Energy storage system health monitoring method based on big data analysis

By conducting real-time monitoring and big data analysis of energy storage devices, a neural network model is constructed to assess the health status of energy storage systems. This solves the problem of difficulty in monitoring the health status of energy storage systems in existing technologies, and enables efficient and flexible equipment detection and maintenance.

CN119026056APending Publication Date: 2024-11-26NANJING APAITEK TECH

Patent Information

Application Number
CN202411179780.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

Existing technologies are insufficient for effectively monitoring and assessing the health status of energy storage systems, which affects their performance and lifespan.

Method used

By real-time monitoring of energy storage devices, extracting voltage, current, and temperature data, constructing a three-layer neural network model for correlation analysis, combining sliding window technology to assess device health status, and utilizing big data analysis for orderly maintenance.

Benefits of technology

It enables efficient, flexible, and safe monitoring of the health status of energy storage systems, allowing for timely identification of equipment faults and preventative maintenance, thereby extending equipment lifespan.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026056A_ABST
    Figure CN119026056A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of energy storage management, in particular to an energy storage system health monitoring method based on big data analysis, and the method comprises the steps: carrying out the real-time monitoring of energy storage equipment, and extracting three real-time operation data with an incidence relation, the three real-time operation data being voltage data, current data and temperature data; performing correlation degree analysis on the extracted three items of real-time operation data, and judging whether the correlation degree among the three items of real-time operation data meets a preset correlation degree or not; and importing the three items of real-time operation data into the health state evaluation model to perform energy storage system health evaluation, and performing ordered maintenance on the energy storage system according to an output evaluation result.
Need to check novelty before this filing date? Find Prior Art

Description

Background Art

[0002] With the rapid development of renewable energy, energy storage systems play a key role in balancing energy supply and demand and improving grid stability. However, the health status of energy storage systems directly affects their performance and lifespan, so effective health monitoring and prediction of energy storage systems is particularly important. Energy storage system health monitoring methods based on big data analysis are an important research direction in the current field of energy management. With the widespread application of energy storage systems, the monitoring and evaluation of their health status has become particularly important. Methods based on big data analysis can process and analyze a large amount of energy storage system operation data to provide accurate health status assessment and prediction. Summary of the invention

[0003] The main purpose of the present invention is to provide a method for monitoring the health of an energy storage system based on big data analysis, so as to effectively solve the above-mentioned problems mentioned in the background technology.

[0004] The technical solution of the present invention is as follows:

[0005] A method for monitoring the health of an energy storage system based on big data analysis is proposed. The method includes the following steps:

[0006] S1. Monitor the energy storage device in real time and extract three items of real-time operation data having a correlation relationship, wherein the three items of real-time operation data are voltage data, current data, and temperature data;

[0007] S2, performing correlation analysis on the three extracted real-time operation data to determine whether the correlation between the three real-time operation data meets the preset correlation. If not, it is determined that the energy storage device is faulty. If it is satisfied, proceed to step S3;

[0008] S3. Import the three real-time operation data into the health status assessment model to conduct a health assessment of the energy storage system, and perform orderly maintenance on the energy storage system based on the output assessment results.

[0009] A further improvement of the present invention is that the correlation analysis of the three extracted real-time operation data in S2 includes the following specific steps:

[0010] S21, extracting features from the three items of real-time operation data, and outputting the three items of real-time operation feature data, including voltage feature data, current feature data, and temperature feature data;

[0011] S22, constructing a correlation analysis model, wherein the correlation analysis model is a neural network model with three layers, the neural network model comprises an input layer, a hidden layer and an output layer, wherein the number of nodes in the input layer is set to 3, each node corresponds to a real-time operation feature data, the number of hidden layers is 2, the number of nodes in the output layer is set to 1, and the correlation is used as the output, and the output value is between 0 and 1;

[0012] S23, comparing the correlation output by the correlation analysis model with the preset correlation, if the output correlation does not meet the preset correlation, it is determined to be an energy storage device failure, if it meets the preset correlation, proceed to step S3.

