Industrial energy storage system management method and system based on multi-source data

Abstract

The present invention relates to the technical field of industrial energy storage management, and in particular to an industrial energy storage system management method and system based on multi-source data. The method comprises the following steps: obtaining comprehensive multi-source data of industrial energy storage; performing data preprocessing on the comprehensive multi-source data of industrial energy storage to generate standard comprehensive multi-source data of industrial energy storage; performing environmental data classification on the standard comprehensive multi-source data of industrial energy storage to generate internal environmental data of industrial energy storage and external environmental data of industrial energy storage; performing equipment operation status classification on the internal environmental data of industrial energy storage to obtain normal equipment operation status data and abnormal equipment operation status data; performing a first warning on the abnormal equipment operation status data to generate abnormal internal environment warning data. The present invention improves the comprehensiveness and accuracy of industrial energy storage system management through systematic data preprocessing, comprehensive equipment and environment monitoring, intelligent energy efficiency prediction and dual warning mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial energy storage management, and in particular to an industrial energy storage system management method and system based on multi-source data. Background Art

[0002] Initially, energy storage systems mostly used flywheel energy storage and batteries, and their application scope was limited to small industrial equipment and power supply systems. With the advancement of science and technology, especially the development of semiconductor technology, electronic control systems have gradually been introduced into energy storage systems, improving the intelligence level of energy storage management. At the beginning of the 21st century, battery technology and energy storage management technology entered a rapid development stage. The emergence of lithium-ion batteries has greatly promoted the application of energy storage systems, and they have begun to be widely used in industrial energy storage systems. At the same time, the advancement of digital control technology and sensor technology has made the monitoring and management of energy storage systems more accurate and efficient. The introduction of big data and cloud computing technologies has provided new methods for the optimization and prediction of energy storage systems, allowing energy storage and release strategies to be optimized through real-time data analysis. In recent years, the rise of multi-source data fusion technology, especially the application of the Internet of Things (IoT) and artificial intelligence (AI), has provided a more intelligent solution for the management of industrial energy storage systems. By collecting system status data through a variety of sensors and data sources, combined with advanced algorithms and models, real-time monitoring, fault prediction and performance optimization of energy storage systems can be achieved. However, current existing technologies usually ignore the in-depth analysis of external environmental data and are unable to comprehensively assess the impact of the environment on the energy storage system. At the same time, the early warning mechanism only targets a single data source or event, resulting in insufficient comprehensiveness and timeliness of the early warning, which in turn leads to low comprehensiveness and accuracy of management. Summary of the invention

[0003] Based on this, it is necessary to provide an industrial energy storage system management method and system based on multi-source data to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for managing an industrial energy storage system based on multi-source data is provided, the method comprising the following steps:

[0005] Step S1: Acquire comprehensive multi-source data of industrial energy storage; perform data preprocessing on the comprehensive multi-source data of industrial energy storage to generate standard comprehensive multi-source data of industrial energy storage; perform environmental data classification on the standard comprehensive multi-source data of industrial energy storage to generate internal environmental data of industrial energy storage and external environmental data of industrial energy storage;

[0006] Step S2: divide the internal environment data of industrial energy storage into equipment operation states, and obtain equipment normal operation state data and equipment abnormal operation state data; perform a first warning on the equipment abnormal operation state data, and generate internal environment abnormal warning data; perform electric energy storage unit network integration on the equipment normal operation state data, and generate an electric energy storage unit integrated network; perform energy storage efficiency analysis on the electric energy storage unit integrated network, and generate internal energy storage efficiency data of industrial energy storage;

[0007] Step S3: extracting environmental features from the external environmental data of the industrial energy storage to obtain external environmental feature data of the industrial energy storage; performing abnormal environmental monitoring on the industrial energy storage system according to the external environmental feature data of the industrial energy storage through the electric energy storage unit integrated network to generate normal environmental monitoring data and abnormal environmental monitoring data, and performing a second warning on the abnormal environmental monitoring data to generate external environmental abnormal warning data;

[0008] Step S4: Based on the normal environment monitoring data, the internal energy storage efficiency data of the industrial energy storage is predicted to generate the industrial energy storage energy efficiency prediction data; the industrial energy storage energy efficiency prediction data is autonomously warned and regulated by the internal environment abnormal warning data and the external environment abnormal warning data, thereby generating the industrial energy storage management and control strategy to execute the industrial energy storage system management operation.

