Energy storage system supporting capacity evaluation model construction method and system

Abstract

The invention relates to the technical field of risk assessment, in particular to an energy storage system supporting capacity assessment model construction method and system. The method comprises the following steps: acquiring structural data of the energy storage system and modeling a topological structure of the energy storage system to obtain a topological structure model of the energy storage system; energy storage system operation data and energy storage system sensing data are obtained and fused, and an energy storage system sensing network is obtained; performing mode identification based on the operation data of the energy storage system to obtain electrical operation mode data of the energy storage system, and performing mode integration to obtain system operation sensing fluctuation mode data; detecting system operation sensing fluctuation mode data to obtain abnormal sensing fluctuation detection data, and evaluating the abnormal sensing fluctuation detection data to obtain energy storage system supporting capability score data; and constructing an energy storage system supporting capability evaluation model based on the abnormal sensing fluctuation detection data and the energy storage system supporting capability score data. According to the method, the accuracy of energy storage system supporting capacity quantification can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of risk assessment, and in particular to a method and system for constructing a support capability assessment model for an energy storage system. Background Art

[0002] In the context of the global energy structure transformation, energy storage technology has received increasing attention as an important means to improve the utilization rate of renewable energy. Energy storage systems play an important role in balancing supply and demand and improving the stability and reliability of the power grid. Therefore, evaluating their support capabilities has become one of the research focuses. Previous evaluation methods often regard energy storage systems as a single component and lack a comprehensive analysis of the overall performance of the system. This one-sided evaluation may lead to the failure of energy storage systems to achieve the expected support capabilities in practical applications. For example, some traditional models may underestimate the discharge capacity of energy storage systems during peak loads, resulting in the inability to meet the needs of the power grid at critical moments. Another significant defect is the lack of dynamics and real-time performance. Traditional evaluation methods are usually based on static analysis and fail to respond to changes in grid conditions and fluctuations in renewable energy generation in a timely manner. For example, when wind or solar power generation fluctuates significantly, traditional methods may not be able to quickly adjust the dispatch strategy of the energy storage system, affecting the stability of the power system. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for constructing an energy storage system support capability assessment model to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for constructing an energy storage system support capacity evaluation model includes the following steps: Step S1: Acquire energy storage system structure data, and perform energy storage system topology modeling according to the energy storage system structure data, thereby obtaining an energy storage system topology model; Step S2: acquiring energy storage system operation data and energy storage system sensor data, and fusing the energy storage system sensor data according to the energy storage system topology model, thereby obtaining an energy storage system sensor network; Step S3: identifying the electrical operation mode of the energy storage system based on the operation data of the energy storage system, thereby obtaining the electrical operation mode data of the energy storage system, and integrating the system operation sensor fluctuation mode of the electrical operation mode data of the energy storage system according to the energy storage system sensor network, thereby obtaining the system operation sensor fluctuation mode data; Step S4: performing abnormal sensor fluctuation detection on the system operation sensor fluctuation mode data, thereby obtaining abnormal sensor fluctuation detection data, and performing energy storage system support capability evaluation based on the abnormal sensor fluctuation detection data, thereby obtaining energy storage system support capability score data; Step S5: constructing an energy storage system support capability assessment model based on the abnormal sensor fluctuation detection data and the energy storage system support capability score data.

[0005] By modeling the topological structure of the energy storage system, the present invention can fully understand the composition and interrelationship of the system, help identify key components and potential bottlenecks, provide a basis for subsequent optimization design, and ensure that the system design can fully meet the actual operation requirements. After the model is established, it can be easily modified and expanded to adapt to future technological developments or changes in demand. Traditional methods often ignore the complexity of the system. Topological modeling can consider multiple factors and improve the accuracy of the evaluation of system performance. Through sensor data fusion, real-time monitoring of the state of the energy storage system can be achieved and the responsiveness of the system can be improved. Fusion of data from different sources can improve the accuracy and reliability of data and reduce the impact of sensor noise. A more comprehensive data view supports decision-making, helping operators to adjust energy storage strategies in a timely manner and optimize resource allocation. By identifying different electrical operation modes, the operation strategy of the energy storage system can be optimized in a targeted manner to improve overall efficiency. At the same time, it can quickly respond to changes in grid load and fluctuations in renewable energy generation to ensure that necessary support is provided during peak loads. Identifying patterns can help predict potential failures or performance degradation, implement predictive maintenance, and reduce operational risks. By detecting the fluctuation mode, it is possible to timely identify abnormal conditions in the system operation, reduce the probability of failure, and improve the reliability of the energy storage system to ensure stable power supply at critical moments. The abnormal detection results can provide an important basis for the performance evaluation of the energy storage system to ensure that the system can achieve the expected support capacity. By constructing a comprehensive evaluation model, the support capacity of the energy storage system can be systematically evaluated to provide a scientific basis. Based on the evaluation results, the scheduling and operation strategies of the energy storage system can be optimized to improve the overall economy and stability. The evaluation model provides a quantitative basis for the scheduling decision of the power system, which helps to make timely responses in a rapidly changing power grid environment. In summary, through the above steps, a dynamic and comprehensive evaluation of the energy storage system can be achieved, thereby improving the accuracy of the quantification of the support capacity of the energy storage system, while improving its support capacity in the utilization of renewable energy, and ensuring the stability and economy of the power grid. This systematic and dynamic evaluation method can effectively address the shortcomings of traditional evaluation methods and help the development and application of energy storage technology.

[0006] Optionally, step S1 specifically includes: Step S11: Acquire energy storage system structure data, and perform structural division on the energy storage system structure data, thereby obtaining energy storage component structure data and control component structure data; Step S12: performing control component spatial distribution analysis according to the control component structure data, thereby obtaining control component spatial distribution data; Step S13: integrating the spatial distribution profile of the control component spatial distribution data, thereby obtaining the spatial distribution profile data of the control component; Step S14: integrating component connection relationships according to the control component spatial distribution profile data and the energy storage component structure data, thereby obtaining energy storage system component connection relationship data; Step S15: Modeling the energy storage system topology based on the energy storage system component connection relationship data, thereby obtaining an energy storage system topology model.

[0007] The present invention can clearly identify the functions and characteristics of different energy storage components (such as batteries, supercapacitors, etc.) and control components (such as inverters, transformers, etc.) by systematically acquiring and dividing the structural data of the energy storage system. This lays the foundation for subsequent analysis and helps to optimize the system design. Analyzing the spatial distribution of the control components can effectively identify their positions and relationships in the entire energy storage system. This analysis helps to improve the layout efficiency of the system, reduce space waste, and optimize operations such as cooling and maintenance. By integrating the spatial distribution profiles of the control components, more intuitive distribution information can be obtained. This information is crucial for subsequent system optimization and fault diagnosis, and can help engineers better understand the physical layout and electrical connections of the system. Integrating the connection relationship data of the energy storage components and the control components can construct a more accurate system interaction relationship, which not only facilitates the understanding of the dependencies between the components, but also provides a reference for the formulation of control strategies and improves the operating efficiency of the system. Topological structure modeling based on the data of component connection relationships can form an overall view of the energy storage system. This model is helpful for simulation and performance evaluation, and provides a theoretical basis for future system optimization, expansion and fault handling.

[0008] Optionally, step S14 is specifically: Step S141: integrating the energy storage component structure data into an energy storage component structure profile, thereby obtaining the energy storage component structure profile data; Step S142: performing similarity calculation on the energy storage component structure profile data and the control component spatial distribution profile data, thereby obtaining profile similarity data; Step S143: performing high-similarity profile combination and integration on the energy storage component structure profile data and the control component spatial distribution profile data according to the profile similarity data, thereby obtaining high-similarity profile combination data; Step S144: integrating the structural connection relationship of the energy storage component structure data and the control component structure data based on the high-similarity profile combination data, thereby obtaining energy storage system component connection relationship data.

