factor to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery; predicts the battery performance according to the performance degradation prediction factor to generate a corresponding performance evaluation score, so as to realize the performance monitoring of the energy storage battery. Thus, by collecting various operating parameters in real time, combining with the trend factor of historical data, and using advanced machine learning technology for modeling and prediction, an innovative solution is provided for the efficient management and maintenance of the energy storage battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a hardware structure block diagram of a computer terminal for a method for monitoring the performance of an energy storage battery based on a big data model provided by an embodiment of the present invention;

[0027] Figure 2 It is a schematic flowchart of a method for monitoring the performance of an energy storage battery based on a big data model provided by an embodiment of the present invention;

[0028] Figure 3 It is a schematic structural diagram of a system for monitoring the performance of an energy storage battery based on a big data model provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0030] An embodiment of the present invention first provides a method for monitoring the performance of an energy storage battery based on a big data model. This method can be applied to an electronic device, such as a computer terminal, specifically, an ordinary computer, etc.

[0031] The following takes running on a computer terminal as an example to describe it in detail. Figure 1The following is a hardware block diagram of a computer terminal for a method of monitoring the performance of energy storage batteries based on a big data model provided by an embodiment of the present invention. As Figure 1 shown, the computer terminal may include one or more ( Figure 1 only one is shown in Figure 1 ) processors 102 (the processors 102 may include, but are not limited to, processing devices such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the above computer terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown in Figure 1 is only schematic and does not limit the structure of the above computer terminal. For example, the computer terminal may further include more or fewer components than

[0032] shown in

[0033] or have a different configuration from that shown in

[0034] Refer to Figure 2 , an embodiment of the present invention provides a method for monitoring the performance of energy storage batteries based on a big data model, which may include the following steps:

[0035] S201, collect real-time data of various operating parameters of the energy storage battery, where the operating parameters include: voltage, current, temperature, internal resistance, and charge and discharge state;

[0036] In the energy storage battery performance monitoring method of the present invention, the collection of real-time data is one of the basic steps. This process involves the monitoring of various key operating parameters, mainly including the following aspects:

[0037] Voltage (V): Voltage is an important indicator reflecting the output ability of the energy storage battery, usually measured in volts (V). The voltage level of the battery can reflect its remaining energy and charge state. Monitoring voltage changes can help identify the charge and discharge conditions of the battery, the risks of overcharging or over-discharging, and voltage imbalance between components. Therefore, voltage monitoring is crucial for ensuring the safe and efficient operation of the energy storage system.

[0038] Current (I): Current is the rate of electric charge flowing through the battery, measured in amperes (A). Changes in current directly affect the charge and discharge process of the battery. Real-time monitoring of current can effectively evaluate the charging efficiency and discharge capacity of the battery, and at the same time can also reflect the load condition of the battery and the dynamic changes in energy use. This is of great significance for improving the utilization efficiency of the battery and extending its service life.

[0039] Temperature (T): Temperature is one of the environmental factors affecting battery performance, usually expressed in degrees Celsius (°C). The operating temperature of the energy storage battery is closely related to its chemical reaction rate and internal resistance. Temperature monitoring can help identify thermal management problems of the battery, such as the adverse effects of overheating or low temperature on battery performance. This is crucial for ensuring the safety and stability of the battery.

[0040] Internal resistance (R): Internal resistance is the resistance to the flow of current inside the battery, generally measured in milliohms (mΩ). The magnitude of the internal resistance reflects the health status and performance degradation of the battery. Monitoring changes in internal resistance helps to evaluate the charge and discharge efficiency and safety of the battery. High internal resistance may indicate battery aging or a risk of failure.

[0041] Charge and discharge state (SOC): The charge and discharge state (State of Charge, SOC) represents the percentage of the current battery charge relative to its rated capacity, usually expressed in %. Monitoring of SOC can provide real-time information on battery energy utilization, provide a basis for energy management and optimization control, and ensure that the energy storage system operates in the best working state.