[0009] The present invention improves the consistency and availability of data by acquiring and preprocessing comprehensive multi-source data, and classifying it into internal environment data and external environment data after standardization, thereby providing a solid foundation for accurate analysis and decision-making. The internal environment data is divided into equipment status, which can effectively distinguish the normal and abnormal operation status of the equipment, and generate internal environment abnormality warning data, which enhances the real-time monitoring capability of the equipment operation status, timely discovers potential faults, and reduces the risk of equipment downtime. By performing network integration of electric energy storage units and energy storage efficiency analysis on the normal operation status data of the equipment, internal energy storage efficiency data is generated, the integration and management of electric energy storage units are optimized, and the overall efficiency and performance of the energy storage system are improved. The external environment data is feature extracted to generate industrial energy storage external environment feature data, so that the system can comprehensively monitor and evaluate the impact of the external environment on the energy storage system, and ensure the stable operation of the system under different environmental conditions. The normal and abnormal environment monitoring data generated by abnormal environment monitoring, as well as the second warning of abnormal environment data, can issue an alarm in time when the environment changes, reducing the negative impact of the external environment on the energy storage system. Based on the energy efficiency prediction of normal environmental monitoring data, and the autonomous warning control combined with internal and external abnormal warning data, an industrial energy storage management and control strategy is generated, which realizes the dynamic and intelligent management of the energy storage system and improves the accuracy of energy efficiency prediction and the flexibility of control. The management and control strategy generated by the above process can accurately and specifically manage the energy storage system, optimize resource allocation and operation, reduce operating costs, extend the service life of the system, and improve the overall reliability and economic benefits of the energy storage system. Therefore, the present invention improves the comprehensiveness and accuracy of industrial energy storage system management through systematic data preprocessing, comprehensive equipment and environmental monitoring, intelligent energy efficiency prediction and dual warning mechanism.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire comprehensive multi-source data of industrial energy storage;

[0012] Step S12: performing data cleaning on the comprehensive multi-source data of industrial energy storage to generate comprehensive multi-source cleaned data of industrial energy storage;

[0013] Step S13: Fill missing values ​​in the industrial energy storage comprehensive multi-source cleaned data to generate industrial energy storage comprehensive multi-source filled data;

[0014] Step S14: Standardize the industrial energy storage comprehensive multi-source data by using the Z-score method to generate standard industrial energy storage comprehensive multi-source data; classify the environmental data of the standard industrial energy storage comprehensive multi-source data to generate industrial energy storage internal environmental data and industrial energy storage external environmental data.

[0015] The present invention can effectively remove or correct the noise, errors and outliers in the data through data cleaning (step S12), thereby improving the accuracy and reliability of the data. Filling missing values ​​in the data (step S13) ensures the integrity of the data and avoids analytical deviations and misjudgments caused by missing values. Using the Z-score method to standardize the data (step S14) can eliminate the dimensional differences between different variables, so that the data has better comparability and consistency. This is crucial for subsequent data analysis and modeling. The standardized data is classified into environmental data (step S14) to generate internal environmental data and external environmental data of industrial energy storage, which helps to analyze and monitor the impact of internal and external environments on the energy storage system respectively, so as to perform more targeted optimization and improvement. Through the above steps, the generated industrial energy storage comprehensive multi-source cleaned data, filled data and standardized data are all high-quality data, which can effectively improve the accuracy and efficiency of data analysis, modeling and prediction. High-quality data provides a solid foundation for decision-making. The cleaned, filled and standardized data can be used in various analysis and prediction models, thereby providing a scientific basis for the optimization operation and maintenance decision of the industrial energy storage system.

[0016] Preferably, step S2 comprises the following steps:

[0017] Step S21: filtering the internal equipment operation data of the industrial energy storage internal environment data to obtain the internal equipment operation data of the industrial energy storage;

[0018] Step S22: dividing the internal equipment operation data of the industrial energy storage into equipment operation states, obtaining equipment normal operation state data and equipment abnormal operation state data; performing a first warning on the equipment abnormal operation state data, and generating internal environment abnormality warning data;

[0019] Step S23: using the electric energy sensor to collect equipment operation data according to the normal operation status data of the equipment, to obtain the electric energy equipment operation data;

[0020] Step S24: Performing electric energy storage unit network integration on the electric energy equipment operation data to generate an electric energy storage unit integrated network; performing energy storage efficiency analysis on the electric energy storage unit integrated network to generate internal energy storage efficiency data for industrial energy storage.

