Multi-dimensional safety monitoring method and early warning system of integrated energy storage system

Abstract

The invention relates to the technical field of safety monitoring, in particular to a multi-dimensional safety monitoring method and an early warning system of an integrated energy storage system. The method comprises the following steps: acquiring structural data of the energy storage system; performing energy storage unit analysis on the structure data of the energy storage system to generate energy storage unit data of the energy storage system; performing unit operation data monitoring on the energy storage unit data to obtain an energy storage unit operation data set; data monitoring network integration is carried out through the energy storage unit data and the energy storage unit operation data set of the energy storage system, an integrated energy storage system monitoring network is generated, and the integrated energy storage system monitoring network comprises a battery operation node, a flywheel operation node and a super capacitor operation node; according to the invention, multi-dimensional monitoring, real-time data analysis and artificial intelligence technologies are introduced, so that the comprehensiveness, real-time performance and fault prediction capability of safety monitoring of an existing integrated energy storage system are improved.

Description

Technical Field

[0001] The present invention relates to the field of safety monitoring technology, and in particular to a multi-dimensional safety monitoring method and early warning system for an integrated energy storage system. Background Art

[0002] Integrated energy storage systems play a key role in energy management and renewable energy integration. However, as the capacity and complexity of the system increase, its safety issues are becoming increasingly prominent. Early energy storage system safety monitoring mainly focused on a single dimension, such as basic parameters such as temperature, voltage and current, which were usually achieved through simple sensors. In the 21st century, energy storage systems gradually adopted multi-dimensional monitoring technology, taking into account multiple factors such as temperature, voltage, current, vibration, gas emissions and electrochemical state. The technological progress at this stage was mainly due to the breakthrough of sensor technology and the improvement of data processing capabilities, especially the introduction of big data and Internet of Things technology, which made real-time monitoring and remote data analysis possible. In recent years, the application of artificial intelligence and machine learning algorithms has further promoted the development of multi-dimensional safety monitoring. Through these advanced technologies, potential faults can be predicted and preventive maintenance can be performed, greatly improving the safety and reliability of the system. However, in the pursuit of real-time performance, the existing technology has compromised on the accuracy of data processing, and at the same time focuses on the safety monitoring of a single energy storage unit, but lacks the comprehensive optimization of the entire integrated system, which leads to low comprehensiveness and accuracy of safety monitoring. Summary of the invention

[0003] Based on this, it is necessary to provide a multi-dimensional safety monitoring method and early warning system for an integrated energy storage system to solve at least one of the above technical problems.

[0004] To achieve the above object, a multi-dimensional safety monitoring method for an integrated energy storage system is provided, the method comprising the following steps:

[0005] Step S1: Acquire energy storage system structure data; perform energy storage unit analysis on the energy storage system structure data to generate energy storage system energy storage unit data; perform unit operation data monitoring on the energy storage unit data to obtain an energy storage unit operation data set; perform data monitoring network integration through the energy storage system energy storage unit data and the energy storage unit operation data set to generate an integrated energy storage system monitoring network, wherein the integrated energy storage system monitoring network includes a battery operation node, a flywheel operation node, and a supercapacitor operation node;

[0006] Step S2: Based on the battery operation node, perform EIS measurement on the standard energy storage unit operation data set and collect impedance response to generate battery node impedance response data; construct an equivalent circuit model for the battery node impedance response data to generate a battery equivalent circuit model; perform battery aging analysis on the battery operation node through the battery equivalent circuit model to generate battery node health monitoring data; perform flywheel stability analysis on the standard energy storage unit operation data set based on the flywheel operation node to generate flywheel node health monitoring data;

[0007] Step S3: Calculate the capacitor self-discharge rate of the standard energy storage unit operation data set based on the supercapacitor operation node to generate capacitor self-discharge rate data; analyze the internal electrolyte aging rate of the supercapacitor operation node according to the capacitor self-discharge rate data to generate supercapacitor node health monitoring data; integrate the battery node health monitoring data, flywheel node health monitoring data and supercapacitor node health monitoring data to generate node health monitoring short-term data; perform long-term trend prediction on the node health monitoring short-term data to generate integrated energy storage system node long-term health prediction data;

[0008] Step S4: Detect node anomalies in the integrated energy storage system monitoring network through the long-term health prediction data of the integrated energy storage system nodes and the short-term data of the node health monitoring, and generate normal operation nodes and abnormal operation nodes; perform adaptive repair on the abnormal operation nodes to generate abnormal node repair data; perform system-level health status assessment on the abnormal operation nodes and normal operation nodes according to the abnormal node repair data to generate integrated energy storage system health status detection data;

[0009] Step S5: Distribute the integrated energy storage system health status detection data to generate energy storage system health status storage data; perform status warning on the integrated energy storage system health status detection data to generate energy storage system health status warning data; perform collaborative feedback on the energy storage system health status storage data and the energy storage system health status warning data to generate integrated energy storage system monitoring feedback data, so as to perform multi-dimensional safety monitoring and warning operations of the integrated energy storage system.

[0010] The present invention generates detailed energy storage unit data by acquiring the structural data of the energy storage system and performing energy storage unit analysis, and on this basis, monitors the unit operation data to build an integrated monitoring network. The network covers the operation nodes of batteries, flywheels and supercapacitors, ensures the all-round monitoring and data integration of the energy storage system, provides a comprehensive data basis for real-time monitoring and analysis of the health status of the system, and improves the accuracy and reliability of monitoring. By performing EIS (electrochemical impedance spectroscopy) measurement and impedance response acquisition on the battery node, the impedance response data of the battery node is generated, and a battery equivalent circuit model is constructed based on this, so that the battery aging state can be deeply analyzed and accurate battery health monitoring data can be provided. At the same time, the stability analysis of the flywheel node generates the flywheel health monitoring data, effectively identifies and predicts the operating state and potential failure risks of the flywheel, and improves the stability and safety of the overall operation of the system. By calculating the self-discharge rate of the supercapacitor and analyzing the aging rate of the internal electrolyte, this step generates the health monitoring data of the supercapacitor node, and integrates it with the health monitoring data of the battery and flywheel nodes to generate short-term health monitoring data. Further, through long-term trend prediction, long-term health prediction data of nodes is generated, thereby improving the system's ability to predict future health status and ensuring the continuous and reliable operation of the system. Using long-term health prediction data and short-term health monitoring data, abnormal detection is performed on nodes in the integrated energy storage system monitoring network to timely identify normal and abnormal operation nodes. For the detected abnormal nodes, the step also provides an adaptive repair mechanism to generate repair data, and through system-level health status assessment, generates comprehensive system health status detection data, thereby achieving rapid response and repair of system abnormalities, effectively reducing the risk of system failures, and improving the overall health level of the system. By distributing the health status detection data of the integrated energy storage system, this step ensures the security and reliability of the data, and at the same time performs status warning and generates warning data to ensure that the system can be warned in time before problems occur. Finally, through the collaborative feedback mechanism, the stored data and warning data are fed back to the system to form a closed-loop monitoring feedback process, which significantly improves the efficiency and effectiveness of the safety monitoring and warning operations of the energy storage system, thereby comprehensively ensuring the long-term stability and safe operation of the system. Therefore, the present invention improves the comprehensiveness, real-timeness and fault prediction capabilities of existing integrated energy storage system safety monitoring by introducing multi-dimensional monitoring, real-time data analysis and artificial intelligence technology.

[0011] Preferably, step S1 comprises the following steps:

[0012] Step S11: Acquire energy storage system structure data;

[0013] Step S12: Performing energy storage unit analysis on the energy storage system structure data to generate energy storage system energy storage unit data;

[0014] Step S13: using sensors to monitor the energy storage unit data to obtain an energy storage unit operation data set; performing data preprocessing on the energy storage unit operation data set to generate a standard energy storage unit operation data set, wherein the data preprocessing includes data cleaning, data denoising, data normalization and data standardization;

[0015] Step S14: using the energy storage unit data of the energy storage system as nodes to perform data monitoring network integration through a standard energy storage unit operation data set to generate an integrated energy storage system monitoring network, wherein the integrated energy storage system monitoring network includes a battery operation node, a flywheel operation node, and a supercapacitor operation node.

[0016] The present invention realizes comprehensive monitoring and management of energy storage units by conducting in-depth analysis and processing of energy storage system structural data. Specifically, by acquiring the structural data of the energy storage system and analyzing and monitoring the energy storage units, refined management of energy storage units such as batteries, flywheels, and supercapacitors is realized. The data preprocessing step ensures the accuracy and consistency of the operating data, making the subsequent data monitoring network integration more reliable. The integrated energy storage system monitoring network finally generated not only improves the operating efficiency of the energy storage system, but also enhances the real-time monitoring capability of each energy storage unit, providing strong support for the stable operation of the system. This integrated monitoring network can achieve collaborative work between various energy storage nodes, improve the response speed and reliability of the entire energy storage system, and effectively improve the overall performance and safety of the energy storage system.

[0017] Preferably, step S2 comprises the following steps:

[0018] Step S21: screening battery characteristic data of a standard energy storage unit operation data set based on a battery operation node to obtain battery operation characteristic data;

[0019] Step S22: setting the AC signal amplitude according to the battery operation characteristic data to obtain AC signal amplitude setting data; performing EIS measurement on the battery operation node and collecting impedance response according to the AC signal amplitude setting data to generate battery node impedance response data;

[0020] Step S23: Perform Nyquist diagram conversion on the battery node impedance response data to generate a battery response Nyquist diagram; construct an equivalent circuit model for the battery response Nyquist diagram to generate a battery equivalent circuit model; perform battery aging analysis on the battery operation node through the battery equivalent circuit model to generate battery node health monitoring data;

[0021] Step S24: based on the flywheel operation node, the flywheel motion characteristic data of the standard energy storage unit operation data set is screened to obtain the flywheel motion characteristic data; the flywheel motion characteristic data is subjected to flywheel stability analysis to generate flywheel node health monitoring data.

[0022] The present invention generates battery node impedance response data by screening battery operation characteristic data and measuring AC impedance spectrum (EIS), and converts it into a Nyquist diagram. This process enables the health status of the battery to be analyzed in detail, especially in aging analysis. By constructing a battery equivalent circuit model, the health status of the battery can be accurately monitored and its service life can be extended. For the flywheel energy storage unit, step S24 generates flywheel node health monitoring data by screening and stability analysis of flywheel motion characteristic data, which ensures the operating stability and reliability of the flywheel system, reduces the occurrence rate of failures, and improves the overall safety of the system. Combining the health monitoring data of the two key components of battery and flywheel, it is possible to achieve all-round health management of standard energy storage units. This comprehensive analysis method improves the operation and maintenance efficiency of the energy storage system and reduces the risks caused by equipment aging or failure. Using the health monitoring data of the battery and flywheel nodes, the energy storage system can dynamically adjust its working mode and optimize performance according to the actual operating conditions. This data-driven optimization strategy helps to extend the overall life of the energy storage unit and improve its energy efficiency.