[0042] In the present invention, the following specific implementation schemes can be adopted for the collection of real-time data of various operating parameters of the energy storage battery:

[0043] Sensor Deployment: Install a variety of sensors at key positions of the energy storage battery. These sensors can include: Voltage sensors: used to monitor the output voltage of the battery in real time; Current sensors: used to measure the charging and discharging current flowing through the battery; Temperature sensors: monitor the operating temperature of the battery to ensure it operates within a safe range; Internal resistance sensors: used to periodically measure and evaluate changes in the internal resistance of the battery; SOC sensors: calculate and feedback the charging and discharging state of the battery in real time through the battery management system (BMS). Intelligent data acquisition modules such as embedded systems or PLCs (Programmable Logic Controllers) can be used to aggregate and process the data collected by the above sensors. The real-time monitoring system can transmit data to the battery management system through the CAN bus or RS-485 communication protocol to achieve real-time data update and remote monitoring. Store the collected real-time data in a database for subsequent analysis. The data storage system needs to be efficient and secure to prevent data loss and damage. Preprocess the collected raw data, including denoising, filtering, and normalization, to improve the accuracy and reliability of the data.

[0044] Through the above implementation methods, it is possible to effectively collect real-time data of various operating parameters of the energy storage battery, providing a solid data foundation for subsequent performance monitoring and analysis. This process not only improves the accuracy of energy storage battery monitoring but also lays a foundation for battery state evaluation and performance prediction, thereby providing support for realizing safe and reliable energy management.

[0045] S202, Analyze the change trend of battery performance, calculate the trend factor of the historical data of the energy storage battery to identify the long-term change trend of battery performance;

[0046] In the performance monitoring of energy storage batteries, analyzing the change trend of battery performance is a key step in evaluating battery health status and expected life. By comparing real-time data with historical data, it is possible to identify performance fluctuations of the battery at different time periods and their influencing factors. This process involves monitoring and statistical analysis of multiple operating parameters such as voltage, current, and internal resistance to generate a trend factor (Trend Factor, TF). The trend factor not only reflects the change of battery performance over time but also reveals potential degradation patterns, helping users take maintenance measures in a timely manner to ensure the safe and efficient operation of the battery system.

[0047] The calculation and analysis of the trend factor make the management of energy storage battery performance more scientific and systematic. By identifying the long-term change trend of battery performance, managers can formulate appropriate strategies based on data insights to optimize battery use and maintenance. In addition, the trend factor also provides important basic information for future battery performance prediction, helping to determine whether the battery needs to be replaced or repaired, ultimately enhancing the economy and reliability of the energy storage system.

[0048] Specifically, the size of the analysis time window can be determined, and historical data of voltage, current, and internal resistance covering the analysis time window can be extracted from the database.

[0049] The size of the analysis time window determines the scope and granularity of data analysis. Usually, an appropriate time window needs to be set according to the specific application scenario and the battery usage cycle. For example, daily, weekly, or monthly. A reasonable time window can ensure capturing the dynamic changes in battery performance while avoiding inaccurate analysis due to overly sparse data. In practical applications, a standard time window, such as 7 days, can be set and adjusted and optimized in combination with the actual collected data.

[0050] Extract the battery operation data within the specified time window from the database. These data include parameters such as voltage, current, and internal resistance, ensuring that they can truly reflect the working conditions of the battery. By extracting relevant data, subsequent trend calculations and performance analysis can be effectively carried out, which provides the necessary data basis for identifying battery degradation. SQL queries can be used to extract relevant data within the specified time period from the historical data table and organize them into a structured data format for further analysis.

[0051] Calculate the average power output by the battery within the analysis time window and determine the internal resistance correction value for correcting the power loss caused by the internal resistance.

[0052] The average power is the average value of the power output by the battery within this time window, and the calculation formula is power = voltage × current. By calculating the average power, the energy output level of the battery within this time period can be understood. The calculation of the average power helps to evaluate the working efficiency of the battery and can reflect the performance of the battery under different conditions.

[0053] The internal resistance correction value is used to compensate for the power loss caused by the internal resistance when calculating the total output power. The internal resistance will cause energy loss, so correction is required when evaluating battery performance. By correcting the power loss caused by the internal resistance, the actual performance of the battery can be more truly reflected, and the accuracy of the analysis can be improved.

[0054] Calculate the trend factor of the historical data of the energy storage battery based on the average power and the internal resistance correction value.

[0055] The trend factor (TF) is calculated by correcting the average power and reflects the operating efficiency and performance changes of the battery within a certain time window. The calculation of the trend factor helps to judge the long-term health status and performance degradation rate of the battery and provides a historical basis for management and decision-making. For example, one kind of trend factor can be:

[0056] is the trend factor, and the design of the trend factor aims to quantify the comprehensive performance of the battery within a specific time window, facilitating long-term monitoring and evaluation of the battery's working efficiency and health status. By combining multiple core parameters such as voltage, current, and internal resistance, the trend factor provides a comprehensive quantitative indicator for the change in battery performance. Assuming the TF calculation result is 0.85, it indicates that the battery's performance is relatively good during this time period.