[0021] The present invention ensures that only key data related to the operation of the equipment is processed by screening the internal equipment operation data, thereby improving the data processing efficiency and accuracy. By dividing the equipment operation status, the normal and abnormal operation status of the equipment can be identified in real time, which is helpful to timely discover and deal with potential problems. The first warning of the abnormal operation status data of the equipment can generate internal environment abnormal warning data, thereby providing early warning, preventing the problem from expanding, and ensuring the safe operation of the system. The equipment operation data is collected by using the electric energy sensor according to the normal operation status data of the equipment, ensuring the accuracy and reliability of the collected data, thereby providing high-quality data for subsequent analysis. By integrating the electric energy storage unit network of the electric energy equipment operation data, the data of multiple energy storage units can be effectively integrated to form a comprehensive electric energy storage unit integrated network. This helps to fully understand the operation status and performance of the entire energy storage system. By analyzing the energy storage efficiency of the electric energy storage unit integrated network, the internal energy storage efficiency data of the industrial energy storage can be generated, thereby providing a scientific basis for optimizing the energy storage and utilization of the system. By analyzing the energy storage efficiency of the electric energy storage unit integrated network, the factors affecting the energy storage efficiency can be identified and optimized, thereby improving the energy utilization efficiency of the entire energy storage system, reducing energy losses, and improving economic benefits. The generated internal environment abnormality warning data and energy storage efficiency data provide important references for system maintenance and optimization. Decision makers can make scientific decisions based on these data, optimize equipment operation and energy storage strategies, and improve the overall performance of the system. Through real-time monitoring and early warning, timely detection and handling of abnormal situations can effectively improve the stability and reliability of the system, reduce equipment failures and downtime, and ensure the continuous operation of the system.

[0022] Preferably, dividing the equipment operation status of the internal equipment operation data of the industrial energy storage device includes:

[0023] Monitor the real-time operation data of the internal equipment of the industrial energy storage system to obtain the real-time operation data of the internal equipment; read the historical operation data of the internal equipment of the industrial energy storage system to obtain the historical operation data of the internal equipment;

[0024] Conduct operation fluctuation analysis on real-time operation data of internal equipment to generate operation fluctuation data of internal equipment; conduct maintenance analysis on historical operation data of internal equipment to generate maintenance data of internal equipment;

[0025] Perform frequency calculation on internal equipment operation fluctuation data and internal equipment maintenance data to obtain internal equipment fluctuation frequency data and internal equipment maintenance frequency data; perform fast spectrum conversion on internal equipment fluctuation frequency data and internal equipment maintenance frequency data to generate internal equipment fluctuation spectrum curve and internal equipment historical maintenance spectrum curve;

[0026] Perform curve fitting on the internal equipment fluctuation spectrum curve and the internal equipment historical maintenance spectrum curve to generate an internal equipment fault fitting curve; map the internal equipment operation data of the industrial energy storage to the internal equipment fault fitting curve to perform deviation calculation to obtain equipment operation deviation data;

[0027] The equipment operation deviation data is compared with the preset deviation threshold. When the equipment operation deviation data is greater than the preset deviation threshold, the corresponding industrial energy storage internal equipment operation data is marked as equipment abnormal operation status data; when the equipment operation deviation data is less than or equal to the preset deviation threshold, the corresponding industrial energy storage internal equipment operation data is marked as equipment normal operation status data.