[0023] Preferably, step S24 includes the following steps:

[0024] Step S241: screening the flywheel motion characteristic data of the standard energy storage unit operation data set based on the flywheel operation node to obtain the flywheel motion characteristic data, wherein the flywheel motion characteristic data includes the flywheel speed data and the flywheel vibration data;

[0025] Step S242: performing fast Fourier transform on the flywheel speed data and the flywheel vibration data to generate a flywheel vibration spectrum diagram; performing abnormal change spectrum analysis on the flywheel vibration spectrum diagram to generate flywheel abnormal vibration spectrum data; performing time domain analysis on the flywheel abnormal vibration spectrum data to generate flywheel abnormal vibration time domain data;

[0026] Step S243: collecting the flywheel bearing acoustic waves at the flywheel operation nodes according to the time domain of the flywheel abnormal vibration to obtain the flywheel bearing acoustic wave data; constructing an acoustic emission event spectrum for the flywheel bearing acoustic wave data to generate a flywheel bearing acoustic emission event spectrum;

[0027] Step S244: analyzing the flywheel operation energy change of the flywheel operation node through the flywheel bearing acoustic emission event spectrum to generate flywheel node health monitoring data.

[0028] The present invention can generate a flywheel vibration spectrum diagram and further identify abnormal vibration spectrum by fast Fourier transform (FFT) analysis of flywheel speed data and vibration data. This process can accurately capture abnormal phenomena in flywheel operation and timely discover potential problems, thereby improving the safety and reliability of the flywheel system. By performing time domain analysis on abnormal vibration spectrum data, the generated flywheel abnormal vibration time domain data provides a more comprehensive perspective on abnormal vibration. This multi-dimensional analysis method helps to deeply understand the causes and characteristics of flywheel abnormalities and provide a scientific basis for subsequent maintenance decisions. The state of the flywheel bearing can be effectively monitored by collecting flywheel bearing sound waves and constructing an acoustic emission event spectrum. The acoustic emission spectrum can reveal the microscopic damage or wear inside the bearing, thereby achieving early warning of bearing health and avoiding the occurrence of serious faults. The flywheel operation energy change analysis performed by the flywheel bearing acoustic emission event spectrum helps to fully grasp the energy conversion efficiency and stability of the flywheel system. This analysis can provide accurate information about the energy state of the flywheel system and provide a basis for optimizing the operating mode and extending the life of the equipment. The flywheel node health monitoring data finally generated integrates the analysis results of various signals such as speed, vibration, and sound waves, providing a comprehensive assessment of the flywheel operating status. This comprehensive health management method helps to improve the overall performance and reliability of the flywheel energy storage system, reduce maintenance costs, and extend the service life of the equipment.

[0029] Preferably, step S3 comprises the following steps:

[0030] Step S31: Screening capacitor characteristic data of a standard energy storage unit operation data set based on a supercapacitor operation node to obtain capacitor operation characteristic data;

[0031] Step S32: extracting voltage characteristic data of the capacitor operation characteristic data, and calculating the capacitor self-discharge rate on the voltage characteristic data to generate capacitor self-discharge rate data;

[0032] Step S33: analyzing the voltage drop rate of the supercapacitor operation node under static conditions according to the capacitor self-discharge rate data to generate capacitor voltage drop rate data; analyzing the internal electrolyte aging rate of the supercapacitor operation node according to the capacitor voltage drop rate to generate supercapacitor node health monitoring data;

[0033] Step S34: Integrate the battery node health monitoring data, flywheel node health monitoring data and supercapacitor node health monitoring data to generate short-term node health monitoring data; perform long-term trend prediction on the short-term node health monitoring data to generate long-term health prediction data for the integrated energy storage system nodes.

[0034] The present invention can accurately evaluate the health status of supercapacitors by screening capacitor operation characteristic data and calculating capacitor self-discharge rate. In particular, by analyzing the voltage drop rate under static conditions, the aging of the electrolyte inside the capacitor can be identified, so as to provide early warning and avoid rapid degradation of capacitor performance. The health monitoring data of batteries, flywheels and supercapacitors are integrated to generate node health monitoring short-term data. This data integration method enables the health status of different energy storage units to be compared and comprehensively analyzed on the same platform, which helps to form an overall system health view. By predicting the long-term trend of node health monitoring short-term data, the future health status of the energy storage system can be understood in advance. This prediction capability enables operation and maintenance personnel to take preventive measures, reduce unexpected downtime and maintenance costs, and extend the overall life of the energy storage system. The long-term health prediction data of the nodes of the integrated energy storage system provides systematic information, which helps to optimize the scheduling and use strategy of the energy storage unit. Based on the long-term health prediction data, the system can dynamically adjust the operation mode of each energy storage unit to ensure the optimal performance of the system under different load conditions. By comprehensively analyzing the health status of batteries, flywheels, and supercapacitors, step S3 enhances the overall monitoring and management capabilities of the energy storage system. This comprehensive health monitoring and prediction method can significantly improve the safety and reliability of the energy storage system and reduce system risks caused by single component failures.

[0035] Preferably, step S34 includes the following steps:

[0036] Step S341: integrating the battery node health monitoring data, the flywheel node health monitoring data and the supercapacitor node health monitoring data to generate node health monitoring short-term data;

[0037] Step S342: performing data dimensionality reduction on the node health monitoring short-term data to generate node health monitoring dimensionality reduction data; dividing the node health monitoring dimensionality reduction data into data sets to generate a model training set and a model test set;

[0038] Step S343: Perform model training on the model training set through a recursive neural network algorithm to generate a node health long-term trend prediction model; perform dilation convolution on the node health long-term regional prediction model using the model test set based on the attention mechanism to generate a node health long-term trend prediction model;

[0039] Step S344: Import the short-term node health monitoring data into the node health long-term trend prediction model to perform long-term trend prediction, and generate the integrated energy storage system node long-term health prediction data.

[0040] The present invention integrates the health monitoring data of batteries, flywheels, and supercapacitors, and performs data dimension reduction processing to generate more concise but information-rich node health monitoring data. This process reduces the interference of redundant data, making the subsequent model training and prediction more efficient and accurate. The data set is trained by a recursive neural network algorithm, and the dilated convolution is combined with the attention mechanism to capture the key features in the time series. The node health long-term trend prediction model generated in this way can more accurately reflect the health evolution trend of the energy storage system and improve the reliability of the prediction. By importing short-term data into the prediction model for long-term trend prediction, the generated long-term health prediction data can identify potential health problems in advance, so that the system can take maintenance measures in advance to prevent excessive aging or failure of components, thereby improving the overall stability and safety of the system. This step provides an integrated health management perspective by integrating the health monitoring data of multiple energy storage units. This global data analysis and prediction not only helps to optimize the operation of a single energy storage unit, but also coordinates the work of each unit at the system level to improve the efficiency of the entire energy storage system. Through long-term health prediction data, operation and maintenance personnel can make more intelligent decisions based on scientific data support. Such predictive decisions not only reduce the need for emergency repairs, but also reduce the operating costs of the system and extend the service life of the energy storage system.

[0041] Preferably, step S4 comprises the following steps:

[0042] Step S41: performing node anomaly detection on the integrated energy storage system monitoring network through the long-term health prediction data of the integrated energy storage system nodes and the short-term health monitoring data of the nodes, and generating normal operation nodes and abnormal operation nodes;

[0043] Step S42: performing node association analysis on the abnormal operation node to generate abnormal operation node association data; performing node fault linkage analysis on the abnormal operation node through the abnormal operation node association data to generate abnormal node fault linkage data;

[0044] Step S43: Adaptively repair the abnormal operation node based on the abnormal node fault linkage data to generate abnormal node repair data;

[0045] Step S44: Perform system-level health status assessment on abnormal operation nodes and normal operation nodes according to the abnormal node repair data to generate integrated energy storage system health status detection data.

[0046] The present invention combines the long-term health prediction data and short-term monitoring data of the nodes of the integrated energy storage system, and step S41 can perform comprehensive abnormal detection on the nodes in the energy storage system monitoring network. The combination of this dual data source makes the detection more accurate and can identify abnormal operation nodes in time, thereby improving the safety of the system. Through the correlation analysis of the abnormal operation nodes, the generated abnormal node fault linkage data can reveal the potential fault association between the abnormal nodes. This analysis can help the system identify the key nodes that cause system-level faults, and provide an in-depth understanding of the complex fault chain, which helps to prevent the spread and deterioration of faults. Based on the fault linkage data, the abnormal operation nodes are adaptively repaired, and the operation status of the abnormal nodes can be automatically adjusted and optimized to generate repair data. This adaptive repair capability can quickly respond to system abnormalities and reduce the impact of faults on the overall performance of the system, thereby enhancing the stability and self-healing ability of the system. By combining the abnormal node repair data and the normal node data, the overall health status of the system is evaluated. This evaluation not only provides a comprehensive view of the current system health status, but also provides an important basis for subsequent maintenance decisions, thereby optimizing the operation and maintenance strategy of the energy storage system. By automatically detecting, analyzing, repairing and evaluating abnormal nodes, step S4 significantly enhances the self-diagnosis and repair capabilities of the energy storage system. This intelligent management method reduces the need for manual intervention, improves the system's automation level, and thus improves the system's reliability and operating efficiency.

[0047] Preferably, step S43 includes the following steps:

[0048] Step S431: performing Monte Carlo simulation on the abnormal operation node based on the abnormal node fault linkage data to generate abnormal node fault propagation simulation data;

[0049] Step S432: performing operation collapse calculation on the integrated energy storage system monitoring network through abnormal node fault propagation simulation data to generate system collapse rate occurrence data;

[0050] Step S433: comparing the system crash rate data with a preset system crash threshold, when the system crash rate data is greater than or equal to the preset system crash threshold, selecting a redundant backup system for the corresponding abnormal operation node, and generating a redundant backup system repair strategy;

[0051] Step S434: When the system crash rate data is less than the preset system crash threshold, the corresponding abnormal operation node is isolated and recovered to generate a fault isolation recovery strategy; the abnormal operation node is adaptively repaired according to the redundant backup system repair strategy and the fault isolation recovery strategy to generate abnormal node repair data.