[0009] The present invention can form unified profile data by integrating the structural data of the energy storage component. This provides a basis for subsequent data processing and analysis, and reduces the complexity caused by the diversity of data. The integrated data helps to discover the potential optimization space between components, promote the optimization of the overall design, and improve the efficiency and reliability of the energy storage system. By calculating the similarity between the structural profile of the energy storage component and the spatial distribution profile of the control component, components with similar functions and structures can be identified. This helps to reuse or modularize components in the design and improve design efficiency. By combining high-similarity profile data, effective integration between components can be achieved. This integrated design helps to improve the compatibility and stability of the system. The combination and integration of high-similarity profiles can reduce material waste in the production process, optimize resource allocation, and thus reduce overall manufacturing costs. The integrated connection relationship data can better reveal the interaction and dependency between components, enhance the system's ability to work together, and improve overall performance. Through clear connection relationships, potential fault points can be effectively identified, the reliability and maintainability of the system can be improved, and the energy storage system can be more stable in practical applications.

[0010] Optionally, step S2 specifically includes: Step S21: Acquire energy storage system operation data and energy storage system sensor data; Step S22: extracting sensor space features from the energy storage system sensor data to obtain sensor space data; Step S23: constructing a sensor space coordinate system according to the sensor space data, thereby obtaining sensor space coordinate system data; Step S24: performing sensor data fusion on the energy storage system sensor data according to the sensor space coordinate system data, thereby obtaining a sensor network; Step S25: Fusion of component spatial relationships of the sensor network is performed according to the energy storage system topology model, thereby obtaining the energy storage system sensor network.

[0011] The present invention obtains accurate real-time operating status and environmental data, which provides raw data support for subsequent analysis, helps to timely discover system anomalies and improve operating efficiency. By extracting spatial features, important patterns and trends in sensor data can be identified. This processing helps to reduce data redundancy and improve data quality, thereby improving the accuracy of subsequent analysis and decision-making. Constructing a spatial coordinate system provides a unified reference framework for sensor data. This enables data between different sensors to be effectively compared and integrated, laying the foundation for subsequent data fusion and analysis. Data fusion technology can integrate information from different sensors to provide a more comprehensive view of the system status. This integration not only improves the reliability of the data, but also reveals the potential interconnectivity and dependence of the system, and enhances decision-making support capabilities. By combining the system topology, the interactions between the various components and their impact on the overall performance can be better understood. The fusion of this relationship helps to optimize the layout and operation strategy of the energy storage system and improve the efficiency and stability of the overall system.

[0012] Optionally, step S3 specifically includes: Step S31: extracting operating electrical characteristics and operating mode characteristics based on the energy storage system operating data, thereby obtaining the energy storage system operating electrical data and the energy storage system operating mode data; Step S32: performing frequency domain conversion on the electrical data of the energy storage system operation to obtain the electrical spectrum of the energy storage system operation, and integrating the spectrum amplitude characteristics according to the electrical spectrum of the energy storage system operation to obtain electrical spectrum amplitude data; Step S33: performing minimum amplitude spectrum selection according to the electrical spectrum amplitude data, thereby obtaining electrical stable amplitude data; Step S34: performing operation electrical benchmark statistics based on the electrical stability amplitude data, thereby obtaining operation electrical benchmark data; Step S35: performing electrical amplitude pattern recognition on the electrical spectrum amplitude data according to the operating electrical reference data, thereby obtaining operating electrical amplitude pattern data; Step S36: performing time-series correlation on the operation electrical amplitude mode data and the energy storage system operation mode data, thereby obtaining the energy storage system electrical operation mode data; Step S37: integrating the system operation sensor fluctuation mode of the energy storage system electrical operation mode data according to the energy storage system sensor network, thereby obtaining the system operation sensor fluctuation mode data.

[0013] By extracting the electrical characteristics and operation mode of the energy storage system, the present invention can conduct an in-depth analysis of the overall operation status of the system. This step provides basic data for subsequent fault detection and performance evaluation, which helps to timely discover potential problems and optimize them. Frequency domain conversion allows complex signals originally in the time domain to be simplified and analyzed in the frequency domain. Through the integration of spectrum amplitude characteristics, key frequency components can be extracted, so that the electrical characteristics and behaviors can be understood more clearly, and the sensitivity to dynamic changes in the system is improved. Implementation helps to eliminate noise and irrelevant signals and focus on stable amplitudes that are critical to system operation. By screening stable amplitude data, the accuracy of data analysis can be improved, thereby enhancing the ability to judge the system status. Establishing electrical benchmark data can provide a reference standard for subsequent performance evaluation. This step helps to monitor the normal operating range of the system and can effectively identify abnormal situations, thereby providing a basis for fault warning and maintenance decisions. Through pattern recognition of electrical spectrum amplitude data, different operating states and their corresponding characteristics can be identified. This recognition capability can help operation and maintenance personnel understand the operating efficiency and reliability of the system and adjust the operation strategy in a timely manner. The time-series correlation of the operating electrical amplitude mode data with the energy storage system operating mode data can reveal the timeliness and relevance of the system operation. This analysis helps to understand the operating trend of the system in different time periods and provide a basis for optimizing scheduling and operation management. Integrating the system operation sensor fluctuation mode data can more comprehensively reflect the health status and operating efficiency of the system. This step can provide support for real-time monitoring and early warning, and enhance the adaptability and intelligence level of the system.

[0014] Optionally, step S37 is specifically: Step S371: collecting electrical component sensor data based on the energy storage system sensor network, thereby obtaining electrical component sensor data; Step S372: performing sensor fluctuation statistics according to the electrical component sensor data, thereby obtaining the electrical component sensor fluctuation data; Step S373: performing sensor fluctuation pattern recognition based on the sensor fluctuation data of the electrical component, thereby obtaining sensor fluctuation pattern data; Step S374: Time-series correlation is performed on the sensor fluctuation mode data and the energy storage system electrical operation mode data, so as to obtain the system operation sensor fluctuation mode data.

[0015] The present invention can realize real-time monitoring of electrical components through a sensor network, ensure timely detection of potential faults or abnormal conditions, and improve the safety and reliability of the system. Integrate sensor data from different electrical components to form a comprehensive monitoring system, providing a rich information basis for subsequent data analysis. Performing fluctuation statistics on sensor data can effectively identify abnormal fluctuations, help technicians quickly locate the source of the problem, and reduce downtime. Through fluctuation statistical analysis, it is possible to provide a quantitative basis for maintenance and optimization decisions and promote data-based management strategies. Using pattern recognition technology, multiple fluctuation patterns can be automatically identified to enhance the system's adaptability to complex operating environments. After identifying common fluctuation patterns, system parameters can be adjusted, operating strategies can be optimized, energy efficiency can be improved, and energy consumption can be reduced. Performing time-series correlation analysis on sensor fluctuation patterns and electrical operating modes helps to fully understand the performance of the system under different operating conditions, thereby improving the overall performance of the system. Through time-series correlation, it is possible to predict possible fluctuations in the future, help formulate preventive measures, and reduce unexpected downtime and maintenance costs.

[0016] Optionally, step S4 specifically includes: Step S41: performing sensor fluctuation amplitude calculation and sensor fluctuation time calculation on the system operation sensor fluctuation mode data, thereby obtaining the system operation sensor fluctuation amplitude data and the system operation sensor fluctuation time data; Step S42: performing statistics of the fluctuation amplitude range of the fluctuation mode according to the sensing fluctuation mode data, thereby obtaining the fluctuation amplitude range data of the fluctuation mode; Step S43: classifying the system operation sensor fluctuation amplitude data based on the fluctuation mode fluctuation amplitude range data, thereby obtaining high amplitude error sensor fluctuation data and low amplitude error sensor fluctuation data; Step S44: classifying the system operation sensor fluctuation time data by sensor fluctuation time, thereby obtaining long-duration sensor fluctuation data and short-duration sensor fluctuation data; Step S45: performing a sensor fluctuation time intersection operation on the high-amplitude error sensor fluctuation data and the long-duration sensor fluctuation data, thereby obtaining abnormal operation sensor fluctuation data; performing a sensor fluctuation time intersection operation on the low-amplitude error sensor fluctuation data and the short-duration sensor fluctuation data, thereby obtaining normal operation sensor fluctuation data; Step S46: performing time series merging of the abnormal operation sensor fluctuation data and the normal operation sensor fluctuation data, thereby obtaining abnormal sensor fluctuation detection data; Step S47: Evaluate the support capability of the energy storage system based on the abnormal sensor fluctuation detection data, so as to obtain the support capability score data of the energy storage system.