[0013] A further improvement of the present invention is that the training method of the correlation analysis model in S22 is:

[0014] S221, collecting three historical operation data of the energy storage system and performing feature extraction, the three historical operation data including voltage, current, and temperature; dividing the three historical operation feature data into a normal operation feature data set and an abnormal operation feature data set according to the operation status of the energy storage device; setting the status label of each group of normal operation feature data in the normal operation feature data set to normal, and setting the status label of each group of abnormal feature data in the abnormal operation feature data set to abnormal, and the status labels of all normal operation feature data and abnormal operation feature data constitute historical status label data;

[0015] S222, converting each set of normal operation feature data and abnormal operation feature data into a positive sample set and a negative sample set respectively, setting a prediction label of 0 for each sample in the positive sample set, and setting a prediction label of 1 for each sample in the negative sample set;

[0016] S223. Select 70% of the positive samples and negative samples from the positive sample set and the negative sample set as training samples, and the remaining 30% of the positive samples and negative samples as test samples; use each training sample as the input of the association analysis model, use the prediction label corresponding to the training sample as the output of the association analysis model, iteratively train the association analysis model, and then verify the prediction accuracy of the association analysis model by using the test sample set, until the prediction accuracy of the test sample set reaches a preset accuracy threshold, then stop the training.

[0017] A further improvement of the present invention is that S3 comprises the following specific steps:

[0018] S31, preset a collection time period, collect voltage data, current data, and temperature data of n time nodes within the time period, and output a voltage data sequence (u1, u2, u3, ..., u n), current data sequence (I1, I2, I3, ..., I n ), temperature data series (P1, P2, P3, ..., P n );

[0019] S32, set the length of the sliding window to 3, and convert the voltage data sequence (u1, u2, u3, ..., u n ), current data sequence (I1, I2, I3, ..., I n ), temperature data series (P1, P2, P3, ..., P n ) are respectively divided into n-2 data groups in an orderly manner, wherein the data groups include data of three consecutive time nodes of one item of real-time operation data;

[0020] S33, respectively calculating the average values ​​of a single voltage data group, a current data group, and a temperature data group, and calculating the standard deviations of a single voltage data group, a current data group, and a temperature data group, to obtain a voltage standard deviation sequence Current standard deviation series Temperature standard deviation series

[0021] A further improvement of the present invention is that S3 further includes:

[0022] S34, constructing a voltage standard deviation envelope with the voltage data set sequence as the horizontal coordinate and the voltage standard deviation sequence as the vertical coordinate, and constructing a current standard deviation envelope and a temperature standard deviation envelope at the same time, and calculating the envelope area of ​​the envelope and the coordinate axis respectively as the current envelope area;

[0023] S35. Taking the rated voltage, rated current and rated temperature as reference values ​​respectively, taking the envelope area under the reference values ​​as the reference area, respectively calculate the deviation between the current envelope area and the reference area. When the deviation is greater than the preset deviation threshold, the evaluation result is that the energy storage system is in a sub-healthy state. When the deviation result is less than or equal to the preset deviation threshold, the evaluation result is that the energy storage system is in a healthy state.

[0024] The technical effects of the present invention are as follows:

[0025] A method for monitoring the health of an energy storage system based on big data analysis has been constructed. The present invention monitors the energy storage device in real time and extracts three items of real-time operating data with correlation, which are voltage data, current data, and temperature data. The three items of real-time operating data extracted are analyzed for correlation, and it is determined whether the correlation between the three items of real-time operating data meets the preset correlation. The three items of real-time operating data are imported into the health status assessment model to perform an energy storage system health assessment, and the energy storage system is maintained in an orderly manner according to the output assessment results. Therefore, the method has good operability, high accuracy, and high flexibility, and can effectively support efficient, flexible, and safe detection of the health status of the energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0027] Figure 1 It is a flow chart of the energy storage system health monitoring method based on big data analysis of the present invention. DETAILED DESCRIPTION

[0028] The present invention aims to propose a method for monitoring the health of an energy storage system based on big data analysis, by real-time monitoring of energy storage equipment and extracting three items of real-time operating data with correlation, the three items of real-time operating data being voltage data, current data, and temperature data; performing correlation analysis on the three extracted items of real-time operating data, judging whether the correlation between the three items of real-time operating data meets the preset correlation, importing the three items of real-time operating data into a health status assessment model to perform an energy storage system health assessment, and performing orderly maintenance of the energy storage system based on the output assessment results. Therefore, the method has good operability, high accuracy, and high flexibility, and can effectively support efficient, flexible, and safe detection of the health status of the energy storage system.