[0028] The present invention combines real-time equipment operation data monitoring with historical equipment operation data reading, and can provide comprehensive equipment operation conditions, including current status and historical performance, to ensure the comprehensiveness and reliability of monitoring. The internal equipment operation fluctuation data generated by operation fluctuation analysis can identify abnormal fluctuations in equipment operation and discover potential problems in a timely manner. The internal equipment maintenance data generated by maintenance analysis helps to understand the maintenance history and maintenance frequency of the equipment, and provides a basis for predicting and preventing faults. The fluctuation frequency data and maintenance frequency data generated by frequency calculation can quantify the operation fluctuations and maintenance conditions of the equipment and provide detailed frequency information. The fluctuation spectrum curve and historical maintenance spectrum curve generated by fast spectrum conversion further reveal the regularity and periodicity of equipment operation and maintenance through frequency domain analysis. The fault fitting curve generated by curve fitting the fluctuation spectrum curve and the historical maintenance spectrum curve can more accurately reflect the fault characteristics of the equipment. The deviation calculation compares the current equipment operation status with the historical fault mode, and can discover abnormal conditions in a timely manner, thereby improving the accuracy of fault detection. The equipment operation deviation data is compared with the preset deviation threshold, and the operation status of the equipment can be quickly judged. Status marking marks the equipment operation data according to the degree of deviation, clearly distinguishing between normal and abnormal operation states, which helps to quickly respond to and handle abnormal situations. By comprehensively utilizing real-time data and historical data, through spectrum analysis and curve fitting, it is possible to more accurately identify equipment failure signs and abnormal conditions, and reduce false alarms and missed alarms. Through accurate fault detection and early warning, maintenance personnel can take measures in advance for preventive maintenance, reduce equipment failures and downtime, and improve equipment reliability and availability. Marking and recording abnormal operation status data provides data support for subsequent equipment management and optimization. Through accurate monitoring and analysis of equipment operation status, the operation strategy of the energy storage system can be optimized, energy storage and utilization efficiency can be improved, operating costs can be reduced, and overall system performance can be improved.

[0029] Preferably, step S24 includes the following steps:

[0030] Step S241: confirming the equipment base station address of the electric energy equipment operation data to obtain the equipment base station address data;

[0031] Step S242: allocating operation data of the electric energy equipment according to the equipment base station address data to generate electric energy storage unit data; constructing a network topology structure for the electric energy storage unit data to obtain network topology structure data of the electric energy storage unit;

[0032] Step S243: extracting power data from the electric energy storage unit data to obtain power characteristic data of the electric energy storage unit; performing charge and discharge energy analysis on the power characteristic data of the electric energy storage unit to obtain charging power data and discharging power data; and constructing edge connections based on the charging power data and the discharging power data to obtain network edge connection data;

[0033] Step S244: Integrate the electric energy storage unit network through network edge connection data and electric energy storage unit network topology data to generate an electric energy storage unit integrated network; perform energy storage efficiency analysis on the electric energy storage unit integrated network to generate internal energy storage efficiency data for industrial energy storage.

[0034] The present invention ensures the accuracy of data geographic positioning by confirming the address of the equipment base station, and facilitates the management and analysis of data from different base stations. The operation data is distributed according to the equipment base station address data, which helps to effectively organize and manage the data of the electric energy storage unit and ensure the orderliness and consistency of the data. The network topology structure of the electric energy storage unit data is constructed, and the generated network topology structure data of the electric energy storage unit can clearly describe the network structure of the electric energy storage system, which helps to understand the connection relationship and data flow between the units. The power data of the electric energy storage unit data is extracted, and the obtained power characteristic data provides a basis for further energy analysis. The charge and discharge energy analysis of the power characteristic data can obtain the charging power data and the discharging power data respectively, which are very important for evaluating the performance and usage of the energy storage unit. The edge connection is constructed based on the charging power data and the discharging power data, and the generated network edge connection data can describe the energy transfer relationship between the energy storage units, which helps to optimize the energy distribution and flow. The electric energy storage unit network is integrated through the network edge connection data and the network topology structure data, and the generated electric energy storage unit integrated network can fully integrate and coordinate the operation of each energy storage unit, and improve the overall coordination and efficiency of the system. Energy storage efficiency analysis of the integrated network of electric energy storage units is performed, and the generated energy storage efficiency data can help identify and optimize factors that affect energy storage efficiency, improve the energy utilization of the entire system, and reduce energy loss. Through the meticulous data confirmation, allocation, analysis and integration process, the operating status of the energy storage system can be fully understood and mastered, which helps to timely discover problems and make optimization adjustments, and improve system management and optimization capabilities. Accurate base station address confirmation and data allocation ensure the accuracy and consistency of data, which helps to improve the reliability of the system. Network integration and energy storage efficiency analysis help optimize energy distribution and utilization, and improve the stability and efficiency of the system. The generated internal energy storage efficiency data provides a scientific basis for system optimization, helping decision makers to formulate effective management strategies and optimization plans, and improve the overall performance and economic benefits of the system.