[0017] The present invention can capture the changes in the operating state of the system in real time by calculating the fluctuation amplitude and time of sensor data. This helps to identify potential problems and improve the responsiveness of the system. The amplitude range of the statistical fluctuation pattern helps to establish benchmark data for subsequent analysis. This step can identify the normal and abnormal ranges of fluctuations and improve the interpretability of the data. Classifying the fluctuation amplitude helps to quickly identify abnormal behavior. By distinguishing between high and low amplitude errors, the stability of the system can be more effectively monitored and maintained. By classifying time, the persistence of fluctuations can be judged. This is crucial for analyzing different types of failure modes and can help to develop more effective early warning mechanisms. Through intersection operations, abnormal and normal operating states can be effectively distinguished. This step provides deeper insights, allowing the system to take corresponding countermeasures for different states. Time-series merging of abnormal and normal data helps to fully understand the operating status of the system, which can provide an important basis for subsequent analysis and decision-making and help optimize maintenance strategies. Evaluating the support capacity of the energy storage system based on abnormal detection data can intuitively reflect the health status and performance of the system, which is crucial to ensuring the stability and reliability of the system.

[0018] Optionally, step S47 is specifically: Step S471: dividing abnormal sensing fluctuation components according to abnormal sensing fluctuation detection data, thereby obtaining component abnormal sensing fluctuation data; Step S472: Counting component abnormality frequencies of component abnormality sensor fluctuation data, thereby obtaining high abnormality frequency component data and low abnormality frequency component data; Step S473: Calculating component abnormality time for the high abnormal frequency component data and the low abnormal frequency component data, respectively, so as to obtain high abnormal frequency component abnormality time data and low abnormal frequency component abnormality time data; Step S474: extracting component operation time features from the energy storage system operation data, thereby obtaining component operation time data; Step S475: Calculate the abnormal fluctuation time proportions of the high abnormal frequency component abnormal time data and the low abnormal frequency component abnormal time data according to the component operation time data, so as to obtain the high abnormal frequency component abnormal fluctuation time proportion data and the low abnormal frequency component abnormal fluctuation time proportion data; Step S476: Evaluate the support capability of the energy storage system according to the abnormal fluctuation time proportion data of the high abnormal frequency component and the abnormal fluctuation time proportion data of the low abnormal frequency component, so as to obtain the support capability score data of the energy storage system.

[0019] By dividing the abnormal sensor fluctuation data, the present invention can clearly identify which components have abnormalities, and then concentrate resources and attention on these problem components, reducing the inspection workload of the entire system and improving the efficiency of fault location. Statistics of the data of high abnormal frequency components and low abnormal frequency components are helpful to evaluate the health status of each component. High-frequency abnormalities may mean that there is a potential fault in the component, while low-frequency abnormalities may indicate normal fluctuations. This classification method can optimize the maintenance strategy and give priority to high-risk components. Calculating the abnormal time of high abnormal frequency and low abnormal frequency components can provide a time basis for troubleshooting, help engineers understand the time pattern of abnormal occurrence, and then improve the design or operating parameters of the component and extend its service life. By extracting features from the running time of the component, its performance and stability can be deeply analyzed. This data will help evaluate the performance of the component under different working conditions and support the formulation of more reasonable maintenance and operation strategies. By calculating the proportion of abnormal fluctuation time, the stability of the component can be quantified. The high fluctuation proportion indicates that immediate measures need to be taken to prevent the expansion of the fault, while the low fluctuation proportion indicates that the component is running well, helping operators to reasonably allocate maintenance resources. Evaluating the support capacity of the energy storage system based on the abnormal fluctuation time proportion data helps to fully understand the performance of the system under different working conditions. This assessment can provide guidance for system optimization and improvement, and enhance the overall efficiency and reliability of the system.

[0020] Optionally, step S476 is specifically: Obtain expert experience data on energy storage systems; According to the experience data of energy storage system experts, the influence factors of energy storage system operation efficiency are estimated based on the abnormal fluctuation time proportion data of high abnormal frequency components, so as to obtain the influence factors of energy storage system operation efficiency; According to the experience data of energy storage system experts, the energy storage system stability influencing factor is estimated based on the abnormal fluctuation time proportion data of low abnormal frequency components, so as to obtain the energy storage system stability influencing factor; Construct a calculation model for the energy storage system support capability score based on the factors affecting the energy storage system operation efficiency and the energy storage system stability; The energy storage system support capability score calculation model is used to calculate the energy storage system support capability score for the abnormal fluctuation time proportion data of high abnormal frequency components and the abnormal fluctuation time proportion data of low abnormal frequency components, thereby obtaining the energy storage system support capability score data.

[0021] The present invention collects expert experience data to help establish a knowledge base for the operation of the energy storage system and provide basic data for subsequent analysis. Through the experience of experts, a scientific basis can be provided for operation and maintenance decisions to reduce human errors. The fluctuation of high abnormal frequency components directly affects the operating efficiency, and accurately evaluating its influencing factors helps to identify problem components. By understanding these influencing factors, the equipment management and maintenance strategies can be optimized in a targeted manner to improve the overall efficiency of the system. Although the fluctuation of low abnormal frequency components is not frequent, it has a greater impact on the stability of the system. Understanding its influencing factors helps to improve the reliability of the system. By analyzing the causes of fluctuations, possible failures can be predicted in advance, so as to perform preventive maintenance. Establishing a scoring model can convert operating efficiency and stability into quantifiable indicators, providing a basis for evaluating system performance. Comprehensive consideration of operating efficiency and stability helps to comprehensively evaluate the support capacity of the energy storage system and provide a multi-dimensional perspective for decision-making. By analyzing the scoring data, potential room for improvement can be discovered, thereby achieving continuous optimization of the system.

[0022] Optionally, the present invention further provides an energy storage system support capability assessment model construction system, which is used to execute the energy storage system support capability assessment model construction method as described above, and the energy storage system support capability assessment model construction system includes: A topology modeling module is used to obtain energy storage system structure data, and perform energy storage system topology modeling based on the energy storage system structure data, thereby obtaining an energy storage system topology model; A sensor data fusion module is used to obtain the energy storage system operation data and the energy storage system sensor data, and to fuse the energy storage system sensor data according to the energy storage system topology model, so as to obtain the energy storage system sensor network; A sensor fluctuation mode integration module is used to identify the electrical operation mode of the energy storage system based on the operation data of the energy storage system, so as to obtain the electrical operation mode data of the energy storage system, and to integrate the system operation sensor fluctuation mode of the electrical operation mode data of the energy storage system according to the energy storage system sensor network, so as to obtain the system operation sensor fluctuation mode data; A support capability evaluation module is used to perform abnormal sensor fluctuation detection on the system operation sensor fluctuation mode data, thereby obtaining abnormal sensor fluctuation detection data, and to evaluate the support capability of the energy storage system based on the abnormal sensor fluctuation detection data, thereby obtaining the support capability score data of the energy storage system; The model building module is used to build an energy storage system support capability evaluation model based on abnormal sensor fluctuation detection data and energy storage system support capability score data.

[0023] The energy storage system support capability assessment model construction system of the present invention can implement any one of the energy storage system support capability assessment model construction methods of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the energy storage system support capability assessment model construction method. The internal modules of the system cooperate with each other, thereby improving the overall stability of the energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings: Figure 1 A schematic diagram of the steps of the method for constructing a supporting capacity evaluation model of an energy storage system according to the present invention; Figure 2 Detailed step flow diagram of step S1 in the present invention; Figure 3 Detailed step flow diagram of step S2 in the present invention; 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

[0025] 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.

[0026] 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.