[0052] The present invention uses Monte Carlo simulation technology to perform fault propagation analysis on abnormal operation nodes, and the generated fault propagation simulation data can provide multiple possible fault propagation paths and their impact ranges. This accurate simulation enables the system to identify potential system crash risks in advance, thereby providing an important basis for the adaptive repair of the system. The operation crash calculation is performed using the fault propagation simulation data to generate system crash rate occurrence data. This process can quickly evaluate the stability of the energy storage system under fault conditions and provide quantitative indicators of the system crash rate, which helps to take repair measures in time when the crash risk is high. According to the comparison between the system crash rate occurrence data and the preset crash threshold, two countermeasures are provided: when the crash rate is higher than or equal to the threshold, a redundant backup system repair strategy is generated; when the crash rate is lower than the threshold, a fault isolation recovery strategy is generated. Through this flexible repair strategy selection, the system can make the best countermeasures in different fault scenarios to ensure the continuous and stable operation of the system. By executing the redundant backup system repair strategy or the fault isolation recovery strategy, the abnormal operation node is adaptively repaired. This process can not only repair the current fault node, but also prevent the fault from spreading further, enhance the self-healing ability of the system, and reduce the downtime of the system caused by the fault. The overall design significantly improves the reliability and fault tolerance of the integrated energy storage system through accurate fault propagation simulation, collapse risk assessment and flexible repair strategies. The system can autonomously identify and handle faults, reducing the need for manual intervention and improving the automation level and long-term stability of the system.

[0053] Preferably, step S5 comprises the following steps:

[0054] Step S51: using blockchain technology to perform distributed storage of the integrated energy storage system health status detection data to generate energy storage system health status storage data;

[0055] Step S52: Performing status warning on the stored data of the health status of the energy storage system to generate health status warning data of the energy storage system;

[0056] Step S53: Transmit the energy storage system health status storage data and the energy storage system health status warning data to the central monitoring system for collaborative feedback, generate integrated energy storage system monitoring feedback data, and perform multi-dimensional safety monitoring and warning operations of the integrated energy storage system.

[0057] The present invention effectively ensures the security and integrity of the health status data of the energy storage system by using blockchain technology for distributed data storage. The immutability and transparency of blockchain technology can prevent the forgery and tampering of data, and ensure the authenticity and reliability of health status data. The status warning of the health status storage data of the energy storage system enables the system to monitor and identify potential health risks in real time. By generating the health status warning data of the energy storage system, the abnormalities in the system can be discovered in time, so as to take preventive measures in advance and reduce the risk of system failure. The health status storage data and warning data of the energy storage system are transmitted to the central monitoring system for collaborative feedback. This centralized data processing and feedback mechanism can comprehensively evaluate the system status and provide comprehensive monitoring feedback data for the central monitoring system, thereby realizing multi-dimensional safety monitoring and warning of the system. The generated integrated energy storage system monitoring feedback data can support multi-dimensional safety monitoring and warning operations. This multi-dimensional monitoring can include real-time status monitoring, trend analysis and risk prediction, etc., which helps to fully grasp the health status of the system and respond to various potential security threats in a timely manner. Through blockchain storage, real-time warning and centralized feedback mechanisms, comprehensive monitoring and management of the health status of the energy storage system is achieved. This integrated management method improves the maintenance efficiency of the system, reduces the need for manual intervention, and improves the response speed and processing capabilities to system failures. Integrated health status detection and warning data not only facilitates real-time monitoring, but also provides data support for system operation and management decisions. Based on this data, operation and maintenance personnel can make more intelligent decisions to optimize the system's operation and maintenance strategies.

[0058] In this specification, a multi-dimensional safety early warning system of an integrated energy storage system is provided, which is used to execute the multi-dimensional safety monitoring method of the integrated energy storage system. The multi-dimensional safety early warning system of the integrated energy storage system includes:

[0059] The energy storage unit division module is used to obtain the energy storage system structure data; perform energy storage unit analysis on the energy storage system structure data to generate energy storage system energy storage unit data; perform unit operation data monitoring on the energy storage unit data to obtain an energy storage unit operation data set; perform data monitoring network integration through the energy storage system energy storage unit data and the energy storage unit operation data set to generate an integrated energy storage system monitoring network, wherein the integrated energy storage system monitoring network includes battery operation nodes, flywheel operation nodes, and supercapacitor operation nodes;

[0060] The battery flywheel node analysis module is used to perform EIS measurement on the standard energy storage unit operation data set based on the battery operation node and collect impedance response to generate battery node impedance response data; construct an equivalent circuit model for the battery node impedance response data to generate a battery equivalent circuit model; perform battery aging analysis on the battery operation node through the battery equivalent circuit model to generate battery node health monitoring data; perform flywheel stability analysis on the standard energy storage unit operation data set based on the flywheel operation node to generate flywheel node health monitoring data;

[0061] The capacitor node analysis module is used to calculate the capacitor self-discharge rate of the standard energy storage unit operation data set based on the supercapacitor operation node to generate capacitor self-discharge rate data; analyze the internal electrolyte aging rate of the supercapacitor operation node based on the capacitor self-discharge rate data to generate supercapacitor node health monitoring data; integrate the battery node health monitoring data, flywheel node health monitoring data and supercapacitor node health monitoring data to generate node health monitoring short-term data; perform long-term trend prediction on the node health monitoring short-term data to generate integrated energy storage system node long-term health prediction data;

[0062] The abnormal node repair module is used to detect node anomalies in the integrated energy storage system monitoring network through the long-term health prediction data of the integrated energy storage system nodes and the short-term data of node health monitoring, and generate normal operation nodes and abnormal operation nodes; perform adaptive repair on abnormal operation nodes and generate abnormal node repair data; perform system-level health status assessment on abnormal operation nodes and normal operation nodes according to the abnormal node repair data, and generate integrated energy storage system health status detection data;

[0063] The health warning module is used to perform distributed storage of the health status detection data of the integrated energy storage system to generate the health status storage data of the energy storage system; to perform status warning on the health status detection data of the integrated energy storage system to generate the health status warning data of the energy storage system; to perform collaborative feedback on the health status storage data of the energy storage system and the health status warning data of the energy storage system to generate the monitoring feedback data of the integrated energy storage system, so as to perform multi-dimensional safety monitoring and warning operations of the integrated energy storage system.

[0064] The beneficial effect of the present invention is that by acquiring the structural data of the energy storage system and performing energy storage unit analysis, operation data monitoring and data monitoring network integration, an integrated energy storage system monitoring network including batteries, flywheels and supercapacitors is constructed, ensuring real-time monitoring and data integration of each energy storage unit in the system, and providing basic data support for subsequent health monitoring. By performing EIS measurement on battery nodes, battery aging analysis, and stability analysis on flywheel nodes, health monitoring data of each energy storage unit is generated, which effectively improves the ability to accurately evaluate battery aging and flywheel stability, and lays the foundation for preventive maintenance of the system. By calculating the self-discharge rate of the supercapacitor and analyzing the aging rate of its internal electrolyte, health monitoring data is generated, and long-term trend prediction is performed in combination with short-term data, which helps to discover and prevent potential capacitor performance degradation problems early and improves the overall health monitoring accuracy of the system. By performing node anomaly detection and adaptive repair through long-term health prediction data and short-term health monitoring data, abnormal operation nodes in the energy storage system can be identified and repaired in a timely manner, and system-level health status evaluation can be performed to ensure stable operation and extend the life of the energy storage system. By distributing the health status detection data, performing status warning and collaborative feedback, the system's multi-dimensional safety monitoring and warning functions are realized, ensuring early warning and rapid response before a failure occurs, and improving the overall safety and reliability of the energy storage system. Therefore, the present invention improves the comprehensiveness, real-timeness and fault prediction capabilities of the existing integrated energy storage system safety monitoring by introducing multi-dimensional monitoring, real-time data analysis and artificial intelligence technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A schematic diagram of the steps of a multi-dimensional safety monitoring method for an integrated energy storage system;

[0066] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0067] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0068] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0069] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0070] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0071] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0072] To achieve this, please refer to Figures 1 to 3 , a multi-dimensional safety monitoring method for an integrated energy storage system, the method comprising the following steps:

[0073] Step S1: Acquire energy storage system structure data; perform energy storage unit analysis on the energy storage system structure data to generate energy storage system energy storage unit data; perform unit operation data monitoring on the energy storage unit data to obtain an energy storage unit operation data set; perform data monitoring network integration through the energy storage system energy storage unit data and the energy storage unit operation data set to generate an integrated energy storage system monitoring network, wherein the integrated energy storage system monitoring network includes a battery operation node, a flywheel operation node, and a supercapacitor operation node;

[0074] Step S2: Based on the battery operation node, perform EIS measurement on the standard energy storage unit operation data set and collect impedance response to generate battery node impedance response data; construct an equivalent circuit model for the battery node impedance response data to generate a battery equivalent circuit model; perform battery aging analysis on the battery operation node through the battery equivalent circuit model to generate battery node health monitoring data; perform flywheel stability analysis on the standard energy storage unit operation data set based on the flywheel operation node to generate flywheel node health monitoring data;

[0075] Step S3: Calculate the capacitor self-discharge rate of the standard energy storage unit operation data set based on the supercapacitor operation node to generate capacitor self-discharge rate data; analyze the internal electrolyte aging rate of the supercapacitor operation node according to the capacitor self-discharge rate data to generate supercapacitor node health monitoring data; integrate the battery node health monitoring data, flywheel node health monitoring data and supercapacitor node health monitoring data to generate node health monitoring short-term data; perform long-term trend prediction on the node health monitoring short-term data to generate integrated energy storage system node long-term health prediction data;

[0076] Step S4: Detect node anomalies in the integrated energy storage system monitoring network through the long-term health prediction data of the integrated energy storage system nodes and the short-term data of the node health monitoring, and generate normal operation nodes and abnormal operation nodes; perform adaptive repair on the abnormal operation nodes to generate abnormal node repair data; perform system-level health status assessment on the abnormal operation nodes and normal operation nodes according to the abnormal node repair data to generate integrated energy storage system health status detection data;

[0077] Step S5: Distribute the integrated energy storage system health status detection data to generate energy storage system health status storage data; perform status warning on the integrated energy storage system health status detection data to generate energy storage system health status warning data; perform collaborative feedback on the energy storage system health status storage data and the energy storage system health status warning data to generate integrated energy storage system monitoring feedback data, so as to perform multi-dimensional safety monitoring and warning operations of the integrated energy storage system.