[0035] Preferably, step S3 comprises the following steps:

[0036] Step S31: extracting environmental features from the external environmental data of the industrial energy storage to obtain external environmental feature data of the industrial energy storage, wherein the external environmental feature data of the industrial energy storage includes environmental temperature data, environmental humidity data and environmental air pressure data;

[0037] Step S32: Associating the geographical data of industrial energy storage equipment with the industrial energy storage system through the electric energy storage unit integrated network to generate geographical environment data of the industrial energy storage equipment;

[0038] Step S33: Performing a multi-factor external environmental impact analysis on the geographical environment data of the industrial energy storage equipment based on the ambient temperature data, the ambient humidity data, and the ambient air pressure data to generate an external environmental impact factor for the industrial energy storage;

[0039] Step S34: Perform abnormal environment monitoring on the external environment data of the industrial energy storage according to the external environment influencing factors of the industrial energy storage, generate normal environment monitoring data and abnormal environment monitoring data, perform a second warning on the abnormal environment monitoring data, and generate external environment abnormal warning data.

[0040] The present invention extracts environmental features from the external environmental data of industrial energy storage to obtain environmental temperature data, environmental humidity data and environmental pressure data, and these feature data provide a basis for subsequent environmental impact analysis and monitoring. The industrial energy storage system is associated with the geographical data of industrial energy storage equipment through the electric energy storage unit integrated network, and the generated geographical environmental data of industrial energy storage equipment can accurately locate the geographical location of the energy storage equipment, which is helpful to understand the impact of environmental factors on equipment at different locations. Based on the environmental temperature data, environmental humidity data and environmental pressure data, the geographical environmental data of industrial energy storage equipment is analyzed by multiple factors of external environmental impact, and the generated external environmental impact factors can comprehensively evaluate the impact of various environmental factors on the energy storage system, and provide a reference for optimizing system performance and safety. According to the external environmental impact factors of industrial energy storage, the external environmental data of industrial energy storage is monitored for abnormal environment, and normal environmental monitoring data and abnormal environmental monitoring data are generated. A second warning is performed on the abnormal environmental monitoring data to generate abnormal external environmental warning data, which can timely discover and respond to abnormal environmental conditions and ensure the safety and stability of the system. Through environmental feature extraction and multi-factor impact analysis, the impact of the external environment on the energy storage system can be fully understood, abnormal environmental conditions can be discovered and warned in time, and the safety and reliability of the system can be improved. Based on environmental influencing factors and abnormal environmental monitoring data, more scientific equipment operation and maintenance strategies can be formulated to optimize the operating environment of energy storage equipment, extend equipment life, and reduce maintenance costs. By associating geographic data and environmental characteristic data, environmental characteristics of different geographical locations can be identified and analyzed, the adaptability of energy storage systems to different environmental conditions can be improved, and stable operation in various environments can be ensured. The generated external environmental influencing factors and abnormal warning data provide scientific data support for managers, help make effective decisions, and improve the scientificity and effectiveness of system management.

[0041] Preferably, step S33 includes the following steps:

[0042] Step S331: extracting the extreme temperature of the geographical environment of the industrial energy storage equipment according to the ambient temperature data, generating extreme low temperature data and extreme high temperature data; performing performance impact analysis on the internal energy storage efficiency data of the industrial energy storage through the extreme low temperature data and the extreme high temperature data, generating an ambient temperature impact factor;

[0043] Step S332: Calculate the environmental dryness of the geographical environment data of the industrial energy storage equipment according to the environmental humidity data to obtain the equipment environmental dryness data; use the environmental equipment dryness data to perform stability impact analysis on the internal energy storage efficiency data of the industrial energy storage to generate an environmental humidity impact factor;

[0044] Step S333: Performing geographic elevation conversion on the geographic environment data of the industrial energy storage equipment to generate elevation data of the industrial energy storage equipment; performing altitude analysis on the elevation data of the industrial energy storage equipment to generate altitude data of the energy storage equipment; performing equipment structure impact analysis on the altitude data of the energy storage equipment through the ambient air pressure data to generate an ambient air pressure impact factor;

[0045] Step S334: Integrate the environmental temperature influence factor, the environmental humidity influence factor and the environmental pressure influence factor to generate the external environment influence factor of industrial energy storage.