[0029] Embodiment 1:

[0030] This embodiment proposes a method for monitoring the health of an energy storage system based on big data analysis, such as Figure 1 As shown, the specific steps include:

[0031] S1. Monitor the energy storage device in real time and extract three items of real-time operation data having a correlation relationship, wherein the three items of real-time operation data are voltage data, current data, and temperature data;

[0032] S2, performing correlation analysis on the three extracted real-time operation data to determine whether the correlation between the three real-time operation data meets the preset correlation. If not, it is determined that the energy storage device is faulty. If it is satisfied, proceed to step S3;

[0033] S3. Import the three real-time operation data into the health status assessment model to conduct a health assessment of the energy storage system, and perform orderly maintenance on the energy storage system based on the output assessment results.

[0034] First, the method monitors and extracts three key operating data from the energy storage device in real time: voltage, current and temperature. These data are important indicators of the operating status of the energy storage device, and the relationship between them can reflect the health of the device. Through real-time monitoring, the operating status of the device at different time points can be obtained in time, laying the foundation for subsequent analysis.

[0035] In this embodiment, the correlation analysis of the three extracted real-time operation data in S2 includes the following specific steps:

[0036] S21. Extract features from three items of real-time operation data and output three items of real-time operation feature data, including voltage feature data, current feature data, and temperature feature data. In order to conduct effective correlation analysis, it is first necessary to extract feature data from the original real-time data. Specifically, the extracted feature data includes voltage feature data, current feature data, and temperature feature data. These feature data can better capture key information in the operation of the equipment.

[0037] S22. Construct a correlation analysis model, which is a neural network model with 3 layers, and the neural network model includes an input layer, a hidden layer and an output layer, wherein the number of nodes in the input layer is set to 3, each node corresponds to a real-time operation feature data, the number of hidden layers is 2, the number of nodes in the output layer is set to 1, and the correlation is used as the output, and the output value is between 0-1; by training the model on historical operation data, the model can learn the normal correlation between the three data under normal operating conditions. When the correlation value output by the model does not meet the preset correlation threshold, it is judged that the equipment may be faulty. This method can effectively identify the abnormal operation state of the equipment.

[0038] S23, compare the correlation output by the correlation analysis model with the preset correlation. If the output correlation does not meet the preset correlation, it is determined that the energy storage device is faulty. If it meets the preset correlation, proceed to step S3. If the correlation analysis shows that the relationship between the data is normal, the next step is to import the data into the health status assessment model for a more detailed health assessment.

[0039] In this embodiment, the training method of the association analysis model in S22 is:

[0040] S221, collecting three historical operation data of the energy storage system and performing feature extraction, the three historical operation data including voltage, current, and temperature; dividing the three historical operation feature data into a normal operation feature data set and an abnormal operation feature data set according to the operation status of the energy storage device; setting the status label of each group of normal operation feature data in the normal operation feature data set to normal, and setting the status label of each group of abnormal feature data in the abnormal operation feature data set to abnormal, and the status labels of all normal operation feature data and abnormal operation feature data constitute historical status label data;

[0041] S222, converting each set of normal operation feature data and abnormal operation feature data into a positive sample set and a negative sample set respectively, setting a prediction label of 0 for each sample in the positive sample set, and setting a prediction label of 1 for each sample in the negative sample set;

[0042] S223. Select 70% of the positive samples and negative samples from the positive sample set and the negative sample set as training samples, and the remaining 30% of the positive samples and negative samples as test samples; use each training sample as the input of the association analysis model, use the prediction label corresponding to the training sample as the output of the association analysis model, iteratively train the association analysis model, and then verify the prediction accuracy of the association analysis model by using the test sample set, until the prediction accuracy of the test sample set reaches a preset accuracy threshold, then stop the training.