[0078] The present invention generates detailed energy storage unit data by acquiring the structural data of the energy storage system and performing energy storage unit analysis, and on this basis, monitors the unit operation data to build an integrated monitoring network. The network covers the operation nodes of batteries, flywheels and supercapacitors, ensures the all-round monitoring and data integration of the energy storage system, provides a comprehensive data basis for real-time monitoring and analysis of the health status of the system, and improves the accuracy and reliability of monitoring. By performing EIS (electrochemical impedance spectroscopy) measurement and impedance response acquisition on the battery node, the impedance response data of the battery node is generated, and a battery equivalent circuit model is constructed based on this, so that the battery aging state can be deeply analyzed and accurate battery health monitoring data can be provided. At the same time, the stability analysis of the flywheel node generates the flywheel health monitoring data, effectively identifies and predicts the operating state and potential failure risks of the flywheel, and improves the stability and safety of the overall operation of the system. By calculating the self-discharge rate of the supercapacitor and analyzing the aging rate of the internal electrolyte, this step generates the health monitoring data of the supercapacitor node, and integrates it with the health monitoring data of the battery and flywheel nodes to generate short-term health monitoring data. Further, through long-term trend prediction, long-term health prediction data of nodes is generated, thereby improving the system's ability to predict future health status and ensuring the continuous and reliable operation of the system. Using long-term health prediction data and short-term health monitoring data, abnormal detection is performed on nodes in the integrated energy storage system monitoring network to timely identify normal and abnormal operation nodes. For the detected abnormal nodes, the step also provides an adaptive repair mechanism to generate repair data, and through system-level health status assessment, generates comprehensive system health status detection data, thereby achieving rapid response and repair of system abnormalities, effectively reducing the risk of system failures, and improving the overall health level of the system. By distributing the health status detection data of the integrated energy storage system, this step ensures the security and reliability of the data, and at the same time performs status warning and generates warning data to ensure that the system can be warned in time before problems occur. Finally, through the collaborative feedback mechanism, the stored data and warning data are fed back to the system to form a closed-loop monitoring feedback process, which significantly improves the efficiency and effectiveness of the safety monitoring and warning operations of the energy storage system, thereby comprehensively ensuring the long-term stability and safe operation of the system. Therefore, the present invention improves the comprehensiveness, real-timeness and fault prediction capabilities of existing integrated energy storage system safety monitoring by introducing multi-dimensional monitoring, real-time data analysis and artificial intelligence technology.

[0079] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a multi-dimensional safety monitoring method for an integrated energy storage system of the present invention. In this example, the multi-dimensional safety monitoring method for an integrated energy storage system includes the following steps:

[0080] Step S1: Acquire energy storage system structure data; perform energy storage unit analysis on the energy storage system structure data to generate energy storage system energy storage unit data; perform unit operation data monitoring on the energy storage unit data to obtain an energy storage unit operation data set; perform data monitoring network integration through the energy storage system energy storage unit data and the energy storage unit operation data set to generate an integrated energy storage system monitoring network, wherein the integrated energy storage system monitoring network includes a battery operation node, a flywheel operation node, and a supercapacitor operation node;

[0081] In the embodiment of the present invention, the physical structure data of the energy storage system is obtained, including the layout, connection mode, installation location and other information of energy storage units such as battery modules, flywheels, and supercapacitors. The electrical connection data of the energy storage system is obtained, such as circuit design diagrams, wiring diagrams, and protection device configurations. The data of the operating environment of the energy storage system is obtained, including data that affect the operation of the energy storage system, such as temperature, humidity, pressure, and vibration. The acquired energy storage system structure data is analyzed to extract the characteristic data of each energy storage unit, such as battery capacity, flywheel speed, and voltage and current characteristics of supercapacitors. Based on the characteristic data of the energy storage unit, a corresponding energy storage unit model is constructed. The model includes a battery model, a flywheel model, and a supercapacitor model, etc., which reflect the operating characteristics and behavior of the energy storage unit. The analyzed energy storage unit characteristic data is aggregated to generate energy storage system energy storage unit data, including characteristic parameters, operating status, and expected performance of each energy storage unit. Appropriate sensors are installed on energy storage units such as batteries, flywheels, and supercapacitors to monitor the operating data of each unit in real time, such as voltage, current, temperature, vibration, and speed. The operation data of the energy storage unit is collected in real time through the sensor network and transmitted to the central data processing system. The collected energy storage unit operation data is cleaned to remove noise and outliers to ensure the accuracy of the data. The energy storage unit operation data is normalized and standardized for subsequent analysis and processing. The preprocessed data is organized into an energy storage unit operation data set, which contains information such as the real-time operation status and historical operation records of the energy storage unit. The data of the battery module is integrated into the monitoring network as a node. The data of the flywheel is integrated into the monitoring network as a node. The data of the supercapacitor is integrated into the monitoring network as a node. The energy storage unit data of the energy storage system is integrated with the energy storage unit operation data set, and an integrated energy storage system monitoring network is constructed through the real-time monitoring of each node and the correlation analysis of historical data. In the monitoring network, each operation node is interconnected to form a comprehensive energy storage system monitoring system. The network can monitor the operation status of different energy storage units such as batteries, flywheels and supercapacitors in real time and provide the overall operation status of the system. Through the integrated design of the data monitoring network, the coordinated monitoring of the battery, flywheel, and supercapacitor operating nodes is realized, and an integrated energy storage system monitoring network is generated. The monitoring network collects and analyzes the operating data of each energy storage unit in real time, detects abnormalities in a timely manner, and ensures the safe and stable operation of the energy storage system.

[0082] Step S2: Based on the battery operation node, perform EIS measurement on the standard energy storage unit operation data set and collect impedance response to generate battery node impedance response data; construct an equivalent circuit model for the battery node impedance response data to generate a battery equivalent circuit model; perform battery aging analysis on the battery operation node through the battery equivalent circuit model to generate battery node health monitoring data; perform flywheel stability analysis on the standard energy storage unit operation data set based on the flywheel operation node to generate flywheel node health monitoring data;

[0083] In an embodiment of the present invention, by ensuring that the battery operation node is in a stable temperature and humidity environment, the influence of the external environment on the EIS measurement is reduced. From the standard energy storage unit operation data set, select a representative battery operation node, and ensure that the node connection is stable and there is no poor contact. Use a precision calibration instrument to calibrate the electrochemical impedance spectroscopy (EIS) measurement equipment to ensure the accuracy of the measurement data. Set the frequency range (such as from 1mHz to 1kHz) and amplitude voltage (such as 10mV) of the EIS measurement to ensure that the measurement range covers the full frequency domain response of the battery. Set the frequency range (such as from 1mHz to 1kHz) and amplitude voltage (such as 10mV) of the EIS measurement to ensure that the measurement range covers the full frequency domain response of the battery. The collected impedance response data is stored in a dedicated database, and the data is preliminarily cleaned and sorted to remove measurement noise and abnormal data points. Fourier transform the impedance data at different frequencies to separate different electrochemical processes inside the battery, such as electrolyte conductivity, interface resistance, and charge transfer resistance. Extract key characteristic parameters, such as high-frequency resistance (R0), medium-frequency resistance (Rct), and low-frequency diffusion coefficient, to provide a basis for subsequent model construction. Based on the extracted characteristic parameters, design an equivalent circuit model, including basic components (such as resistance, capacitance, inductance) and their connection methods (series or parallel). Use electrochemical analysis software to fit the preliminarily designed circuit model to minimize the error between the model and the actual measured data. Apply the constructed equivalent circuit model to the battery operation nodes under different conditions to verify its accuracy and robustness, and adjust the model parameters when necessary. Compare the battery impedance response data over multiple cycles to identify features related to battery aging, such as increased resistance, decreased capacitance, or slowed reaction kinetics. Based on the changes in the equivalent circuit model and combined with material science knowledge, analyze the main causes of battery aging (such as electrode material degradation, thickening of the interface layer, etc.). Define the battery health index (SoH) based on the battery aging characteristics, such as calculating the health status of each battery node based on the internal resistance growth rate or capacity decay rate, and generate a monitoring report containing information such as health index, aging trend chart, and fault prediction, and support visualization tools for real-time monitoring and diagnosis. Install high-precision accelerometers, gyroscopes, and speed sensors on the flywheel operating nodes to obtain the vibration and speed data of the flywheel. Set a suitable sampling frequency (such as 1kHz) to ensure that the stability changes of the flywheel under different operating conditions can be captured. Analyze the flywheel vibration data through FFT (Fast Fourier Transform), identify the resonant frequency and harmonic components of the flywheel, and evaluate the vibration stability of the flywheel. Calculate the imbalance of the flywheel, and use the model to predict its stability changes at different speeds. Apply machine learning algorithms to detect anomalies in the flywheel operating data, such as sudden amplitude increases or speed fluctuations, to provide early warning of possible failures.Define flywheel health index (SoH), such as based on vibration amplitude or speed fluctuation, to evaluate the health status of flywheel nodes, and generate reports including flywheel health index, stability trend chart, potential failure point analysis and other information to support decision-making and maintenance.

[0084] Step S3: Calculate the capacitor self-discharge rate of the standard energy storage unit operation data set based on the supercapacitor operation node to generate capacitor self-discharge rate data; analyze the internal electrolyte aging rate of the supercapacitor operation node according to the capacitor self-discharge rate data to generate supercapacitor node health monitoring data; integrate the battery node health monitoring data, flywheel node health monitoring data and supercapacitor node health monitoring data to generate node health monitoring short-term data; perform long-term trend prediction on the node health monitoring short-term data to generate integrated energy storage system node long-term health prediction data;

[0085] In an embodiment of the present invention, by extracting key parameters such as voltage, current, and temperature of the supercapacitor operation node from the standard energy storage unit operation data set. After the supercapacitor is fully charged, its initial voltage value V0 is recorded as a reference for calculating the self-discharge rate. Monitor and record the voltage drop VT of the supercapacitor regularly (such as every hour). Considering that the self-discharge rate is affected by temperature, temperature compensation is performed on the voltage data measured each time to ensure the accuracy of the data. The self-discharge rate at each time point is calculated using the formula self-discharge rate = V0-VT / t, where V0 is the initial voltage and VT is the voltage at time t. The self-discharge rates at multiple time points are averaged to obtain more stable self-discharge rate data, and the calculated self-discharge rate data is organized into a report format and stored in a database. According to the self-discharge rate data, characteristic parameters related to electrolyte aging are extracted, such as self-discharge rate growth rate, temperature sensitivity, etc. Based on the physical and chemical properties of the electrolyte, a mathematical model of the electrolyte aging rate is established, considering factors including temperature, voltage stress, and number of cycles. Using the established physical model, combined with the self-discharge rate data, the aging rate of the electrolyte is calculated. According to the aging rate, the health status of the supercapacitor is evaluated and a health index (SoH) is generated to indicate the severity of electrolyte aging. The aging rate and health index of the supercapacitor node are integrated into health monitoring data, and relevant reports and charts are generated. The health monitoring data is input into the real-time monitoring system for continuous monitoring of the operating status of the supercapacitor. The health monitoring data of the battery node, flywheel node and supercapacitor node are aggregated to form a comprehensive node health monitoring data set. The aggregated data is cleaned, outliers are removed, and standardized for subsequent analysis. Short-term time series analysis is performed on the standardized node health monitoring data to extract recent change trends. The analysis results are organized into short-term health monitoring data to reflect the changes in the health status of the energy storage system in a short period of time. A long-term trend prediction model is constructed using machine learning algorithms (such as ARIMA, LSTM, etc.), and the input of the model is the short-term node health monitoring data. The prediction model is trained using historical data and verified using partial data to improve the accuracy and robustness of the prediction. The short-term node health monitoring data is input into the long-term trend prediction model to predict the health status in the future time period. Output prediction results, including health status change trends of each node, potential fault risk assessment, etc., to form long-term health prediction data of the integrated energy storage system nodes. The long-term health prediction data is organized into a report, including prediction curves of future health status, health risk warnings of key nodes, etc.