[0046] The present invention generates extreme low temperature data and extreme high temperature data by performing extreme temperature extraction on ambient temperature data, and analyzes the performance impact of these data to generate ambient temperature impact factors. This helps to identify and evaluate the impact of extreme temperature conditions on the performance of the energy storage system, optimize system design and operation strategies to improve the efficiency and stability of the system under different temperature conditions. By calculating the environmental dryness data, the stability impact analysis is performed on the internal energy storage efficiency data of the industrial energy storage, and the environmental humidity impact factor is generated. This can evaluate the impact of humidity changes on the stability of the energy storage system, help formulate effective humidity control measures, and ensure the stable operation of the energy storage system under different humidity conditions. The geographical environment data is converted to elevation and analyzed, and the equipment structure impact analysis is performed in combination with the ambient air pressure data to generate the ambient air pressure impact factor. This helps to understand the impact of elevation and air pressure changes on the structure and performance of energy storage equipment, optimize equipment selection and structural design, and improve the adaptability of the system under different altitude conditions. The ambient temperature, ambient humidity and ambient air pressure impact factors are integrated to generate a comprehensive external environmental impact factor of industrial energy storage. This comprehensive factor can fully reflect the comprehensive impact of various external environmental factors on the energy storage system, and provide a scientific basis for the design, operation and maintenance of the system. Through comprehensive analysis of multiple environmental factors, step S33 can comprehensively evaluate the impact of the external environment on the energy storage system, help formulate more scientific response strategies, and improve the adaptability and reliability of the system under various environmental conditions. Based on the analysis results of environmental impact factors, the design and operation strategies of the energy storage system can be optimized, the adverse effects of environmental factors on system performance can be reduced, and the overall efficiency and safety of the system can be improved. The generated environmental impact factors provide scientific data support for managers, help make more reasonable decisions, and improve the scientificity and effectiveness of system management. By optimizing the energy storage efficiency analysis, the energy utilization efficiency of the energy storage system can be improved, energy loss can be reduced, and the economy and environmental protection of the system can be improved.

[0047] Preferably, step S4 comprises the following steps:

[0048] Step S41: Integrate the internal environment abnormality warning data and the external environment abnormality warning data to generate comprehensive environment abnormality warning data;

[0049] Step S42: performing energy efficiency prediction on the internal energy storage efficiency data of the industrial energy storage based on the normal environment monitoring data to generate industrial energy storage energy efficiency prediction data;

[0050] Step S43: Setting a warning threshold for the industrial energy storage energy efficiency prediction data according to the comprehensive environmental abnormality warning data to obtain an energy efficiency prediction warning threshold; autonomously regulating the industrial energy storage energy efficiency prediction data using the energy efficiency prediction warning threshold, thereby generating an industrial energy storage management and regulation strategy to execute industrial energy storage system management operations.

[0051] The present invention integrates the internal environment abnormality warning data and the external environment abnormality warning data to generate comprehensive environment abnormality warning data. This helps to comprehensively monitor the environmental abnormalities of the energy storage system, timely discover and warn potential environmental problems, and improve the system's warning capability and response speed. Based on the normal environment monitoring data, the energy storage efficiency data of the internal energy storage of the industrial energy storage is predicted for energy efficiency, and the industrial energy storage energy efficiency prediction data is generated. This can predict the energy efficiency performance of the system in the future, provide data support for the operation of the system, and help to formulate optimization strategies in advance and improve the operation efficiency of the system. According to the comprehensive environment abnormality warning data, the warning threshold of the industrial energy storage energy efficiency prediction data is set to obtain the energy efficiency prediction warning threshold. These thresholds are used to autonomously regulate the energy efficiency prediction data, thereby generating an industrial energy storage management control strategy. This can automatically adjust the system operating parameters under abnormal environmental conditions, ensure the stable operation of the system under various environmental conditions, reduce energy efficiency losses, and improve the reliability and stability of the system. By integrating the internal and external environmental warning data, step S4 can improve the system's warning and response capabilities, ensure that under abnormal environmental conditions, the system can respond quickly, take corresponding control measures, and avoid losses and risks. The generated industrial energy storage management and control strategy provides scientific guidance and support for the management and operation of the system, which can optimize the management of the energy storage system and improve the efficiency and safety of the system operation. The application of autonomous control strategy improves the intelligence level of the energy storage system, enabling the system to automatically adjust the operating parameters according to environmental changes to ensure that the system is always in the best state. Through energy efficiency prediction and control, the energy storage efficiency of the energy storage system under various environmental conditions is ensured, energy loss is reduced, and the economic and environmental benefits of the system are improved. Energy efficiency prediction data and control strategies provide system managers with reliable data support and decision-making basis, helping them to formulate more scientific and reasonable management strategies and improve the overall management level of the system.