[0057] is the voltage of the i-th data point within the analysis time window, is the current of the i-th data point within the analysis time window, is the power output by the battery within the analysis time window, is the average power, is the resistance of the i-th data point within the analysis time window, is the internal resistance correction value used to correct the power loss caused by the internal resistance, and n is the number of data points within the analysis time window, is the correction coefficient related to the temperature of the i-th data point within the analysis time window, which is used to compensate for the influence of temperature changes on the internal resistance and power calculation, ensuring the accuracy of data analysis. For example, one correction coefficient can be:

[0058] The design of this formula aims to correct the internal resistance and battery performance through the environmental impact under different temperature conditions. In practical applications, the internal resistance and performance of the battery often fluctuate with temperature changes. Therefore, adopting such a correction method can more accurately reflect the true performance of the battery at a specific temperature. Through this formula, the environmental temperature factor can be incorporated into the calculation of the trend factor, thereby improving the accuracy and reliability of battery performance monitoring.

[0059] Among them, is the basic correction coefficient, which provides a baseline to characterize the basic performance of the battery in a standard or reference environment. It can be based on data or empirical values provided by the battery manufacturer. For example, can be set to 1.00, which usually represents the basic performance at the reference temperature. is the temperature sensitivity coefficient, which reflects the degree of influence of temperature changes on the correction coefficient and can be determined based on historical data. It can quantify the degree of influence of temperature changes on battery performance. For example, when beta takes a value of 0.02, it means that for every 1°C increase, the correction coefficient will increase by 0.02. is the temperature of the i-th data point within the analysis time window, is the first reference temperature, which is usually set to a fixed temperature value to represent the standard test temperature of the battery performance, usually the temperature in the laboratory environment. A commonly used first reference temperature can be set to 20°C.

[0060] S203. Use a big data model based on a neural network to model the real-time data and the trend factor to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery.

[0061] In the method of the present invention, using a big data model based on a neural network to model real-time data and trend factors, the main purpose is to generate a performance degradation prediction factor. This process generally involves taking various real-time parameters of the battery (such as voltage, current, temperature, etc.) and the calculated trend factors as inputs, and using an adaptive recurrent neural network (RNN) to train the model to learn the complex non-linear relationship between these inputs and the battery performance. In this way, the model can extract the potential patterns of battery performance degradation and generate a prediction factor that can be used to evaluate the degradation speed and state of the battery, thereby achieving a comprehensive assessment of the battery health status.

[0062] The significance of this step is that by introducing the neural network technology of deep learning, the process of energy storage battery performance monitoring becomes more intelligent and accurate. Compared with traditional linear regression or simple statistical methods, neural networks can process more complex input features and multi-dimensional data, thereby improving the prediction accuracy of battery performance degradation. This method can not only timely detect potential faults of the battery, but also provide a scientific basis for the maintenance and management of the battery through the continuous update of the performance evaluation factor, improving the reliability and economy of the energy storage system.

[0063] Specifically, a big data model for generating a performance degradation prediction factor can be trained using an adaptive recurrent neural network. Among them, the model generates a performance degradation prediction factor by learning the weight parameters corresponding to a preset first non-linear feature function and a second non-linear feature function. And the first non-linear feature function is used to comprehensively evaluate the overall impact of battery voltage, current, temperature and trend factor on battery performance, and the second non-linear feature function is used to evaluate the degradation impact of charge and discharge state and internal resistance on the battery.

[0064] Exemplarily, a performance degradation prediction factor can be:

[0065] , is the performance degradation prediction factor, reflecting the degradation degree of the battery. The higher the value, the worse the battery performance. For example, if DF is 0.75, it indicates that there is a certain degree of degradation in the health state of the battery. is the first non-linear feature function, is the second non-linear feature function, , They are the corresponding weight parameters obtained through learning by the big data model. These two parameters are obtained through model training and reflect the relative importance of different input features to the degree of battery performance degradation. For example, beta_1 = 0.6 and beta_2 = 0.4, indicating that voltage, current, and temperature have a greater impact on battery degradation.

[0066] Exemplarily, a first non-linear feature function can be:

[0067] Among them, a, b, and c are the corresponding first adjustment parameters. a weighs the impact of the product of voltage and current on battery performance. For example, a = 0.1; b reflects the impact of temperature on battery performance. For example, b = 0.05; c is used to adjust the impact degree of the trend factor on battery performance. For example, c = 0.2; is the average voltage in the real-time data within the acquisition time period, is the average current in the real-time data within the acquisition time period, is the average temperature in the real-time data within the acquisition time period.