[0086] Step S4: Detect node anomalies in the integrated energy storage system monitoring network through the long-term health prediction data of the integrated energy storage system nodes and the short-term data of the node health monitoring, and generate normal operation nodes and abnormal operation nodes; perform adaptive repair on the abnormal operation nodes to generate abnormal node repair data; perform system-level health status assessment on the abnormal operation nodes and normal operation nodes according to the abnormal node repair data to generate integrated energy storage system health status detection data;

[0087] In an embodiment of the present invention, the long-term health prediction data of the nodes of the integrated energy storage system and the short-term data of the node health monitoring are input into the abnormal detection module. Using data fusion technology, such as weighted average method or Bayesian fusion, the long-term trend data and the short-term monitoring data are comprehensively processed to generate a unified health status indicator. According to historical data and expert knowledge, the normal threshold range of the health status indicator is set. If the indicator exceeds the threshold, it is considered that the node is abnormal. Advanced machine learning algorithms (such as isolation forests, support vector machines, etc.) are used for anomaly detection to identify abnormal operation nodes with faults or performance degradation. The detected nodes are divided into normal operation nodes and abnormal operation nodes, and corresponding label data are generated to generate a list containing abnormal node information, including node ID, abnormality type, abnormality severity, etc. The distribution and operation status of normal nodes and abnormal nodes are intuitively displayed through charts and dashboards. For the detected abnormal nodes, their fault characteristics, such as voltage instability, temperature abnormality, frequent discharge, etc., are analyzed to determine the fault type. According to the fault type, a suitable adaptive repair strategy is selected, such as parameter adjustment, node restart, load balancing, etc. For abnormalities that can be repaired online, adaptive repairs are performed by adjusting node operating parameters or reallocating tasks. For abnormalities that need to be handled offline, nodes are scheduled to suspend operation for more in-depth detection and repair operations, such as replacing components or performing software upgrades. The repair process is monitored in real time, and changes in various parameters during the repair process are recorded to ensure the repair effect. All operations and results during the repair process are recorded as abnormal node repair data, including information such as whether the repair is successful, the repair time, and the node performance after the repair. A detailed repair report is generated, including comparative data before and after the repair and node performance evaluation. According to the structure and node characteristics of the integrated energy storage system, a system-level health status assessment model is constructed, using methods such as fuzzy logic, hierarchical analysis method (AHP) or Bayesian network. The abnormal node repair data and normal operating node data are input into the system-level health status assessment model for comprehensive analysis. The health status of each node is scored, and the system-level health index (such as system SoH) is calculated based on the scoring results to reflect the health status of the entire energy storage system. Analyze the impact of abnormal nodes on the overall system, evaluate whether the fault will propagate in the system, and predict possible chain reactions. Based on the current health status, the system performance change trend in the future is predicted, early warning information is provided, and a health status detection data report of the integrated energy storage system is generated, including system-level health index, fault node impact analysis, future performance prediction, etc. Based on the health status detection data, system optimization suggestions are put forward, such as node maintenance plan, load redistribution strategy, etc., to help decision makers formulate the next action plan.

[0088] Step S5: Distribute the integrated energy storage system health status detection data to generate energy storage system health status storage data; perform status warning on the integrated energy storage system health status detection data to generate energy storage system health status warning data; perform collaborative feedback on the energy storage system health status storage data and the energy storage system health status warning data to generate integrated energy storage system monitoring feedback data, so as to perform multi-dimensional safety monitoring and warning operations of the integrated energy storage system.

[0089] In the embodiment of the present invention, a suitable distributed database system (such as Cassandra, Hadoop HDFS, MongoDB, etc.) is selected to support high availability and scalability. A data sharding strategy is set to reasonably shard the health status detection data of the energy storage system, and a copy is configured to improve data reliability and access speed. The health status detection data is preprocessed, such as data cleaning, format conversion, etc., to ensure the consistency of data storage. The processed health status detection data is written to the distributed database according to the sharding strategy, and the copy is synchronized to ensure high availability and persistence of the data. A storage monitoring mechanism is set to monitor the health status and performance of the storage system in real time to ensure the stability and security of data storage. A data access interface is designed to allow system users and applications to query and analyze the health status storage data. Access rights and authentication mechanisms are set to ensure that only authorized users can access or modify the health status storage data. Based on the historical analysis and expert knowledge of the health status detection data, health status warning rules are defined, such as abnormal health index thresholds, fault prediction models, etc. The warning model is trained using historical data, and algorithms such as logistic regression, decision trees, or deep learning are used to improve the accuracy of the warning. Monitor health status detection data in real time and apply early warning models to detect whether abnormal situations occur. When abnormal situations or potential risks are detected, generate status warning data, including warning type, severity, recommended measures and other information. Send warning information to relevant personnel through system notifications, emails or text messages to ensure timely response. Record detailed information of each warning event, including time, trigger conditions, handling measures, etc., for subsequent analysis and auditing. Generate early warning reports regularly, summarize statistical data and trend analysis of warning events, and provide support for decision-making. Integrate health status storage data and warning data, and generate collaborative feedback data through data processing platforms (such as ETL tools). Perform collaborative analysis on the integrated data to identify correlations and potential problems in the data and generate comprehensive feedback results. Based on the collaborative analysis results, calculate the monitoring feedback data of the integrated energy storage system, including system health status summary, fault trend, warning response effect, etc. Create a detailed monitoring feedback report, including health status data, warning effect analysis, system optimization suggestions, etc. Based on the feedback data, implement multi-dimensional safety monitoring and early warning operations, including comprehensive performance monitoring, risk assessment, optimization and adjustment, etc. Set up an automated early warning system to monitor system status in real time and automatically perform early warning operations, such as adjusting system configurations, triggering automatic repair processes, etc. Regularly evaluate the effectiveness of monitoring and early warning operations, adjust early warning rules and system parameters, and continuously improve the security and reliability of the system.

[0090] Preferably, step S1 comprises the following steps:

[0091] Step S11: Acquire energy storage system structure data;

[0092] Step S12: Performing energy storage unit analysis on the energy storage system structure data to generate energy storage system energy storage unit data;

[0093] Step S13: using sensors to monitor the energy storage unit data to obtain an energy storage unit operation data set; performing data preprocessing on the energy storage unit operation data set to generate a standard energy storage unit operation data set, wherein the data preprocessing includes data cleaning, data denoising, data normalization and data standardization;

[0094] Step S14: using the energy storage unit data of the energy storage system as nodes to perform data monitoring network integration through a standard energy storage unit operation data set to generate an integrated energy storage system monitoring network, wherein the integrated energy storage system monitoring network includes a battery operation node, a flywheel operation node, and a supercapacitor operation node.

[0095] In an embodiment of the present invention, detailed structural data of the energy storage system is collected, including information such as the configuration, layout, and connection mode of energy storage units such as batteries, flywheels, and supercapacitors. These data are usually from system design documents, engineering drawings, and equipment specifications. Each energy storage unit (such as a battery pack, flywheel, and capacitor) in the energy storage system structural data is classified to identify its type, model, and function. Each energy storage unit is analyzed in detail to generate relevant data of the energy storage unit, including its electrical characteristics, capacity, operating parameters, etc. These data form the energy storage unit data of the energy storage system. Sensors are installed on each energy storage unit of the energy storage system to monitor the operating status of the unit in real time. These sensors can measure indicators such as current, voltage, temperature, and health status. Real-time operating data is collected through sensors to form an energy storage unit operating data set. The collected energy storage unit operating data set is preprocessed to generate a standard energy storage unit operating data set. Data preprocessing includes: removing noise, errors, and outliers to ensure data accuracy, applying a denoising algorithm to reduce noise interference in the signal, standardizing the data to a unified scale range for comparison and analysis, and converting the data into a standard format to ensure its consistency and availability. Based on the standard energy storage unit operation data set, the data of each energy storage unit in the energy storage system is integrated into a monitoring network as a node. The battery operation node monitors the status and performance of the battery pack, the flywheel operation node monitors the operating status and health of the flywheel, and the supercapacitor operation node: monitors the operation and efficiency of the supercapacitor. The integrated energy storage system monitoring network integrates the monitoring data of all energy storage units to provide comprehensive monitoring and data analysis support for the operation of the system.

[0096] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0097] Step S21: screening battery characteristic data of a standard energy storage unit operation data set based on a battery operation node to obtain battery operation characteristic data;

[0098] Step S22: setting the AC signal amplitude according to the battery operation characteristic data to obtain AC signal amplitude setting data; performing EIS measurement on the battery operation node and collecting impedance response according to the AC signal amplitude setting data to generate battery node impedance response data;

[0099] Step S23: Perform Nyquist diagram conversion on the battery node impedance response data to generate a battery response Nyquist diagram; construct an equivalent circuit model for the battery response Nyquist diagram to generate a battery equivalent circuit model; perform battery aging analysis on the battery operation node through the battery equivalent circuit model to generate battery node health monitoring data;

[0100] Step S24: based on the flywheel operation node, the flywheel motion characteristic data of the standard energy storage unit operation data set is screened to obtain the flywheel motion characteristic data; the flywheel motion characteristic data is subjected to flywheel stability analysis to generate flywheel node health monitoring data.

[0101] In an embodiment of the present invention, characteristic data related to the battery are extracted from a standard energy storage unit operation data set, and these characteristics include battery voltage, current, temperature, charge and discharge cycle, capacity, etc. Representative battery characteristic data are screened out by an algorithm or data analysis method, focusing on key indicators that affect battery performance, and generating battery operation characteristic data. The amplitude setting range of the AC signal is determined according to the battery operation characteristic data. Ensure that the selected amplitude can effectively reflect the impedance characteristics of the battery. The determined AC signal amplitude range is recorded as the AC signal amplitude setting data. Electrochemical impedance spectroscopy (EIS) is measured on the battery operation node using the AC signal amplitude setting data. An AC signal is applied using an instrument or device and the response of the battery is measured. The impedance response data of the battery node is recorded, and these data contain the impedance characteristics of the battery at different frequencies. The impedance response data of the battery node is converted into a Nyquist diagram. The Nyquist diagram shows the relationship between the real and imaginary parts of the impedance as the frequency changes. The battery response Nyquist diagram is generated by a software tool or a graphics processing tool. According to the characteristics of the Nyquist diagram, a suitable equivalent circuit model is selected, such as the Randles circuit model. By fitting the Nyquist plot data, the resistance, capacitance, inductance and other parameters in the equivalent circuit model are determined, and the equivalent circuit model of the battery is established for further analysis. The equivalent circuit model is used to analyze the aging of the battery and check the degradation trend of the battery performance. Based on the aging analysis results, the health monitoring data of the battery node is generated, including indicators such as the remaining life and health status of the battery. The motion characteristic data related to the flywheel is extracted from the standard energy storage unit operation data set, including speed, torque, vibration, temperature, etc. The key flywheel motion characteristic data is screened out through data analysis methods to generate flywheel motion characteristic data. According to the flywheel motion characteristic data, the stability of the flywheel is analyzed, including vibration analysis, speed fluctuation, etc. Based on the stability analysis results, the health monitoring data of the flywheel node is generated, including the health status of the flywheel, stability evaluation, etc.