[0052] Preferably, step S42 includes the following steps:

[0053] Step S421: extracting energy efficiency impact features from the internal energy storage efficiency data of the industrial energy storage based on the normal environment monitoring data to obtain energy efficiency impact feature data;

[0054] Step S422: Divide the energy efficiency impact feature data into data sets to obtain a model training set and a model test set; perform model training on the model training set using a linear regression algorithm to generate an industrial energy storage energy efficiency training model; perform model optimization iteration on the industrial energy storage energy efficiency training model using the model test set to generate an industrial energy storage energy efficiency prediction model;

[0055] Step S423: Import the internal energy storage efficiency data of the industrial energy storage into the industrial energy storage energy efficiency prediction model to perform energy efficiency prediction and generate industrial energy storage energy efficiency prediction data.

[0056] The present invention extracts energy efficiency impact features from the internal energy storage efficiency data of industrial energy storage based on normal environmental monitoring data to obtain energy efficiency impact feature data. This can identify and quantify the impact of various environmental factors on the energy efficiency of the energy storage system, and provide basic data for subsequent model training and prediction. The energy efficiency impact feature data is divided into a data set to obtain a model training set and a model test set; the model training set is trained using a linear regression algorithm to generate an industrial energy storage energy efficiency training model. The industrial energy storage energy efficiency training model is optimized and iterated through the model test set to generate an industrial energy storage energy efficiency prediction model. This ensures the accuracy and reliability of the model and can accurately predict the energy efficiency performance of the energy storage system under different environmental conditions. The internal energy storage efficiency data of the industrial energy storage is imported into the industrial energy storage energy efficiency prediction model for energy efficiency prediction, and the industrial energy storage energy efficiency prediction data is generated. This provides estimated data for the operation of the energy storage system, can identify potential problems in advance, and formulate corresponding optimization strategies. Through energy efficiency impact feature extraction and model training optimization, step S42 can improve the accuracy of energy efficiency prediction, ensure that the prediction results can reflect the actual situation, and guide system operation. The application of energy efficiency prediction models enables the energy storage system to adjust operating parameters according to the prediction results, enhance the system's adaptability to environmental changes, and improve the stability and efficiency of the system's operation. Energy efficiency prediction data provides reliable data support for system management, helping managers optimize resource allocation, reduce energy waste, and improve the economic benefits of the system. Through energy efficiency prediction, the system can identify potential energy efficiency problems in advance, take corresponding preventive measures, reduce the occurrence of failures, and improve the safety and reliability of the system. The application of prediction models has improved the intelligence level of the energy storage system, enabling the system to autonomously analyze and respond to environmental changes and maintain the best operating state. Energy efficiency prediction data provides system managers with a scientific basis for decision-making, helping them to formulate more reasonable management strategies and improve the overall management level of the system.

[0057] In this specification, an industrial energy storage system management system based on multi-source data is provided, which is used to execute the above-mentioned industrial energy storage system management method based on multi-source data. The industrial energy storage system management system based on multi-source data includes:

[0058] The environmental classification module is used to obtain comprehensive multi-source data of industrial energy storage; perform data preprocessing on the comprehensive multi-source data of industrial energy storage to generate standard comprehensive multi-source data of industrial energy storage; perform environmental data classification on the standard comprehensive multi-source data of industrial energy storage to generate internal environmental data of industrial energy storage and external environmental data of industrial energy storage;

[0059] The electric energy storage efficiency analysis module is used to divide the internal environmental data of industrial energy storage into equipment operation states, obtain equipment normal operation state data and equipment abnormal operation state data; perform the first warning on the abnormal operation state data of the equipment, and generate internal environment abnormal warning data; perform electric energy storage unit network integration on the normal operation state data of the equipment, and generate an electric energy storage unit integrated network; perform energy storage efficiency analysis on the electric energy storage unit integrated network, and generate internal energy storage efficiency data of industrial energy storage;