[0068] Exemplarily, a second non-linear feature function can be:

[0069] Among them, d and e are the second adjustment parameters. d represents the positive impact degree of the charge and discharge state on battery performance. For example, d = 0.3; e represents the negative impact degree of the internal resistance on battery performance. For example, e = 0.4; is the average charge and discharge state in the real-time data within the acquisition time period, is the average resistance in the real-time data within the acquisition time period.

[0070] Through the above design, integrating the performance degradation prediction factor into the big data model can effectively utilize the capabilities of machine learning, enabling the model to automatically learn and optimize the weights of each parameter, and improving the accuracy and reliability of battery performance monitoring. This method combines the empirical knowledge of traditional battery monitoring with modern big data technology, and can better adapt to the complexity and variability of battery performance.

[0071] S204, according to the performance degradation prediction factor, predict the battery performance and generate a corresponding performance evaluation score to achieve the performance monitoring of the energy storage battery.

[0072] In the energy storage battery performance monitoring method, the core of the method is to predict the performance of the battery using the performance degradation prediction factor (DF). By analyzing the real-time data and trend factors, the generated performance evaluation score will reflect the health of the battery in the future. This process involves a comprehensive analysis of multiple operating parameters of the battery, including voltage, current, temperature, etc., to ensure the accuracy and real-time nature of the prediction.

[0073] The implementation of this step makes the performance monitoring of energy storage batteries more scientific and accurate. By generating corresponding performance evaluation scores, users can timely understand the health status of the battery, foresee possible failures or performance degradation, and take preventive measures. This not only helps to extend the service life of the battery, but also optimizes the battery operation strategy, improves the overall energy efficiency and reliability of the battery system, and reduces maintenance costs and risks of downstream applications.

[0074] Specifically, the temperature average value and the temperature correction factor in the real-time data within the acquisition time period can be calculated;

[0075] In this step, the battery temperature data collected within a specific period of time must first be averaged to obtain the average temperature value. Subsequently, the temperature correction factor is calculated using the average value and other related parameters to correct the battery performance changes caused by temperature fluctuations. This correction factor will play a key role in subsequent performance evaluation.

[0076] The impact of temperature on battery performance is significant, especially under different environmental conditions of charge and discharge. By calculating the temperature average and temperature correction factor, it is possible to ensure that the temperature factor is taken into account during performance evaluation, thereby improving the accuracy and reliability of the prediction results. This provides a scientific basis for the battery management system and helps optimize the battery's use and maintenance strategy.

[0077] Exemplarily, a temperature correction factor may be:

[0078] This formula provides a quantitative description of the effect of temperature on battery performance, which can be used to effectively correct the temperature factor in performance evaluation.

[0079] in, is the second reference temperature, which is used as the reference point for temperature correction, for example, 25°C. is the standard temperature difference, which affects the calculation accuracy of the temperature correction factor, for example, 10°C; k is the temperature influence coefficient, which adjusts the impact of temperature changes on battery performance, for example, k = 0.1.

[0080] A performance evaluation score for predicting future battery performance is calculated based on the performance degradation prediction factor, the temperature average value, and the temperature correction factor.

[0081] In this step, combining the performance degradation prediction factor and the temperature correction factor calculated previously, an evaluation score of the future battery performance is generated. This score reflects the expected performance of the battery under specific temperature conditions by subtracting the influence of the temperature correction factor from the performance degradation prediction factor.

[0082] The calculated performance evaluation score is an important indicator for battery performance monitoring and can provide an intuitive basis for judgment for users. By monitoring this score, changes in battery performance can be detected in a timely manner, and then the operation strategy can be adjusted and necessary maintenance measures can be taken. This process significantly improves the scientificity and effectiveness of battery management.

[0083] Exemplarily, a kind of performance evaluation score can be:

[0084] This formula is used to comprehensively consider the influence of the performance degradation prediction factor and temperature on battery performance. By introducing the correction factor, the prediction result is made closer to the actual situation.

[0085] It can be seen that real-time data of various operating parameters of the energy storage battery are collected; the change trend of battery performance is analyzed, and the trend factor of the historical data of the energy storage battery is calculated to identify the long-term change trend of battery performance; a big data model based on a neural network is used to model the real-time data and the trend factor to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery; according to the performance degradation prediction factor, the battery performance is predicted to generate a corresponding performance evaluation score to realize the performance monitoring of the energy storage battery. Thus, by collecting various operating parameters in real time and combining with the trend factor of historical data, advanced machine learning technology is used for modeling and prediction, providing an innovative solution for the efficient management and maintenance of the energy storage battery.