[0102] Preferably, step S24 includes the following steps:

[0103] Step S241: screening the flywheel motion characteristic data of the standard energy storage unit operation data set based on the flywheel operation node to obtain the flywheel motion characteristic data, wherein the flywheel motion characteristic data includes the flywheel speed data and the flywheel vibration data;

[0104] Step S242: performing fast Fourier transform on the flywheel speed data and the flywheel vibration data to generate a flywheel vibration spectrum diagram; performing abnormal change spectrum analysis on the flywheel vibration spectrum diagram to generate flywheel abnormal vibration spectrum data; performing time domain analysis on the flywheel abnormal vibration spectrum data to generate flywheel abnormal vibration time domain data;

[0105] Step S243: collecting the flywheel bearing acoustic waves at the flywheel operation nodes according to the time domain of the flywheel abnormal vibration to obtain the flywheel bearing acoustic wave data; constructing an acoustic emission event spectrum for the flywheel bearing acoustic wave data to generate a flywheel bearing acoustic emission event spectrum;

[0106] Step S244: analyzing the flywheel operation energy change of the flywheel operation node through the flywheel bearing acoustic emission event spectrum to generate flywheel node health monitoring data.

[0107] In an embodiment of the present invention, the motion characteristic data related to the flywheel is extracted from the standard energy storage unit operation data set. It includes: recording the real-time speed data of the flywheel, recording the vibration data of the flywheel, which is usually obtained by a vibration sensor installed on the flywheel. The extracted flywheel motion characteristic data is screened to ensure data quality and accuracy, including removing noise, processing outliers, etc. The flywheel vibration data is fast Fourier transformed and converted into frequency domain data, and a flywheel vibration spectrum is drawn to show the distribution of the vibration signal in the frequency domain. The abnormal changes in the spectrum are analyzed, the abnormal spectrum components are identified, and the flywheel abnormal vibration spectrum data is generated. The abnormal vibration spectrum data is analyzed in the time domain, the time characteristics of the abnormal signal are studied, and the flywheel abnormal vibration time domain data is generated. The flywheel bearing is subjected to acoustic wave collection using an acoustic wave sensor (such as an acoustic emission sensor), and the acoustic wave data of the flywheel bearing is recorded to reflect the operating status and abnormality of the bearing. The collected acoustic wave data is analyzed to generate an acoustic emission event spectrum. The spectrum shows the time series distribution and intensity of the acoustic emission event. By analyzing the acoustic emission event spectrum of the flywheel bearing, the energy changes of the flywheel under different operating conditions are studied. Based on the analysis results, health monitoring data of the flywheel node is generated. These data include the health status assessment of the flywheel, the change of operating energy, etc., to help determine whether there are potential problems with the flywheel.

[0108] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0109] Step S31: Screening capacitor characteristic data of a standard energy storage unit operation data set based on a supercapacitor operation node to obtain capacitor operation characteristic data;

[0110] Step S32: extracting voltage characteristic data of the capacitor operation characteristic data, and calculating the capacitor self-discharge rate on the voltage characteristic data to generate capacitor self-discharge rate data;

[0111] Step S33: analyzing the voltage drop rate of the supercapacitor operation node under static conditions according to the capacitor self-discharge rate data to generate capacitor voltage drop rate data; analyzing the internal electrolyte aging rate of the supercapacitor operation node according to the capacitor voltage drop rate to generate supercapacitor node health monitoring data;

[0112] Step S34: Integrate the battery node health monitoring data, flywheel node health monitoring data and supercapacitor node health monitoring data to generate short-term node health monitoring data; perform long-term trend prediction on the short-term node health monitoring data to generate long-term health prediction data for the integrated energy storage system nodes.

[0113] In an embodiment of the present invention, characteristic data related to supercapacitors are extracted from a standard energy storage unit operation data set, and these characteristics include capacitor voltage, current, temperature, charge and discharge cycles, etc. The extracted data is screened to ensure that the selected data reflects the actual operating state of the capacitor, and capacitor operation characteristic data is generated. Voltage characteristic data is extracted from the capacitor operation characteristic data, including the voltage value of the capacitor at different time points. The self-discharge rate refers to the natural rate of voltage drop of the capacitor when no current is applied. The self-discharge rate is calculated using the data of the capacitor voltage change over time to generate capacitor self-discharge rate data, which can be achieved through statistical analysis or fitting models. When the capacitor is kept static (not charged or discharged), the voltage drop rate is analyzed. The capacitor self-discharge rate data can be used for this analysis. The rate at which the capacitor voltage drops under static conditions is calculated to generate capacitor voltage drop rate data. According to the capacitor voltage drop rate data, the aging rate of the electrolyte inside the capacitor is analyzed. A faster voltage drop rate indicates that the electrolyte ages faster. Based on the analysis results, health monitoring data of the supercapacitor node is generated to evaluate the aging state and overall health level of the capacitor. Integrate the battery node health monitoring data, flywheel node health monitoring data, and supercapacitor node health monitoring data to generate short-term node health monitoring data, which includes the current health status and performance indicators of each node. Use historical data and current short-term node health monitoring data to perform long-term trend forecasting, involving time series analysis, regression analysis, or machine learning models. Based on long-term trend forecasting, generate long-term health forecasting data for the nodes of the integrated energy storage system. This data provides an expectation of the overall health status of the energy storage system in the future and helps formulate maintenance and optimization strategies.

[0114] Preferably, step S34 includes the following steps:

[0115] Step S341: integrating the battery node health monitoring data, the flywheel node health monitoring data and the supercapacitor node health monitoring data to generate node health monitoring short-term data;

[0116] Step S342: performing data dimensionality reduction on the node health monitoring short-term data to generate node health monitoring dimensionality reduction data; dividing the node health monitoring dimensionality reduction data into data sets to generate a model training set and a model test set;

[0117] Step S343: Perform model training on the model training set through a recursive neural network algorithm to generate a node health long-term trend prediction model; perform dilation convolution on the node health long-term regional prediction model using the model test set based on the attention mechanism to generate a node health long-term trend prediction model;

[0118] Step S344: Import the short-term node health monitoring data into the node health long-term trend prediction model to perform long-term trend prediction, and generate the integrated energy storage system node long-term health prediction data.

[0119] In an embodiment of the present invention, the battery node health monitoring data, the flywheel node health monitoring data and the supercapacitor node health monitoring data are integrated. The integrated data forms node health monitoring short-term data, which includes the current health status, performance indicators and operating parameters of all nodes. Dimensionality reduction techniques (such as principal component analysis (PCA), t-SNE, etc.) are applied to reduce the dimension of the node health monitoring short-term data. Dimensionality reduction aims to reduce the complexity of the data while retaining the most important features. The data after dimension reduction is called node health monitoring dimension reduction data, which has a lower dimension and can be better analyzed later. The node health monitoring dimension reduction data is divided into a model training set and a model test set. Generally, the training set is used for learning and training the model, while the test set is used to evaluate the performance of the model. Create a model training set and a model test set for subsequent model training and testing. The model training set is trained using a recursive neural network (such as a long short-term memory network (LSTM) or a gated recursive unit (GRU)). RNN is suitable for processing time series data and can capture the time series features in the data. After training, a node health long-term trend pre-model is generated. This model is used to predict the long-term trend of node health status. Based on the attention mechanism, the model test set is dilated and convolved. The attention mechanism can help the model focus on the most important information in the data. Through dilated convolution, a node health long-term trend prediction model is generated, which can more accurately capture the long-term change trend of node health status. The short-term node health monitoring data is input into the node health long-term trend prediction model. Using the trained prediction model, the input data is predicted for the long-term trend. Based on the model output, the long-term health prediction data of the integrated energy storage system node is generated. This data provides the expected health status of the energy storage system in the future, which helps to detect potential problems in advance and formulate maintenance strategies.

[0120] Preferably, step S4 comprises the following steps:

[0121] Step S41: performing node anomaly detection on the integrated energy storage system monitoring network through the long-term health prediction data of the integrated energy storage system nodes and the short-term health monitoring data of the nodes, and generating normal operation nodes and abnormal operation nodes;

[0122] Step S42: performing node association analysis on the abnormal operation node to generate abnormal operation node association data; performing node fault linkage analysis on the abnormal operation node through the abnormal operation node association data to generate abnormal node fault linkage data;

[0123] Step S43: Adaptively repair the abnormal operation node based on the abnormal node fault linkage data to generate abnormal node repair data;

[0124] Step S44: Perform system-level health status assessment on abnormal operation nodes and normal operation nodes according to the abnormal node repair data to generate integrated energy storage system health status detection data.

[0125] In an embodiment of the present invention, the long-term health prediction data of the nodes of the integrated energy storage system and the short-term data of the node health monitoring are input into the monitoring network of the integrated energy storage system. The monitoring network processes the input data and identifies the operating status of the node in combination with the prediction data and the short-term data. An abnormal detection algorithm, such as a statistical method, a machine learning algorithm or a deep learning model, is applied to identify abnormal operation nodes in the system. According to the detection results, normal operation nodes and abnormal operation nodes are distinguished, and a data list or identification of normal operation nodes and abnormal operation nodes is generated. An association analysis is performed on the abnormal operation nodes to study the relationship between these nodes and their impact on the system, and the association data of the abnormal operation nodes is generated, including information such as the relationship between the nodes, the degree of impact and potential common cause failures. Based on the association data of the abnormal operation nodes, node fault linkage analysis is performed, including identifying the fault propagation path and linkage effect between abnormal nodes, generating abnormal node fault linkage data, and displaying the propagation and linkage effect of the fault in the system. Based on the abnormal node fault linkage data, an adaptive repair strategy is formulated, which includes adjusting system parameters, replacing faulty components, optimizing operation modes, etc., and repair data for abnormal operation nodes is generated, including specific repair measures and steps. According to the repair plan, perform adaptive repair operations on abnormal operation nodes, record the repair process and results, and generate abnormal node repair data. Integrate the abnormal node repair data with the data of normal operation nodes and abnormal operation nodes. Apply the system-level health status assessment algorithm or model to perform health status detection on the entire integrated energy storage system, including evaluating the repair effect and the health level of the overall system, and generate integrated energy storage system health status detection data, which includes the current health status of the system, the repair effect of abnormal nodes, and the overall operation status of the system.