[0027] 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 unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for constructing an energy storage system support capability evaluation model, the method comprising the following steps: Step S1: Acquire energy storage system structure data, and perform energy storage system topology modeling according to the energy storage system structure data, thereby obtaining an energy storage system topology model; In this embodiment, the structural data of the energy storage system is collected through the energy storage system management platform, including the configuration, connection relationship and electrical parameters of each component (such as battery pack, inverter, charging equipment, etc.). The topological model of the energy storage system can be constructed using graph theory methods to define nodes (components) and edges (connections). For example, the NetworkX library in MATLAB or Python is used for modeling. By drawing the system topology diagram and marking the electrical characteristics of each component, it is ensured that the model accurately reflects the structure of the real system and provides a basis for subsequent analysis.

[0029] Step S2: acquiring energy storage system operation data and energy storage system sensor data, and fusing the energy storage system sensor data according to the energy storage system topology model, thereby obtaining an energy storage system sensor network; In this embodiment, the energy storage system management platform is used to obtain the operating data (such as current, voltage, power, etc.) and sensor data (such as temperature, humidity, etc.) of the energy storage system, and then the sensor data is processed using data fusion technology, such as Kalman filtering or particle filtering, to eliminate noise and redundancy. According to the established topological structure model, the fused data is associated with the system structure to generate a comprehensive sensor network. This process can use Python's pandas library for data processing to ensure the accuracy and consistency of the information.

[0030] Step S3: identifying the electrical operation mode of the energy storage system based on the operation data of the energy storage system, thereby obtaining the electrical operation mode data of the energy storage system, and integrating the system operation sensor fluctuation mode of the electrical operation mode data of the energy storage system according to the energy storage system sensor network, thereby obtaining the system operation sensor fluctuation mode data; In this embodiment, the collected operation data is used to apply machine learning algorithms (such as support vector machines, neural networks, etc.) to identify the electrical operation mode. The identification results are combined with the previous sensor network data to integrate the electrical operation modes of different time periods to form the operation characteristics of the system. For example, by using the Scikit-learn library, the operation data under different working conditions are classified to obtain the electrical operation mode data of the system and establish the basis for the operation fluctuation mode.

[0031] Step S4: performing abnormal sensor fluctuation detection on the system operation sensor fluctuation mode data, thereby obtaining abnormal sensor fluctuation detection data, and performing energy storage system support capability evaluation based on the abnormal sensor fluctuation detection data, thereby obtaining energy storage system support capability score data; In this embodiment, statistical analysis and machine learning methods (such as anomaly detection algorithms and cluster analysis) are applied to the obtained system operation sensor fluctuation pattern data to detect anomalies. Thresholds are set to identify abnormal fluctuations and relevant data are recorded. Subsequently, based on the detection results and combined with the system's historical performance data, the energy storage system's support capacity is evaluated to form a support capacity score. This process can be implemented with the help of the forecast package of the R language or the statsmodels library of Python.

[0032] Step S5: constructing an energy storage system support capability assessment model based on the abnormal sensor fluctuation detection data and the energy storage system support capability score data.

[0033] In this embodiment, a storage system support capacity assessment model is constructed based on the obtained abnormal detection data and support capacity scores. Multiple linear regression or decision tree algorithm is selected to incorporate factors affecting support capacity into the model. TensorFlow is used to build a neural network and optimize model parameters to improve the accuracy of prediction. In addition, an interactive interface is designed to update the model evaluation results through real-time data input by the user to ensure the dynamic adaptability and practicality of the model.

[0034] Optionally, step S1 specifically includes: Step S11: Acquire energy storage system structure data, and perform structural division on the energy storage system structure data, thereby obtaining energy storage component structure data and control component structure data; In this embodiment, the detailed structural data of the energy storage system is collected through the energy storage system management platform, including the specifications of components such as battery packs, inverters, transformers, controllers, and their interrelationships. Professional software (such as AutoCAD or Revit) is used to structure the data, identify and classify the energy storage component structural data (such as the voltage and capacity of the battery unit) and the control component structural data (such as the model and function of the controller). In this way, the composition of the energy storage system and the characteristics of each component can be clarified, forming a preliminary structural framework.

[0035] Step S12: performing control component spatial distribution analysis according to the control component structure data, thereby obtaining control component spatial distribution data; In this embodiment, the spatial distribution of the control components is analyzed to evaluate the rationality of their layout in the energy storage system. By using GIS (Geographic Information System) tools, the spatial location data of the control components is visualized to generate a spatial distribution map. Cluster analysis (such as K-means algorithm) is used to determine the spatial aggregation and distribution characteristics of the control components. This step ensures the rational layout of the control system to optimize performance and maintenance efficiency.

[0036] Step S13: integrating the spatial distribution profile of the control component spatial distribution data, thereby obtaining the spatial distribution profile data of the control component; In this embodiment, the obtained spatial distribution data of the control components are integrated, and the spatial distribution contour data of the control components are generated by using data interpolation technology (such as Kriging interpolation method). Through MATLAB or Python's SciPy library, the spatial distribution is visualized to help identify the distribution trend and regional density of the control components. This integration provides basic data for subsequent connection relationship analysis to ensure the accuracy of the evaluation results.

[0037] Step S14: integrating component connection relationships according to the control component spatial distribution profile data and the energy storage component structure data, thereby obtaining energy storage system component connection relationship data; In this embodiment, the spatial distribution profile data of the control components is combined with the structural data of the energy storage components, and the component connection relationship is integrated using the graph theory method. Specifically, by defining nodes (components) and edges (connection relationships), a graph model is built in Python, and network analysis tools (such as the NetworkX library) are used to identify the connection relationship between components. This will help clarify the interaction between components in the system and improve the system integration.

[0038] Step S15: Modeling the energy storage system topology based on the energy storage system component connection relationship data, thereby obtaining an energy storage system topology model.

[0039] In this embodiment, the topological structure modeling of the energy storage system is performed based on the obtained data on the connection relationship of the energy storage system components. A suitable modeling tool (such as MATLAB Simulink or PSS / E) is selected to establish a dynamic simulation model. By converting the component connection relationship into an electrical network model, the electrical characteristics and connection method of each component are defined, and finally a complete energy storage system topological structure model is generated for subsequent performance analysis and optimization.

[0040] Optionally, step S14 is specifically: Step S141: integrating the energy storage component structure data into an energy storage component structure profile, thereby obtaining the energy storage component structure profile data; In this embodiment, the structural data of the energy storage components are integrated to obtain the structural contour data of the energy storage components. Specifically, the CAD drawings of various energy storage components (such as lithium batteries, supercapacitors, etc.) are imported using 3D modeling software, and the contour boundaries are analyzed by algorithms to generate unified 3D contour graphics to ensure that the geometric features of different components can be expressed in a standardized manner.

[0041] Step S142: performing similarity calculation on the energy storage component structure profile data and the control component spatial distribution profile data, thereby obtaining profile similarity data; In this embodiment, the similarity calculation is performed between the energy storage component structure profile data and the control component spatial distribution profile data. A shape matching algorithm (such as Hausdorff distance or profile centroid distance) can be used to quantify the similarity between the two profiles. Python and OpenCV libraries can be used to implement this calculation and generate a similarity matrix to facilitate subsequent data analysis.

[0042] Step S143: performing high-similarity profile combination and integration on the energy storage component structure profile data and the control component spatial distribution profile data according to the profile similarity data, thereby obtaining high-similarity profile combination data; In this embodiment, two kinds of profile data are combined and integrated with high similarity according to the profile similarity data. A cluster analysis method (such as K-means clustering) can be used to aggregate the profile data with high similarity to form a new profile combination. This can be achieved through the clustering tool in MATLAB, and a visual high-similarity profile combination diagram can be output.

[0043] Step S144: integrating the structural connection relationship of the energy storage component structure data and the control component structure data based on the high-similarity profile combination data, thereby obtaining energy storage system component connection relationship data.

[0044] In this embodiment, the energy storage component structure data and the control component structure data are connected and integrated based on the high similarity profile combination data. This step can use the minimum spanning tree algorithm in graph theory to identify and establish the connection relationship between components. The final energy storage system component connection relationship data can be generated by constructing a graph containing all component nodes and edges and applying the Dijkstra algorithm to optimize the connection path.