[0043] In this embodiment, S3 includes the following specific steps:

[0044] S31, preset a collection time period, collect voltage data, current data, and temperature data of n time nodes within the time period, and output a voltage data sequence (u1, u2, u3, ..., u n ), current data sequence (I1, I2, I3, ..., I n ), temperature data series (P1, P2, P3, ..., P n );

[0045] S32, set the length of the sliding window to 3, and convert the voltage data sequence (u1, u2, u3, ..., u n ), current data sequence (I1, I2, I3, ..., I n ), temperature data series (P1, P2, P3, ..., P n ) are respectively divided into n-2 data groups in an orderly manner, wherein the data groups include data of three consecutive time nodes of one item of real-time operation data;

[0046] S33, respectively calculating the average values ​​of a single voltage data group, a current data group, and a temperature data group, and calculating the standard deviations of a single voltage data group, a current data group, and a temperature data group, to obtain a voltage standard deviation sequence Current standard deviation series Temperature standard deviation series

[0047] In order to better evaluate the health status of the equipment, this method first serializes the collected real-time data according to the time nodes, that is, generates voltage data sequences, current data sequences and temperature data sequences. Then, using the sliding window technology, these data sequences are divided into multiple data groups, each of which contains data from three consecutive time nodes. The sliding window technology is very effective in capturing the temporal dynamic changes of data. Statistical analysis is performed on each data group to calculate its mean and standard deviation. The standard deviation is an important feature of data distribution, which can reflect the fluctuation of data. The voltage standard deviation sequence, current standard deviation sequence and temperature standard deviation sequence obtained by calculation can further analyze the operating stability of the equipment.

[0048] In this embodiment, S3 further includes:

[0049] S34, constructing a voltage standard deviation envelope with the voltage data set sequence as the horizontal coordinate and the voltage standard deviation sequence as the vertical coordinate, and constructing a current standard deviation envelope and a temperature standard deviation envelope at the same time, and calculating the envelope area of ​​the envelope and the coordinate axis respectively as the current envelope area;

[0050] S35. Taking the rated voltage, rated current and rated temperature as reference values ​​respectively, taking the envelope area under the reference values ​​as the reference area, respectively calculate the deviation between the current envelope area and the reference area. When the deviation is greater than the preset deviation threshold, the evaluation result is that the energy storage system is in a sub-healthy state. When the deviation result is less than or equal to the preset deviation threshold, the evaluation result is that the energy storage system is in a healthy state.

[0051] This energy storage system health monitoring method based on big data analysis can effectively identify and predict the health status of energy storage equipment through real-time data monitoring, correlation analysis, sliding window processing and health assessment. It provides a scientific basis for the operation and maintenance of energy storage systems and can perform preventive maintenance before equipment failures, thereby extending the service life of equipment and reducing maintenance costs.

[0052] Embodiment 2:

[0053] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned energy storage system health monitoring method based on big data analysis by calling the computer program stored in the memory.

[0054] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement the energy storage system health monitoring method based on big data analysis provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0055] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), and it can also be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0056] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0057] The present invention is described with reference to flowcharts and block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process or block in the flowchart and block diagram, as well as the combination of processes and blocks in the flowchart or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1Process or multiple processes and boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 Process or multiple processes and boxes Figure 1 A step that specifies a function in one or more boxes.

[0059] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A method for monitoring the health of an energy storage system based on big data analysis, characterized in that: The specific steps include: S1. Monitor the energy storage device in real time and extract three items of real-time operation data having a correlation relationship, wherein the three items of real-time operation data are voltage data, current data, and temperature data; S2, performing correlation analysis on the three extracted real-time operation data to determine whether the correlation between the three real-time operation data meets the preset correlation. If not, it is determined that the energy storage device is faulty. If it is satisfied, proceed to step S3; S3. Import the three real-time operation data into the health status assessment model to conduct a health assessment of the energy storage system, and perform orderly maintenance on the energy storage system based on the output assessment results.

2. The energy storage system health monitoring method based on big data analysis according to claim 1 is characterized in that: The correlation analysis of the three extracted real-time operation data in S2 includes the following specific steps: S21, extracting features from the three items of real-time operation data, and outputting the three items of real-time operation feature data, including voltage feature data, current feature data, and temperature feature data; S22, constructing a correlation analysis model, wherein the correlation analysis model is a neural network model with three layers, the neural network model comprises an input layer, a hidden layer and an output layer, wherein the number of nodes in the input layer is set to 3, each node corresponds to a real-time operation feature data, the number of hidden layers is 2, the number of nodes in the output layer is set to 1, and the correlation is used as the output, and the output value is between 0 and 1; S23, comparing the correlation output by the correlation analysis model with the preset correlation, if the output correlation does not meet the preset correlation, it is determined to be an energy storage device failure, if it meets the preset correlation, proceed to step S3.