[0086] Another embodiment of the present invention provides an energy storage battery performance monitoring system based on a big data model. Refer to Figure 3 , the system may include:

[0087] A collection module 301 for collecting real-time data of various operating parameters of the energy storage battery, wherein the operating parameters include: voltage, current, temperature, internal resistance, and charge and discharge state;

[0088] An analysis module 302 for analyzing the change trend of battery performance and calculating the trend factor of the historical data of the energy storage battery to identify the long-term change trend of battery performance;

[0089] A generation module 303, configured to model the real-time data and the trend factor by using a big data model based on a neural network, so as to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery;

[0090] A monitoring module 304, configured to predict the battery performance according to the performance degradation prediction factor, and generate a corresponding performance evaluation score, so as to implement the performance monitoring of the energy storage battery.

[0091] It can be seen that real-time data of various operating parameters of the energy storage battery are collected; the change trend of the battery performance is analyzed, and the trend factor of the historical data of the energy storage battery is calculated to identify the long-term change trend of the battery performance; the real-time data and the trend factor are modeled by using a big data model based on a neural network to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery; the battery performance is predicted according to the performance degradation prediction factor, and a corresponding performance evaluation score is generated to implement the performance monitoring of the energy storage battery. Therefore, by collecting various operating parameters in real time and combining the trend factor of the historical data, advanced machine learning technologies are used for modeling and prediction, providing an innovative solution for the efficient management and maintenance of the energy storage battery.

[0092] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, and the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0093] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for executing the following steps:

[0094] S201, collecting real-time data of various operating parameters of the energy storage battery, where the operating parameters include: voltage, current, temperature, internal resistance, and charge and discharge state;

[0095] S202, analyzing the change trend of the battery performance, and calculating the trend factor of the historical data of the energy storage battery to identify the long-term change trend of the battery performance;

[0096] S203, using a big data model based on a neural network to model the real-time data and the trend factor, so as to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery;

[0097] S204, predicting the battery performance according to the performance degradation prediction factor, and generating a corresponding performance evaluation score to implement the performance monitoring of the energy storage battery.

[0098] It can be seen that real-time data of various operating parameters of the energy storage battery are collected; the changing trend of the battery performance is analyzed, and the trend factor of the historical data of the energy storage battery is calculated to identify the long-term changing trend of the battery performance; a big data model based on a neural network is used to model the real-time data and the trend factor to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery; according to the performance degradation prediction factor, the battery performance is predicted to generate a corresponding performance evaluation score, so as to realize the performance monitoring of the energy storage battery. Therefore, by collecting various operating parameters in real time, combining with the trend factor of historical data, and using advanced machine learning technology for modeling and prediction, an innovative solution can be provided for the efficient management and maintenance of the energy storage battery.

[0099] An embodiment of the present invention further provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0100] Specifically, the above electronic device may further include a transmission device and an input / output device. Among them, the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0101] Specifically, in this embodiment, the above processor may be configured to execute the following steps through a computer program:

[0102] S201, collect real-time data of various operating parameters of the energy storage battery, where the operating parameters include: voltage, current, temperature, internal resistance, and charge and discharge state;

[0103] S202, analyze the changing trend of the battery performance, calculate the trend factor of the historical data of the energy storage battery to identify the long-term changing trend of the battery performance;

[0104] S203, use a big data model based on a neural network to model the real-time data and the trend factor to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery;

[0105] S204, predict the battery performance according to the performance degradation prediction factor to generate a corresponding performance evaluation score to realize the performance monitoring of the energy storage battery.

[0106] It can be seen that real-time data of various operating parameters of the energy storage battery is collected; the change trend of the battery performance is analyzed, and the trend factor of the historical data of the energy storage battery is calculated to identify the long-term change trend of the battery performance; a big data model based on a neural network is used to model the real-time data and the trend factor to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery; according to the performance degradation prediction factor, the battery performance is predicted to generate a corresponding performance evaluation score, so as to realize the performance monitoring of the energy storage battery. Therefore, by collecting various operating parameters in real time, combining with the trend factor of historical data, and using advanced machine learning technology for modeling and prediction, an innovative solution can be provided for the efficient management and maintenance of the energy storage battery.