[0045] Optionally, step S2 specifically includes: Step S21: Acquire energy storage system operation data and energy storage system sensor data; In this embodiment, the energy storage system management platform is used to obtain the operating data of the energy storage system (such as battery voltage, charge and discharge status, temperature, etc.) and sensor data (such as acceleration, humidity, pressure, etc.) in real time. Industrial standard sensors (such as RS-485 or Modbus protocol) can be used to connect to the central energy storage system management platform and transmit the data to the data server regularly (for example, every second). The data can be stored in a cloud database for subsequent analysis and processing.

[0046] Step S22: extracting sensor space features from the energy storage system sensor data to obtain sensor space data; In this embodiment, a machine learning algorithm is applied to extract spatial features of the collected sensor data. For example, principal component analysis (PCA) is used to reduce the dimension of the sensor data and extract the main spatial features of the sensor to identify the spatial distribution information of the sensor in the energy storage system.

[0047] Step S23: constructing a sensor space coordinate system according to the sensor space data, thereby obtaining sensor space coordinate system data; In this embodiment, the extracted spatial features are mapped to a unified coordinate system. Specifically, the physical position and measurement data of the sensor can be used to generate the spatial coordinate system of the sensor through 3D modeling software (such as MATLAB or Python's Matplotlib library). In this process, the installation position of the sensor in the energy storage system is considered to ensure that the constructed coordinate system accurately reflects the actual distribution of the sensor in space, laying the foundation for subsequent data fusion.

[0048] Step S24: performing sensor data fusion on the energy storage system sensor data according to the sensor space coordinate system data, thereby obtaining a sensor network; In this embodiment, the sensor spatial coordinate system data is used to fuse the relevant data obtained by different sensors to form a complete sensor network. A data fusion algorithm (such as Kalman filtering or particle filtering) can be used to integrate the data of multiple sensors in the spatial coordinate system. Using NumPy and SciPy libraries, weighted averaging or weighted summing of different sensor data is performed to obtain a more accurate and reliable sensor data network.

[0049] Step S25: Fusion of component spatial relationships of the sensor network is performed according to the energy storage system topology model, thereby obtaining the energy storage system sensor network.

[0050] In this embodiment, the spatial relationship of components in the sensor network is integrated according to the topological structure model of the energy storage system. Graph theory methods can be used to establish a relationship network between sensors and energy storage components. Specifically, the NetworkX library can be used to build a connection graph between sensors and components, and the shortest path algorithm can be used to analyze the spatial relationship between sensors and energy storage units, so as to identify key sensors and components that affect system performance and optimize the system layout. Ultimately, a comprehensive energy storage system sensor network is formed to provide support for subsequent monitoring and decision-making.

[0051] Optionally, step S3 specifically includes: Step S31: extracting operating electrical characteristics and operating mode characteristics based on the energy storage system operating data, thereby obtaining the energy storage system operating electrical data and the energy storage system operating mode data; In this embodiment, operating data such as current, voltage, and power are collected from sensors of the energy storage system. Then, signal processing algorithms (such as Fourier transform) are applied to extract electrical features, including instantaneous power, effective value, and harmonic components. For operating mode features, the system's charge and discharge status, operating time, and ambient temperature are recorded. After preprocessing, these data form a structured data set for subsequent analysis.

[0052] Step S32: performing frequency domain conversion on the electrical data of the energy storage system operation to obtain the electrical spectrum of the energy storage system operation, and integrating the spectrum amplitude characteristics according to the electrical spectrum of the energy storage system operation to obtain electrical spectrum amplitude data; In this embodiment, the acquired electrical data is subjected to a discrete Fourier transform (DFT) to convert it into the frequency domain and obtain the electrical spectrum. Subsequently, the amplitude spectrum of the spectrum is calculated to extract important frequency components, such as the fundamental frequency and its harmonics. Combined with power spectral density analysis, the features are integrated to identify the performance of the system under different load conditions and generate electrical spectrum amplitude data.

[0053] Step S33: performing minimum amplitude spectrum selection according to the electrical spectrum amplitude data, thereby obtaining electrical stable amplitude data; In this embodiment, a threshold is set in the electrical spectrum amplitude data to filter out frequency components below the threshold, thereby obtaining a minimum amplitude spectrum. A statistical analysis method (such as variance analysis) is used to evaluate the stability of the spectrum amplitude and filter out frequencies with a small change amplitude, thereby determining electrical stable amplitude data to ensure the reliability and accuracy of the data.

[0054] Step S34: performing operation electrical benchmark statistics based on the electrical stability amplitude data, thereby obtaining operation electrical benchmark data; In this embodiment, the electrical stability amplitude data is statistically analyzed to calculate the mean, standard deviation, maximum value, and minimum value to construct the operating electrical benchmark data. These benchmark data are visualized using charts and statistical software (such as Pandas and Matplotlib in Python) to facilitate understanding and identification of the differences between normal operation and abnormal operation, forming a reference benchmark.

[0055] Step S35: performing electrical amplitude pattern recognition on the electrical spectrum amplitude data according to the operating electrical reference data, thereby obtaining operating electrical amplitude pattern data; In this embodiment, a machine learning algorithm (such as K-means clustering or support vector machine) is used to perform pattern recognition on the electrical spectrum amplitude data. By comparing the operating electrical benchmark data, different electrical amplitude modes, such as normal operating mode, overload mode or fault mode, are identified. A classification model is constructed to monitor and predict the operating status of the system in real time and generate operating electrical amplitude mode data.

[0056] Step S36: performing time-series correlation on the operation electrical amplitude mode data and the energy storage system operation mode data, thereby obtaining the energy storage system electrical operation mode data; In this embodiment, the operating electrical amplitude mode data and the energy storage system operating mode data are analyzed in time series, and the dynamic time warping (DTW) method is used to identify their time series association. In this way, the relationship between the operating mode and the electrical mode is established, and the electrical operating mode data of the energy storage system is formed to facilitate subsequent mode optimization and decision support.

[0057] Step S37: integrating the system operation sensor fluctuation mode of the energy storage system electrical operation mode data according to the energy storage system sensor network, thereby obtaining the system operation sensor fluctuation mode data.

[0058] In this embodiment, the sensor network data of the energy storage system is combined with data fusion technology (such as Kalman filtering) to integrate the electrical operation mode data with the sensor fluctuation data to form the system operation sensor fluctuation mode data. These modes are displayed through visualization tools to help engineers identify potential problems and predict faults.

[0059] Optionally, step S37 is specifically: Step S371: collecting electrical component sensor data based on the energy storage system sensor network, thereby obtaining electrical component sensor data; In this embodiment, a variety of sensors are arranged in the energy storage system, including temperature sensors, current sensors, and voltage sensors. These sensors are connected via a wireless network to collect real-time operating status data of electrical components (such as battery packs and inverters). For example, the temperature sensor monitors the operating temperature of the battery pack, the current sensor monitors the charge and discharge current, and the voltage sensor monitors the battery voltage. These data are transmitted to the central processing unit in the form of a timestamp to ensure the integrity and real-time nature of the data.

[0060] Step S372: performing sensor fluctuation statistics according to the electrical component sensor data, thereby obtaining the electrical component sensor fluctuation data; In this embodiment, the sliding average method and standard deviation calculation are used to analyze the data fluctuation of each sensor. For example, a time window (such as 1 minute) is set, and the standard deviation of the temperature change within the window is calculated to determine whether the temperature fluctuation is within the normal range. Finally, a fluctuation data report is formed, which contains information such as the fluctuation amplitude and frequency of each sensor.

[0061] Step S373: performing sensor fluctuation pattern recognition based on the sensor fluctuation data of the electrical component, thereby obtaining sensor fluctuation pattern data; In this embodiment, based on the fluctuation data, a machine learning algorithm (such as K-means clustering or support vector machine) is used for pattern recognition. First, feature extraction is performed on the statistical results, and the fluctuation amplitude, frequency and change rate are selected as features. By training the model, different fluctuation patterns are identified. For example, normal working mode, overload mode and fault mode are identified. The recognition results are presented in a visual way to facilitate subsequent analysis and decision-making.

[0062] Step S374: Time-series correlation is performed on the sensor fluctuation mode data and the energy storage system electrical operation mode data, so as to obtain the system operation sensor fluctuation mode data.