3. The method for monitoring the health of an energy storage system based on big data analysis according to claim 2, characterized in that: The training method of the correlation analysis model in S22 is: S221, collecting three historical operation data of the energy storage system and performing feature extraction, the three historical operation data including voltage, current, and temperature; dividing the three historical operation feature data into a normal operation feature data set and an abnormal operation feature data set according to the operation status of the energy storage device; setting the status label of each group of normal operation feature data in the normal operation feature data set to normal, and setting the status label of each group of abnormal feature data in the abnormal operation feature data set to abnormal, and the status labels of all normal operation feature data and abnormal operation feature data constitute historical status label data; S222, converting each set of normal operation feature data and abnormal operation feature data into a positive sample set and a negative sample set respectively, setting a prediction label of 0 for each sample in the positive sample set, and setting a prediction label of 1 for each sample in the negative sample set; S223. Select 70% of the positive samples and negative samples from the positive sample set and the negative sample set as training samples, and the remaining 30% of the positive samples and negative samples as test samples; use each training sample as the input of the association analysis model, use the prediction label corresponding to the training sample as the output of the association analysis model, iteratively train the association analysis model, and then verify the prediction accuracy of the association analysis model by using the test sample set, until the prediction accuracy of the test sample set reaches a preset accuracy threshold, then stop the training.

4. The method for monitoring the health of an energy storage system based on big data analysis according to claim 3, characterized in that: The S3 comprises the following specific steps: S31, preset a collection time period, collect voltage data, current data, and temperature data of n time nodes within the time period, and output a voltage data sequence (u1, u2, u3, ..., u n ), current data sequence (I1, I2, I3, ..., I n ), temperature data series (P1, P2, P3, ..., P n ); S32, set the length of the sliding window to 3, and convert the voltage data sequence (u1, u2, u3, ..., u n ), current data sequence (I1, I2, I3, ..., I n ), temperature data series (P1, P2, P3, ..., P n ) are respectively divided into n-2 data groups in an orderly manner, wherein the data groups include data of three consecutive time nodes of one item of real-time operation data; S33, respectively calculating the average values ​​of a single voltage data group, a current data group, and a temperature data group, and calculating the standard deviations of a single voltage data group, a current data group, and a temperature data group, to obtain a voltage standard deviation sequence Current standard deviation series Temperature standard deviation series 5. The method for monitoring the health of an energy storage system based on big data analysis according to claim 4 is characterized in that: The S3 further includes: S34, constructing a voltage standard deviation envelope with the voltage data set sequence as the horizontal coordinate and the voltage standard deviation sequence as the vertical coordinate, and constructing a current standard deviation envelope and a temperature standard deviation envelope at the same time, and calculating the envelope area of ​​the envelope and the coordinate axis respectively as the current envelope area; S35. Taking the rated voltage, rated current and rated temperature as reference values ​​respectively, taking the envelope area under the reference values ​​as the reference area, respectively calculate the deviation between the current envelope area and the reference area. When the deviation is greater than the preset deviation threshold, the evaluation result is that the energy storage system is in a sub-healthy state. When the deviation result is less than or equal to the preset deviation threshold, the evaluation result is that the energy storage system is in a healthy state.

Citation Information

Patent Citations

  • Energy storage system working state monitoring method and device, storage medium and electronic equipment

    CN115018366A

Cited By

  • Security detection method and system of energy storage system and storage medium

    CN120064818A

  • Safety detection method, system and storage medium for energy storage system

    CN120064818B

  • Artificial intelligence-based correlation analysis method and system for spine-pelvis sagittal morphology parameters and cardiopulmonary exercise endurance parameters

    CN120183738A

  • Analysis Method and System for the Correlation between Spinal-Pelvic Sagittal Morphological Parameters and Cardiopulmonary Exercise Endurance Parameters Based on Artificial Intelligence

    CN120183738B

  • Electronic control module health state evaluation method based on parameter incidence matrix

    CN122017644A