[0107] The structure, features and effects of the present invention have been described in detail based on the embodiments shown in the drawings. The above is only the preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or equivalent embodiments modified into equivalent changes, should still be within the protection scope of the present invention as long as they do not exceed the spirit covered by the specification and the drawings.

Claims

1. A method for monitoring the performance of energy storage batteries based on a big data model, characterized in that, The method includes: Collecting real-time data of multiple operating parameters of the energy storage battery, where the operating parameters include: voltage, current, temperature, internal resistance, and charge / discharge state; Analyzing the change trend of battery performance and calculating the trend factor of the historical data of the energy storage battery for identifying the long-term change trend of battery performance; The analyzing the change trend of battery performance and calculating the trend factor of the historical data of the energy storage battery includes: Determining the size of the analysis time window and extracting the historical data of voltage, current, and internal resistance covering the analysis time window from the database; Calculating the average power output by the battery within the analysis time window and determining the internal resistance correction value for correcting the power loss caused by the internal resistance; Calculating the trend factor of the historical data of the energy storage battery according to the average power and the internal resistance correction value; Using a big data model based on a neural network to model the real-time data and the trend factor to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery; The using a big data model based on a neural network to model the real-time data and the trend factor to generate a performance degradation prediction factor includes: Using an adaptive recurrent neural network to train a big data model for generating a performance degradation prediction factor, where the model generates a performance degradation prediction factor by learning the weight parameters corresponding to a preset first non-linear characteristic function and a second non-linear characteristic function, and the first non-linear characteristic function is used to comprehensively evaluate the overall influence of battery voltage, current, temperature, and trend factor on battery performance, and the second non-linear characteristic function is used to evaluate the degradation influence of charge / discharge state and internal resistance on the battery; Predicting the battery performance according to the performance degradation prediction factor and generating a corresponding performance evaluation score to achieve the performance monitoring of the energy storage battery.

2. The method according to claim 1, wherein The predicting the battery performance according to the performance degradation prediction factor and generating a corresponding performance evaluation score includes: Calculating the average temperature and the temperature correction factor in the real-time data within the acquisition time period; Calculating the performance evaluation score for predicting the future battery performance according to the performance degradation prediction factor, the average temperature, and the temperature correction factor.

3. A performance monitoring system for energy storage batteries based on a big data model, characterized in that, The system includes: A collection module for collecting real-time data of multiple operating parameters of the energy storage battery, where the operating parameters include: voltage, current, temperature, internal resistance, and charge / discharge state; An analysis module for analyzing the change trend of battery performance and calculating the trend factor of the historical data of the energy storage battery for identifying the long-term change trend of battery performance; The analyzing the change trend of battery performance and calculating the trend factor of the historical data of the energy storage battery includes: Determining the size of the analysis time window and extracting the historical data of voltage, current, and internal resistance covering the analysis time window from the database; Calculating the average power output by the battery within the analysis time window and determining the internal resistance correction value for correcting the power loss caused by the internal resistance; Calculating the trend factor of the historical data of the energy storage battery according to the average power and the internal resistance correction value; A generation module, configured to model the real-time data and the trend factor by using a big data model based on a neural network, so as to generate a performance degradation prediction factor for quantitatively evaluating the degradation speed and state of the battery; the modeling of the real-time data and the trend factor by using the big data model based on the neural network to generate the performance degradation prediction factor includes: Training a big data model for generating a performance degradation prediction factor by using an adaptive recurrent neural network, wherein the model generates a performance degradation prediction factor by learning weight parameters corresponding to a preset first non-linear feature function and a second non-linear feature function, and the first non-linear feature function is used for comprehensively evaluating the overall influence of battery voltage, current, temperature and trend factor on battery performance, and the second non-linear feature function is used for evaluating the degradation influence of charge and discharge state and internal resistance on the battery; A monitoring module, configured to predict the battery performance according to the performance degradation prediction factor and generate a corresponding performance evaluation score, so as to implement performance monitoring of the energy storage battery.

4. The system according to claim 3, characterized in that, The monitoring module is specifically configured to: Calculate the average temperature and the temperature correction factor in the real-time data within the acquisition time period; Calculate a performance evaluation score for predicting the future battery performance according to the performance degradation prediction factor, the average temperature and the temperature correction factor.

5. A storage medium, characterized in that, A computer program is stored in the storage medium, wherein the computer program is set to execute the method according to any one of claims 1-2 when running.

6. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is set to run the computer program to execute the method according to any one of claims 1-2.

Images