[0126] Preferably, step S43 includes the following steps:

[0127] Step S431: performing Monte Carlo simulation on the abnormal operation node based on the abnormal node fault linkage data to generate abnormal node fault propagation simulation data;

[0128] Step S432: performing operation collapse calculation on the integrated energy storage system monitoring network through abnormal node fault propagation simulation data to generate system collapse rate occurrence data;

[0129] Step S433: comparing the system crash rate data with a preset system crash threshold, when the system crash rate data is greater than or equal to the preset system crash threshold, selecting a redundant backup system for the corresponding abnormal operation node, and generating a redundant backup system repair strategy;

[0130] Step S434: When the system crash rate data is less than the preset system crash threshold, the corresponding abnormal operation node is isolated and recovered to generate a fault isolation recovery strategy; the abnormal operation node is adaptively repaired according to the redundant backup system repair strategy and the fault isolation recovery strategy to generate abnormal node repair data.

[0131] In an embodiment of the present invention, by collecting abnormal node fault linkage data, including the fault propagation path and impact between nodes. Set the parameters of the Monte Carlo simulation, such as the number of simulations, the fault propagation model, etc. Perform Monte Carlo simulation on the abnormal operation node. This method generates simulation data of abnormal node fault propagation through random sampling and repeated simulation. The simulation process takes into account various possible fault propagation paths and impacts, and generates abnormal node fault propagation simulation data. These data show the propagation behavior and consequences of the fault in the system. Input the abnormal node fault propagation simulation data into the system collapse calculation model. These models can be based on the structure of the system, the relationship between nodes and the law of fault propagation. Perform operation collapse calculation on the integrated energy storage system to evaluate the impact of fault propagation on system stability. Calculate the collapse rate of the system under fault propagation, and generate system collapse rate occurrence data. These data represent the probability or occurrence rate of system collapse under the conditions of simulated fault propagation. Set a system collapse threshold for judging the stability of the system. This threshold can be based on the fault tolerance and reliability requirements of the system. Compare the system collapse rate occurrence data with the preset system collapse threshold. If the system collapse rate occurrence data is greater than or equal to the preset system collapse threshold, select a redundant backup system for the abnormal operation node. Select a redundant backup system and generate a redundant backup system repair strategy to improve the reliability and fault tolerance of the system. If the system crash rate data is less than the preset system crash threshold, proceed to the next step of fault isolation and recovery analysis. Perform fault isolation and recovery on abnormal operation nodes, including isolating the faulty node from the system to reduce its impact on other parts of the system, and perform necessary repair operations to generate a fault isolation and recovery strategy to ensure the stability of the system. According to the redundant backup system repair strategy and the fault isolation and recovery strategy, adaptively repair the abnormal operation nodes respectively. Record the repair process and results, and generate abnormal node repair data, which includes the implementation of the repair measures and the repair effect.

[0132] Preferably, step S5 comprises the following steps:

[0133] Step S51: using blockchain technology to perform distributed storage of the integrated energy storage system health status detection data to generate energy storage system health status storage data;

[0134] Step S52: Performing status warning on the stored data of the health status of the energy storage system to generate health status warning data of the energy storage system;

[0135] Step S53: Transmit the energy storage system health status storage data and the energy storage system health status warning data to the central monitoring system for collaborative feedback, generate integrated energy storage system monitoring feedback data, and perform multi-dimensional safety monitoring and warning operations of the integrated energy storage system.

[0136] In an embodiment of the present invention, the health status detection data of the integrated energy storage system is organized into a format that can be used for blockchain storage. Ensure the integrity and consistency of the data for easy storage and subsequent processing. Build a suitable blockchain network for distributed storage. You can choose a public chain, a private chain or a consortium chain, depending on the needs and security requirements of the system. Use blockchain technology to store the health status detection data of the energy storage system in a distributed manner in the blockchain network. The data writing process includes operations such as data encryption, packaging into blocks, and adding to the chain to generate energy storage system health status storage data, which has the characteristics of being tamper-proof and traceable on the blockchain. Set thresholds and rules for energy storage system health status warning. For example, set upper and lower limits of health indicators, and trigger warnings when these values ​​are exceeded. Use data analysis and warning algorithms to analyze the energy storage system health status storage data and identify potential anomalies and risks. Analyze the health status storage data and generate energy storage system health status warning data according to preset thresholds and rules, including warning types, risk levels, and recommended measures. Transmit the energy storage system health status storage data and health status warning data to the central monitoring system through a secure transmission channel. Ensure the security and integrity of data during transmission. The central monitoring system receives and integrates health status storage data and warning data. The central monitoring system conducts a comprehensive analysis of the received data and generates integrated energy storage system monitoring feedback data. The feedback data includes a comprehensive evaluation of the health status, risk warning processing suggestions and system optimization solutions. Based on the integrated energy storage system monitoring feedback data, perform multi-dimensional safety monitoring and warning operations. Including real-time monitoring, trend analysis, risk assessment and emergency response. According to the monitoring feedback data, implement corresponding warning measures and system adjustments to ensure the safe and stable operation of the energy storage system.

[0137] In this specification, a multi-dimensional safety early warning system of an integrated energy storage system is provided, which is used to execute the multi-dimensional safety monitoring method of the integrated energy storage system. The multi-dimensional safety early warning system of the integrated energy storage system includes:

[0138] The energy storage unit division module is used to obtain the energy storage system structure data; perform energy storage unit analysis on the energy storage system structure data to generate energy storage system energy storage unit data; perform unit operation data monitoring on the energy storage unit data to obtain an energy storage unit operation data set; perform data monitoring network integration through the energy storage system energy storage unit data and the energy storage unit operation data set to generate an integrated energy storage system monitoring network, wherein the integrated energy storage system monitoring network includes battery operation nodes, flywheel operation nodes, and supercapacitor operation nodes;

[0139] The battery flywheel node analysis module is used to perform EIS measurement on the standard energy storage unit operation data set based on the battery operation node and collect impedance response to generate battery node impedance response data; construct an equivalent circuit model for the battery node impedance response data to generate a battery equivalent circuit model; perform battery aging analysis on the battery operation node through the battery equivalent circuit model to generate battery node health monitoring data; perform flywheel stability analysis on the standard energy storage unit operation data set based on the flywheel operation node to generate flywheel node health monitoring data;

[0140] The capacitor node analysis module is used to calculate the capacitor self-discharge rate of the standard energy storage unit operation data set based on the supercapacitor operation node to generate capacitor self-discharge rate data; analyze the internal electrolyte aging rate of the supercapacitor operation node based on the capacitor self-discharge rate data to generate supercapacitor node health monitoring data; integrate the battery node health monitoring data, flywheel node health monitoring data and supercapacitor node health monitoring data to generate node health monitoring short-term data; perform long-term trend prediction on the node health monitoring short-term data to generate integrated energy storage system node long-term health prediction data;

[0141] The abnormal node repair module is used to detect node anomalies in the integrated energy storage system monitoring network through the long-term health prediction data of the integrated energy storage system nodes and the short-term data of node health monitoring, and generate normal operation nodes and abnormal operation nodes; perform adaptive repair on abnormal operation nodes and generate abnormal node repair data; perform system-level health status assessment on abnormal operation nodes and normal operation nodes according to the abnormal node repair data, and generate integrated energy storage system health status detection data;

[0142] The health warning module is used to perform distributed storage of the health status detection data of the integrated energy storage system to generate the health status storage data of the energy storage system; to perform status warning on the health status detection data of the integrated energy storage system to generate the health status warning data of the energy storage system; to perform collaborative feedback on the health status storage data of the energy storage system and the health status warning data of the energy storage system to generate the monitoring feedback data of the integrated energy storage system, so as to perform multi-dimensional safety monitoring and warning operations of the integrated energy storage system.

[0143] The beneficial effect of the present invention is that by acquiring the structural data of the energy storage system and performing energy storage unit analysis, operation data monitoring and data monitoring network integration, an integrated energy storage system monitoring network including batteries, flywheels and supercapacitors is constructed, ensuring real-time monitoring and data integration of each energy storage unit in the system, and providing basic data support for subsequent health monitoring. By performing EIS measurement on battery nodes, battery aging analysis, and stability analysis on flywheel nodes, health monitoring data of each energy storage unit is generated, which effectively improves the ability to accurately evaluate battery aging and flywheel stability, and lays the foundation for preventive maintenance of the system. By calculating the self-discharge rate of the supercapacitor and analyzing the aging rate of its internal electrolyte, health monitoring data is generated, and long-term trend prediction is performed in combination with short-term data, which helps to discover and prevent potential capacitor performance degradation problems early and improves the overall health monitoring accuracy of the system. By performing node anomaly detection and adaptive repair through long-term health prediction data and short-term health monitoring data, abnormal operation nodes in the energy storage system can be identified and repaired in a timely manner, and system-level health status evaluation can be performed to ensure stable operation and extend the life of the energy storage system. By distributing the health status detection data, performing status warning and collaborative feedback, the system's multi-dimensional safety monitoring and warning functions are realized, ensuring early warning and rapid response before a failure occurs, and improving the overall safety and reliability of the energy storage system. Therefore, the present invention improves the comprehensiveness, real-timeness and fault prediction capabilities of the existing integrated energy storage system safety monitoring by introducing multi-dimensional monitoring, real-time data analysis and artificial intelligence technology.