[0063] In this embodiment, the sensor fluctuation mode data is time-series associated with the electrical operation mode data of the energy storage system. Specifically, the electrical operation mode data (such as charging, discharging, standby, etc.) is time-aligned with the sensor fluctuation mode data to form a time series data set. Through time series analysis methods (such as cross-correlation analysis), the fluctuation characteristics under different operation modes are identified. For example, the fluctuation of battery temperature under high load conditions can be analyzed to evaluate its impact on system safety, thereby optimizing the operation strategy of the energy storage system.

[0064] Optionally, step S4 specifically includes: Step S41: performing sensor fluctuation amplitude calculation and sensor fluctuation time calculation on the system operation sensor fluctuation mode data, thereby obtaining the system operation sensor fluctuation amplitude data and the system operation sensor fluctuation time data; In this embodiment, digital signal processing technology is applied to calculate the fluctuation amplitude. In specific implementation, the root mean square (RMS) method can be used to calculate the sensor fluctuation amplitude, and the formula is: \text{RMS}=\sqrt{\frac{1}{N}\sum_{i=1}^{N}x_i^2}, where x_i is the sensor value of each sampling point and N is the number of samples. At the same time, when calculating the fluctuation time, the time points of the start and end of the fluctuation are identified, and its duration is recorded.

[0065] Step S42: performing statistics of the fluctuation amplitude range of the fluctuation mode according to the sensing fluctuation mode data, thereby obtaining the fluctuation amplitude range data of the fluctuation mode; In this embodiment, amplitude range statistics are performed based on the sensed fluctuation pattern data. Thresholds are set to divide the amplitude data into multiple intervals, such as 0-5%, 5-10%, and above 10%, and the number of data points in each interval is calculated. This classification can help identify the general characteristics of the fluctuation pattern through data visualization tools (such as histograms), thereby obtaining the fluctuation pattern fluctuation amplitude range data.

[0066] Step S43: classifying the system operation sensor fluctuation amplitude data based on the fluctuation mode fluctuation amplitude range data, thereby obtaining high amplitude error sensor fluctuation data and low amplitude error sensor fluctuation data; In this embodiment, based on the statistical fluctuation amplitude range data, the system operation sensor fluctuation amplitude data is classified. For example, a threshold is set to mark the fluctuation data with an amplitude greater than 15V as a high amplitude error, and the fluctuation data with an amplitude less than or equal to 15V as a low amplitude error. Through conditional judgment, the sensor fluctuation data sets of high amplitude error and low amplitude error are obtained respectively, which is convenient for subsequent analysis.

[0067] Step S44: classifying the system operation sensor fluctuation time data by sensor fluctuation time, thereby obtaining long-duration sensor fluctuation data and short-duration sensor fluctuation data; In this embodiment, the sensor fluctuation time data is classified. A time threshold is set. For example, fluctuation data with a duration of more than 5 seconds is marked as long duration, and fluctuation data with a duration of less than 5 seconds is marked as low duration. By traversing the time data list, the fluctuation time is effectively classified and the corresponding data set is generated.

[0068] Step S45: performing a sensor fluctuation time intersection operation on the high-amplitude error sensor fluctuation data and the long-duration sensor fluctuation data, thereby obtaining abnormal operation sensor fluctuation data; performing a sensor fluctuation time intersection operation on the low-amplitude error sensor fluctuation data and the short-duration sensor fluctuation data, thereby obtaining normal operation sensor fluctuation data; In this embodiment, an intersection operation is performed on the high amplitude error sensor fluctuation data and the long duration sensor fluctuation data to filter out abnormal operation sensor fluctuation data that satisfies both conditions. Similarly, an intersection operation is performed on the low amplitude error and low duration data to obtain normal operation sensor fluctuation data. This step is achieved by writing SQL queries or using set operations.

[0069] Step S46: performing time series merging of the abnormal operation sensor fluctuation data and the normal operation sensor fluctuation data, thereby obtaining abnormal sensor fluctuation detection data; In this embodiment, the abnormal operation sensor fluctuation data obtained is merged with the normal operation data in time series. First, the timestamps are sorted to ensure the time series of the data is complete. By marking the abnormal data as "abnormal" and the normal data as "normal", a comprehensive abnormal sensor fluctuation detection data list is formed to facilitate subsequent evaluation and analysis.

[0070] Step S47: Evaluate the support capability of the energy storage system based on the abnormal sensor fluctuation detection data, so as to obtain the support capability score data of the energy storage system.

[0071] In this embodiment, a decision tree or machine learning model is applied to evaluate the support capacity of the energy storage system based on the abnormal sensor fluctuation detection data. The model generates a comprehensive evaluation report by analyzing the frequency and duration of abnormal conditions and other influencing factors, and outputs the support capacity score data of the energy storage system. For example, the score range is 0-100, and the higher the score, the stronger the system support capacity. A score below a certain threshold indicates that there may be safety hazards.

[0072] Optionally, step S47 is specifically: Step S471: dividing abnormal sensing fluctuation components according to abnormal sensing fluctuation detection data, thereby obtaining component abnormal sensing fluctuation data; In this embodiment, the fluctuation data is processed using a statistical analysis method. The component information monitored by the sensor detected as abnormal sensor fluctuation in the abnormal sensor fluctuation detection data is extracted. For example, the fluctuation of the component monitored by sensor A is frequent and large, and is classified as a high abnormal frequency component; the fluctuation of the component monitored by sensor B is small and the frequency of occurrence is low, and is classified as a low abnormal frequency component.

[0073] Step S472: Counting component abnormality frequencies of component abnormality sensor fluctuation data, thereby obtaining high abnormality frequency component data and low abnormality frequency component data; In this embodiment, the frequency statistics are performed on the divided high abnormal frequency components and low abnormal frequency components. The counting method can be used to count the number of abnormal events that occur in each component within a certain period of time. For example, component X has 10 abnormalities in a month, while component Y has only 2 abnormalities. In this way, component X is marked as a high abnormal frequency component, and component Y is a low abnormal frequency component, forming a data set for subsequent analysis.

[0074] Step S473: Calculating component abnormality time for the high abnormal frequency component data and the low abnormal frequency component data, respectively, so as to obtain high abnormal frequency component abnormality time data and low abnormal frequency component abnormality time data; In this embodiment, the abnormal time of the identified high and low abnormal frequency components is calculated. By recording the time of occurrence of each abnormal event, the abnormal duration of each component can be obtained. For example, the abnormal event of component A lasted for 4 days from January 1 to January 5, while the abnormality of component B lasted only 1 day. Based on this information, the abnormal time data of the high abnormal frequency component and the abnormal time data of the low abnormal frequency component are generated respectively.

[0075] Step S474: extracting component operation time features from the energy storage system operation data, thereby obtaining component operation time data; In this embodiment, for the operation data of the energy storage system, the time series analysis method is used to extract the operation time characteristics of the components. The operation time records of the components are collected, and the operation status of each component in different time periods is analyzed. For example, component C has been running for 400 hours in the past 6 months, while component D has been running for 100 hours, thus forming the basis of the component operation time data.

[0076] Step S475: Calculate the abnormal fluctuation time proportions of the high abnormal frequency component abnormal time data and the low abnormal frequency component abnormal time data according to the component operation time data, so as to obtain the high abnormal frequency component abnormal fluctuation time proportion data and the low abnormal frequency component abnormal fluctuation time proportion data; In this embodiment, the abnormal time data and the running time data are combined to calculate the abnormal fluctuation time ratio. The formula is: abnormal fluctuation time ratio = (abnormal time / total running time) × 100%. For example, if the abnormal time of component A is 48 hours and the running time is 400 hours, the abnormal fluctuation time ratio is 12%. Similarly, the same calculation is performed for the low-frequency component to generate the ratio data of high and low abnormal frequency components.

[0077] Step S476: Evaluate the support capability of the energy storage system according to the abnormal fluctuation time proportion data of the high abnormal frequency component and the abnormal fluctuation time proportion data of the low abnormal frequency component, so as to obtain the support capability score data of the energy storage system.

[0078] In this embodiment, the energy storage system support capacity is evaluated based on the abnormal fluctuation time proportion data of high abnormal frequency components and low abnormal frequency components. The weighted average method can be used to comprehensively score the proportion of each component. For example, if the abnormal proportion of high-frequency components is high, the overall support capacity score will be reduced; if the abnormal proportion of low-frequency components is low, the overall score will be improved. Finally, the energy storage system support capacity score data is formed to help decision-making and optimize system operation.

[0079] Optionally, step S476 is specifically: Obtain expert experience data on energy storage systems; In this embodiment, an interview framework including energy storage system experts is constructed, covering key areas such as system design, operation and maintenance, fault diagnosis and performance evaluation. The experience and opinions of experts on high and low abnormal frequency components are collected through questionnaires and face-to-face interviews. The data should include the abnormal frequency, typical failure mode and its impact on the system operation efficiency and stability of each component. Through statistical analysis, the experts' data on the proportion of abnormal fluctuation time of different types of components are summarized to form a basic database.

[0080] According to the experience data of energy storage system experts, the influence factors of energy storage system operation efficiency are estimated based on the abnormal fluctuation time proportion data of high abnormal frequency components, so as to obtain the influence factors of energy storage system operation efficiency; In this embodiment, based on the acquired expert experience data, high abnormal frequency components are selected to analyze the proportion of their abnormal fluctuation time. Regression analysis is used to calculate the impact factors of these fluctuations on the overall operating efficiency of the energy storage system. A linear regression model is established, with the proportion of abnormal fluctuation time as the independent variable and the operating efficiency as the dependent variable. The significance of the influencing factors is measured by the R² value of the model, and detailed effect values ​​are given for each component. The collected expert data can also be analyzed to compare the abnormal fluctuation time of high abnormal frequency components (such as high cycle life batteries) with the overall operating time. The weighted average method is applied, combined with the expert scores for the performance of these components, to determine the impact factors on the operating efficiency. For example, if the expert evaluates that the component efficiency drops by 15% when the high-frequency fluctuation exceeds 5%, the impact factor can be set to 0.15.

[0081] According to the experience data of energy storage system experts, the energy storage system stability influencing factor is estimated based on the abnormal fluctuation time proportion data of low abnormal frequency components, so as to obtain the energy storage system stability influencing factor; In this embodiment, a similar process is repeated for low abnormal frequency components to analyze the impact of the proportion of abnormal fluctuation time on system stability. A similar statistical model, such as logistic regression or time series analysis, is used to explore how the fluctuations of these components affect the stability of the system. Special attention is paid to the effects of factors such as frequency fluctuations and load changes, and the specific values ​​of stability influencing factors are calculated. Similarly, the abnormal fluctuation time of low abnormal frequency components (such as pumped storage equipment) is analyzed. Through expert experience, the stability performance of these components under abnormal conditions is evaluated. If experts point out that when the low-frequency fluctuation time accounts for more than 10%, the system stability may be reduced by 20%, then the impact factor can be set to 0.20, and quantitative analysis is performed based on the data.

[0082] Construct a calculation model for the energy storage system support capability score based on the factors affecting the energy storage system operation efficiency and the energy storage system stability; In this embodiment, a weighted scoring model is constructed by combining the results of the first two steps, with the energy storage system operation efficiency influencing factor and stability influencing factor as input variables. The weight coefficient is set through expert experience (for example, the operation efficiency weight is 0.6, and the stability weight is 0.4), and the score calculation formula is established: support capacity score = 0.6 × operation efficiency influencing factor + 0.4 × stability influencing factor; this model can effectively reflect the comprehensive support capacity of the energy storage system, and it is recommended to be regularly calibrated and optimized in actual applications.

[0083] The energy storage system support capability score calculation model is used to calculate the energy storage system support capability score for the abnormal fluctuation time proportion data of high abnormal frequency components and the abnormal fluctuation time proportion data of low abnormal frequency components, thereby obtaining the energy storage system support capability score data.

[0084] In this embodiment, the constructed support capability score calculation model is used to input the abnormal fluctuation time proportion data of high and low abnormal frequency components collected previously. Through model calculation, the support capability score of each component and system is obtained. The results can be visualized and the support capability scores of different components can be displayed in the form of charts to help decision makers identify weak links in the system and make optimization adjustments. For example, a low score for a high abnormal frequency component may indicate the need to optimize its design or increase maintenance frequency to improve the overall system performance.

[0085] Optionally, the present invention further provides an energy storage system support capability assessment model construction system, which is used to execute the energy storage system support capability assessment model construction method as described above, and the energy storage system support capability assessment model construction system includes: A topology modeling module is used to obtain energy storage system structure data, and perform energy storage system topology modeling based on the energy storage system structure data, thereby obtaining an energy storage system topology model; A sensor data fusion module is used to obtain the energy storage system operation data and the energy storage system sensor data, and to fuse the energy storage system sensor data according to the energy storage system topology model, so as to obtain the energy storage system sensor network; A sensor fluctuation mode integration module is used to identify the electrical operation mode of the energy storage system based on the operation data of the energy storage system, so as to obtain the electrical operation mode data of the energy storage system, and to integrate the system operation sensor fluctuation mode of the electrical operation mode data of the energy storage system according to the energy storage system sensor network, so as to obtain the system operation sensor fluctuation mode data; A support capability evaluation module is used to perform abnormal sensor fluctuation detection on the system operation sensor fluctuation mode data, thereby obtaining abnormal sensor fluctuation detection data, and to evaluate the support capability of the energy storage system based on the abnormal sensor fluctuation detection data, thereby obtaining the support capability score data of the energy storage system; The model building module is used to build an energy storage system support capability evaluation model based on abnormal sensor fluctuation detection data and energy storage system support capability score data.

[0086] 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.

[0087] 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 method for constructing a support capability assessment model for an energy storage system, characterized in that: The following steps are involved: Step S1: Acquire energy storage system structure data, and perform energy storage system topology modeling according to the energy storage system structure data, thereby obtaining an energy storage system topology model; Step S2: acquiring energy storage system operation data and energy storage system sensor data, and fusing the energy storage system sensor data according to the energy storage system topology model, thereby obtaining an energy storage system sensor network; Step S3: identifying the electrical operation mode of the energy storage system based on the operation data of the energy storage system, thereby obtaining the electrical operation mode data of the energy storage system, and integrating the system operation sensor fluctuation mode of the electrical operation mode data of the energy storage system according to the energy storage system sensor network, thereby obtaining the system operation sensor fluctuation mode data; Step S4: performing abnormal sensor fluctuation detection on the system operation sensor fluctuation mode data, thereby obtaining abnormal sensor fluctuation detection data, and performing energy storage system support capability evaluation based on the abnormal sensor fluctuation detection data, thereby obtaining energy storage system support capability score data; Step S5: constructing an energy storage system support capability assessment model based on the abnormal sensor fluctuation detection data and the energy storage system support capability score data.

2. The method for constructing an energy storage system support capability assessment model according to claim 1, characterized in that: Step S1 is specifically as follows: Step S11: Acquire energy storage system structure data, and perform structural division on the energy storage system structure data, thereby obtaining energy storage component structure data and control component structure data; Step S12: performing control component spatial distribution analysis according to the control component structure data, thereby obtaining control component spatial distribution data; Step S13: integrating the spatial distribution profile of the control component spatial distribution data, thereby obtaining the spatial distribution profile data of the control component; Step S14: integrating component connection relationships according to the control component spatial distribution profile data and the energy storage component structure data, thereby obtaining energy storage system component connection relationship data; Step S15: Modeling the energy storage system topology based on the energy storage system component connection relationship data, thereby obtaining an energy storage system topology model.

3. The method for constructing an energy storage system support capability assessment model according to claim 2, characterized in that: Step S14 is specifically as follows: Step S141: integrating the energy storage component structure data into an energy storage component structure profile, thereby obtaining the energy storage component structure profile data; Step S142: performing similarity calculation on the energy storage component structure profile data and the control component spatial distribution profile data, thereby obtaining profile similarity data; Step S143: performing high-similarity profile combination and integration on the energy storage component structure profile data and the control component spatial distribution profile data according to the profile similarity data, thereby obtaining high-similarity profile combination data; Step S144: integrating the structural connection relationship of the energy storage component structure data and the control component structure data based on the high-similarity profile combination data, thereby obtaining energy storage system component connection relationship data.