[0144] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0145] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A multi-dimensional safety monitoring method for an integrated energy storage system, characterized in that: The following steps are involved: Step S1: Obtaining energy storage system structure data; Perform energy storage unit analysis on the energy storage system structure data to generate energy storage unit data of the energy storage system; Perform unit operation data monitoring on energy storage unit data to obtain an energy storage unit operation data set; The data monitoring network is integrated through the energy storage unit data and the energy storage unit operation data set of the energy storage system to generate an integrated energy storage system monitoring network, wherein the integrated energy storage system monitoring network includes a battery operation node, a flywheel operation node and a supercapacitor operation node; Step S2: Based on the battery operation node, perform EIS measurement on the standard energy storage unit operation data set and collect impedance response to generate battery node impedance response data; construct an equivalent circuit model for the battery node impedance response data to generate a battery equivalent circuit model; perform battery aging analysis on the battery operation node through the battery equivalent circuit model to generate battery node health monitoring data; perform flywheel stability analysis on the standard energy storage unit operation data set based on the flywheel operation node to generate flywheel node health monitoring data; Step S3: Calculate the capacitor self-discharge rate for the standard energy storage unit operation data set based on the supercapacitor operation node to generate capacitor self-discharge rate data; Analyze the internal electrolyte aging rate of the supercapacitor operation node based on the capacitor self-discharge rate data to generate supercapacitor node health monitoring data; Integrate the battery node health monitoring data, flywheel node health monitoring data and supercapacitor node health monitoring data to generate node health monitoring short-term data; Carry out long-term trend prediction on short-term node health monitoring data to generate long-term health prediction data of integrated energy storage system nodes; Step S4: Detect node anomalies in the integrated energy storage system monitoring network through the long-term health prediction data of the integrated energy storage system nodes and the short-term health monitoring data of the nodes, and generate normal operation nodes and abnormal operation nodes; Adaptively repair abnormal running nodes and generate abnormal node repair data; Perform system-level health status assessment on abnormal and normal operating nodes based on abnormal node repair data, and generate health status detection data for the integrated energy storage system; Step S5: Distribute the integrated energy storage system health status detection data to generate energy storage system health status storage data; perform status warning on the integrated energy storage system health status detection data to generate energy storage system health status warning data; The energy storage system health status storage data and energy storage system health status warning data are collaboratively fed back to generate integrated energy storage system monitoring feedback data to perform multi-dimensional safety monitoring and early warning operations of the integrated energy storage system.

2. The multi-dimensional safety monitoring method of the integrated energy storage system according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire energy storage system structure data; Step S12: Performing energy storage unit analysis on the energy storage system structure data to generate energy storage system energy storage unit data; Step S13: using sensors to monitor the energy storage unit data to obtain an energy storage unit operation data set; performing data preprocessing on the energy storage unit operation data set to generate a standard energy storage unit operation data set, wherein the data preprocessing includes data cleaning, data denoising, data normalization and data standardization; Step S14: using the energy storage unit data of the energy storage system as nodes to perform data monitoring network integration through a standard energy storage unit operation data set to generate an integrated energy storage system monitoring network, wherein the integrated energy storage system monitoring network includes a battery operation node, a flywheel operation node, and a supercapacitor operation node.

3. The multi-dimensional safety monitoring method for an integrated energy storage system according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: screening battery characteristic data of a standard energy storage unit operation data set based on a battery operation node to obtain battery operation characteristic data; Step S22: setting the AC signal amplitude according to the battery operation characteristic data to obtain AC signal amplitude setting data; performing EIS measurement on the battery operation node and collecting impedance response according to the AC signal amplitude setting data to generate battery node impedance response data; Step S23: Perform Nyquist diagram conversion on the battery node impedance response data to generate a battery response Nyquist diagram; construct an equivalent circuit model for the battery response Nyquist diagram to generate a battery equivalent circuit model; perform battery aging analysis on the battery operation node through the battery equivalent circuit model to generate battery node health monitoring data; Step S24: based on the flywheel operation node, the flywheel motion characteristic data of the standard energy storage unit operation data set is screened to obtain the flywheel motion characteristic data; the flywheel motion characteristic data is subjected to flywheel stability analysis to generate flywheel node health monitoring data.

4. The multi-dimensional safety monitoring method of the integrated energy storage system according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: screening the flywheel motion characteristic data of the standard energy storage unit operation data set based on the flywheel operation node to obtain the flywheel motion characteristic data, wherein the flywheel motion characteristic data includes the flywheel speed data and the flywheel vibration data; Step S242: performing fast Fourier transform on the flywheel speed data and the flywheel vibration data to generate a flywheel vibration spectrum diagram; performing abnormal change spectrum analysis on the flywheel vibration spectrum diagram to generate flywheel abnormal vibration spectrum data; performing time domain analysis on the flywheel abnormal vibration spectrum data to generate flywheel abnormal vibration time domain data; Step S243: collecting the flywheel bearing acoustic waves at the flywheel operation nodes according to the time domain of the flywheel abnormal vibration to obtain the flywheel bearing acoustic wave data; constructing an acoustic emission event spectrum for the flywheel bearing acoustic wave data to generate a flywheel bearing acoustic emission event spectrum; Step S244: analyzing the flywheel operation energy change of the flywheel operation node through the flywheel bearing acoustic emission event spectrum to generate flywheel node health monitoring data.

5. The multi-dimensional safety monitoring method of an integrated energy storage system according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Screening capacitor characteristic data of a standard energy storage unit operation data set based on a supercapacitor operation node to obtain capacitor operation characteristic data; Step S32: extracting voltage characteristic data of the capacitor operation characteristic data, and calculating the capacitor self-discharge rate on the voltage characteristic data to generate capacitor self-discharge rate data; Step S33: analyzing the voltage drop rate of the supercapacitor operation node under static conditions according to the capacitor self-discharge rate data to generate capacitor voltage drop rate data; analyzing the internal electrolyte aging rate of the supercapacitor operation node according to the capacitor voltage drop rate to generate supercapacitor node health monitoring data; Step S34: Integrate the battery node health monitoring data, flywheel node health monitoring data and supercapacitor node health monitoring data to generate short-term node health monitoring data; perform long-term trend prediction on the short-term node health monitoring data to generate long-term health prediction data for the integrated energy storage system nodes.

6. The multi-dimensional safety monitoring method of the integrated energy storage system according to claim 5, characterized in that: Step S34 includes the following steps: Step S341: integrating the battery node health monitoring data, the flywheel node health monitoring data and the supercapacitor node health monitoring data to generate node health monitoring short-term data; Step S342: performing data dimensionality reduction on the node health monitoring short-term data to generate node health monitoring dimensionality reduction data; dividing the node health monitoring dimensionality reduction data into data sets to generate a model training set and a model test set; Step S343: Perform model training on the model training set through a recursive neural network algorithm to generate a node health long-term trend prediction model; perform dilation convolution on the node health long-term regional prediction model using the model test set based on the attention mechanism to generate a node health long-term trend prediction model; Step S344: Import the short-term node health monitoring data into the node health long-term trend prediction model to perform long-term trend prediction, and generate the integrated energy storage system node long-term health prediction data.

7. The multi-dimensional safety monitoring method for an integrated energy storage system according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing node anomaly detection on the integrated energy storage system monitoring network through the long-term health prediction data of the integrated energy storage system nodes and the short-term health monitoring data of the nodes, and generating normal operation nodes and abnormal operation nodes; Step S42: performing node association analysis on the abnormal operation node to generate abnormal operation node association data; performing node fault linkage analysis on the abnormal operation node through the abnormal operation node association data to generate abnormal node fault linkage data; Step S43: Adaptively repair the abnormal operation node based on the abnormal node fault linkage data to generate abnormal node repair data; Step S44: Perform system-level health status assessment on abnormal operation nodes and normal operation nodes according to the abnormal node repair data to generate integrated energy storage system health status detection data.

8. The multi-dimensional safety monitoring method for an integrated energy storage system according to claim 7, characterized in that: Step S43 includes the following steps: Step S431: performing Monte Carlo simulation on the abnormal operation node based on the abnormal node fault linkage data to generate abnormal node fault propagation simulation data; Step S432: performing operation collapse calculation on the integrated energy storage system monitoring network through abnormal node fault propagation simulation data to generate system collapse rate occurrence data; Step S433: comparing the system crash rate data with a preset system crash threshold, when the system crash rate data is greater than or equal to the preset system crash threshold, selecting a redundant backup system for the corresponding abnormal operation node, and generating a redundant backup system repair strategy; Step S434: When the system crash rate data is less than the preset system crash threshold, the corresponding abnormal operation node is isolated and recovered to generate a fault isolation recovery strategy; the abnormal operation node is adaptively repaired according to the redundant backup system repair strategy and the fault isolation recovery strategy to generate abnormal node repair data.

9. The multi-dimensional safety monitoring method for an integrated energy storage system according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: using blockchain technology to perform distributed storage of the integrated energy storage system health status detection data to generate energy storage system health status storage data; Step S52: Performing status warning on the stored data of the health status of the energy storage system to generate health status warning data of the energy storage system; Step S53: Transmit the energy storage system health status storage data and the energy storage system health status warning data to the central monitoring system for collaborative feedback, generate integrated energy storage system monitoring feedback data, and perform multi-dimensional safety monitoring and warning operations of the integrated energy storage system.

10. A multi-dimensional safety warning system for an integrated energy storage system, characterized in that: For executing the multi-dimensional safety monitoring method of the integrated energy storage system according to claim 1, the multi-dimensional safety early warning system of the integrated energy storage system comprises: The energy storage unit division module is used to obtain the energy storage system structure data; perform energy storage unit analysis on the energy storage system structure data to generate energy storage system energy storage unit data; perform unit operation data monitoring on the energy storage unit data to obtain an energy storage unit operation data set; perform data monitoring network integration through the energy storage system energy storage unit data and the energy storage unit operation data set to generate an integrated energy storage system monitoring network, wherein the integrated energy storage system monitoring network includes battery operation nodes, flywheel operation nodes, and supercapacitor operation nodes; The battery flywheel node analysis module is used to perform EIS measurement on the standard energy storage unit operation data set based on the battery operation node and collect impedance response to generate battery node impedance response data; construct an equivalent circuit model for the battery node impedance response data to generate a battery equivalent circuit model; perform battery aging analysis on the battery operation node through the battery equivalent circuit model to generate battery node health monitoring data; perform flywheel stability analysis on the standard energy storage unit operation data set based on the flywheel operation node to generate flywheel node health monitoring data; The capacitor node analysis module is used to calculate the capacitor self-discharge rate of the standard energy storage unit operation data set based on the supercapacitor operation node to generate capacitor self-discharge rate data; analyze the internal electrolyte aging rate of the supercapacitor operation node based on the capacitor self-discharge rate data to generate supercapacitor node health monitoring data; integrate the battery node health monitoring data, flywheel node health monitoring data and supercapacitor node health monitoring data to generate node health monitoring short-term data; perform long-term trend prediction on the node health monitoring short-term data to generate integrated energy storage system node long-term health prediction data; The abnormal node repair module is used to detect node anomalies in the integrated energy storage system monitoring network through the long-term health prediction data of the integrated energy storage system nodes and the short-term data of node health monitoring, and generate normal operation nodes and abnormal operation nodes; perform adaptive repair on abnormal operation nodes and generate abnormal node repair data; perform system-level health status assessment on abnormal operation nodes and normal operation nodes according to the abnormal node repair data, and generate integrated energy storage system health status detection data; The health warning module is used to perform distributed storage of the health status detection data of the integrated energy storage system to generate the health status storage data of the energy storage system; to perform status warning on the health status detection data of the integrated energy storage system to generate the health status warning data of the energy storage system; to perform collaborative feedback on the health status storage data of the energy storage system and the health status warning data of the energy storage system to generate the monitoring feedback data of the integrated energy storage system, so as to perform multi-dimensional safety monitoring and warning operations of the integrated energy storage system.

Images