4. The method for constructing an energy storage system support capability assessment model according to claim 1, characterized in that: Step S2 is specifically as follows: Step S21: Acquire energy storage system operation data and energy storage system sensor data; Step S22: extracting sensor space features from the energy storage system sensor data to obtain sensor space data; Step S23: constructing a sensor space coordinate system according to the sensor space data, thereby obtaining sensor space coordinate system data; Step S24: performing sensor data fusion on the energy storage system sensor data according to the sensor space coordinate system data, thereby obtaining a sensor network; Step S25: Fusion of component spatial relationships of the sensor network is performed according to the energy storage system topology model, thereby obtaining the energy storage system sensor network.

5. The method for constructing an energy storage system support capability assessment model according to claim 1, characterized in that: Step S3 is specifically as follows: Step S31: extracting operating electrical characteristics and operating mode characteristics based on the energy storage system operating data, thereby obtaining the energy storage system operating electrical data and the energy storage system operating mode data; Step S32: performing frequency domain conversion on the electrical data of the energy storage system operation to obtain the electrical spectrum of the energy storage system operation, and integrating the spectrum amplitude characteristics according to the electrical spectrum of the energy storage system operation to obtain electrical spectrum amplitude data; Step S33: performing minimum amplitude spectrum selection according to the electrical spectrum amplitude data, thereby obtaining electrical stable amplitude data; Step S34: performing operation electrical benchmark statistics based on the electrical stability amplitude data, thereby obtaining operation electrical benchmark data; Step S35: performing electrical amplitude pattern recognition on the electrical spectrum amplitude data according to the operating electrical reference data, thereby obtaining operating electrical amplitude pattern data; Step S36: performing time-series correlation on the operation electrical amplitude mode data and the energy storage system operation mode data, thereby obtaining the energy storage system electrical operation mode data; Step S37: integrating the system operation sensor fluctuation mode of the energy storage system electrical operation mode data according to the energy storage system sensor network, thereby obtaining the system operation sensor fluctuation mode data.

6. The method for constructing an energy storage system support capability assessment model according to claim 5, characterized in that: Step S37 is specifically as follows: Step S371: collecting electrical component sensor data based on the energy storage system sensor network, thereby obtaining electrical component sensor data; Step S372: performing sensor fluctuation statistics according to the electrical component sensor data, thereby obtaining the electrical component sensor fluctuation data; Step S373: performing sensor fluctuation pattern recognition based on the sensor fluctuation data of the electrical component, thereby obtaining sensor fluctuation pattern data; Step S374: Time-series correlation is performed on the sensor fluctuation mode data and the energy storage system electrical operation mode data, so as to obtain the system operation sensor fluctuation mode data.

7. The method for constructing an energy storage system support capability assessment model according to claim 1, characterized in that: Step S4 is specifically as follows: Step S41: performing sensor fluctuation amplitude calculation and sensor fluctuation time calculation on the system operation sensor fluctuation mode data, thereby obtaining the system operation sensor fluctuation amplitude data and the system operation sensor fluctuation time data; Step S42: performing statistics of the fluctuation amplitude range of the fluctuation mode according to the sensing fluctuation mode data, thereby obtaining the fluctuation amplitude range data of the fluctuation mode; Step S43: classifying the system operation sensor fluctuation amplitude data based on the fluctuation mode fluctuation amplitude range data, thereby obtaining high amplitude error sensor fluctuation data and low amplitude error sensor fluctuation data; Step S44: classifying the system operation sensor fluctuation time data by sensor fluctuation time, thereby obtaining long-duration sensor fluctuation data and short-duration sensor fluctuation data; Step S45: performing a sensor fluctuation time intersection operation on the high amplitude error sensor fluctuation data and the long duration sensor fluctuation data, thereby obtaining abnormal operation sensor fluctuation data; Perform sensor fluctuation time intersection operation on low-amplitude error sensor fluctuation data and low-duration sensor fluctuation data, so as to obtain normal operation sensor fluctuation data; Step S46: performing time series merging of the abnormal operation sensor fluctuation data and the normal operation sensor fluctuation data, thereby obtaining abnormal sensor fluctuation detection data; Step S47: Evaluate the support capability of the energy storage system based on the abnormal sensor fluctuation detection data, so as to obtain the support capability score data of the energy storage system.

8. The method for constructing an energy storage system support capability assessment model according to claim 7, characterized in that: Step S47 is specifically as follows: Step S471: dividing abnormal sensing fluctuation components according to abnormal sensing fluctuation detection data, thereby obtaining component abnormal sensing fluctuation data; Step S472: Counting component abnormality frequencies of component abnormality sensor fluctuation data, thereby obtaining high abnormality frequency component data and low abnormality frequency component data; Step S473: Calculating component abnormality time for the high abnormal frequency component data and the low abnormal frequency component data, respectively, so as to obtain high abnormal frequency component abnormality time data and low abnormal frequency component abnormality time data; Step S474: extracting component operation time features from the energy storage system operation data, thereby obtaining component operation time data; Step S475: Calculate the abnormal fluctuation time proportions of the high abnormal frequency component abnormal time data and the low abnormal frequency component abnormal time data according to the component operation time data, thereby obtaining the high abnormal frequency component abnormal fluctuation time proportion data and the low abnormal frequency component abnormal fluctuation time proportion data; Step S476: Evaluate the support capability of the energy storage system according to the abnormal fluctuation time proportion data of the high abnormal frequency component and the abnormal fluctuation time proportion data of the low abnormal frequency component, so as to obtain the support capability score data of the energy storage system.

9. The method for constructing an energy storage system support capability assessment model according to claim 8, characterized in that: Step S476 is specifically as follows: Obtain expert experience data on energy storage systems; According to the experience data of energy storage system experts, the influence factors of energy storage system operation efficiency are estimated based on the abnormal fluctuation time proportion data of high abnormal frequency components, so as to obtain the influence factors of energy storage system operation efficiency; According to the experience data of energy storage system experts, the energy storage system stability influencing factor is estimated based on the abnormal fluctuation time proportion data of low abnormal frequency components, so as to obtain the energy storage system stability influencing factor; Construct a calculation model for the energy storage system support capability score based on the factors affecting the energy storage system operation efficiency and the energy storage system stability; The energy storage system support capability score calculation model is used to calculate the energy storage system support capability score for the abnormal fluctuation time proportion data of high abnormal frequency components and the abnormal fluctuation time proportion data of low abnormal frequency components, thereby obtaining the energy storage system support capability score data.

10. A system for constructing a support capability assessment model for an energy storage system, characterized in that: Used to execute the energy storage system support capability assessment model construction method according to claim 1, the energy storage system support capability assessment model construction system comprises: A topology modeling module is used to obtain energy storage system structure data, and perform energy storage system topology modeling based on the energy storage system structure data, thereby obtaining an energy storage system topology model; A sensor data fusion module is used to obtain the energy storage system operation data and the energy storage system sensor data, and to fuse the energy storage system sensor data according to the energy storage system topology model, so as to obtain the energy storage system sensor network; A sensor fluctuation mode integration module is used to identify the electrical operation mode of the energy storage system based on the operation data of the energy storage system, so as to obtain the electrical operation mode data of the energy storage system, and to integrate the system operation sensor fluctuation mode of the electrical operation mode data of the energy storage system according to the energy storage system sensor network, so as to obtain the system operation sensor fluctuation mode data; A support capability evaluation module is used to perform abnormal sensor fluctuation detection on the system operation sensor fluctuation mode data, thereby obtaining abnormal sensor fluctuation detection data, and to evaluate the support capability of the energy storage system based on the abnormal sensor fluctuation detection data, thereby obtaining the support capability score data of the energy storage system; The model building module is used to build an energy storage system support capability evaluation model based on abnormal sensor fluctuation detection data and energy storage system support capability score data.

Images