[0060] The abnormal environment monitoring module is used to extract environmental characteristics of the external environment data of the industrial energy storage to obtain the external environment characteristic data of the industrial energy storage; perform abnormal environment monitoring on the industrial energy storage system according to the external environment characteristic data of the industrial energy storage through the electric energy storage unit integrated network, generate normal environment monitoring data and abnormal environment monitoring data, and perform a second warning on the abnormal environment monitoring data to generate external environment abnormal warning data;

[0061] The energy efficiency management module is used to predict the energy efficiency of the internal energy storage efficiency data of industrial energy storage based on the normal environment monitoring data, and generate industrial energy storage energy efficiency prediction data; the industrial energy storage energy efficiency prediction data is autonomously monitored and regulated through the internal environment abnormal warning data and the external environment abnormal warning data, thereby generating an industrial energy storage management and control strategy to execute the industrial energy storage system management operations.

[0062] The beneficial effect of the present invention is that standardized data is generated by acquiring and preprocessing multi-source data of industrial energy storage, providing a reliable basis for subsequent analysis and processing. Classifying the standardized data and separating the internal environment data and external environment data of industrial energy storage helps to better understand the operation of the system and the impact of the external environment. The internal environment data is divided into equipment states to distinguish between normal and abnormal operating states of the equipment. By issuing early warnings for abnormal state data, potential problems and faults can be discovered in a timely manner. The data of normal operating states is integrated into the electric energy storage unit network and the energy storage efficiency is analyzed to help evaluate the energy storage performance of the industrial energy storage system and provide a basis for subsequent energy efficiency prediction. The external environment characteristic data of the industrial energy storage system is extracted, and abnormal environment monitoring is performed in combination with the electric energy storage unit network to promptly discover the adverse effects of the external environment on the operation of the system. By analyzing the normal environment monitoring data and the abnormal environment monitoring data, the energy efficiency of industrial energy storage is predicted, and autonomous regulation is carried out according to the early warning data to formulate management strategies to ensure the efficient operation of the system. At the same time, the industrial energy storage system can better monitor and manage its operating status, timely discover and handle abnormal situations, improve energy storage efficiency, and achieve efficient energy management through autonomous regulation, thereby achieving the goals of energy conservation and emission reduction, cost reduction and system reliability improvement. Therefore, the present invention improves the comprehensiveness and accuracy of industrial energy storage system management through systematic data preprocessing, comprehensive equipment and environment monitoring, intelligent energy efficiency prediction and dual early warning mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic diagram of a process flow of a method for managing an industrial energy storage system based on multi-source data;

[0064] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0065] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0066] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0067] 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

[0068] 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.

[0069] 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.

[0070] 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.

[0071] To achieve this, please refer to Figures 1 to 4 , a method for managing an industrial energy storage system based on multi-source data, the method comprising the following steps:

[0072] Step S1: Acquire comprehensive multi-source data of industrial energy storage; perform data preprocessing on the comprehensive multi-source data of industrial energy storage to generate standard comprehensive multi-source data of industrial energy storage; perform environmental data classification on the standard comprehensive multi-source data of industrial energy storage to generate internal environmental data of industrial energy storage and external environmental data of industrial energy storage;

[0073] Step S2: divide the internal environment data of industrial energy storage into equipment operation states, and obtain equipment normal operation state data and equipment abnormal operation state data; perform a first warning on the equipment abnormal operation state data, and generate internal environment abnormal warning data; perform electric energy storage unit network integration on the equipment normal operation state data, and generate an electric energy storage unit integrated network; perform energy storage efficiency analysis on the electric energy storage unit integrated network, and generate internal energy storage efficiency data of industrial energy storage;

[0074] Step S3: extracting environmental features from the external environmental data of the industrial energy storage to obtain external environmental feature data of the industrial energy storage; performing abnormal environmental monitoring on the industrial energy storage system according to the external environmental feature data of the industrial energy storage through the electric energy storage unit integrated network to generate normal environmental monitoring data and abnormal environmental monitoring data, and performing a second warning on the abnormal environmental monitoring data to generate external environmental abnormal warning data;

[0075] Step S4: Based on the normal environment monitoring data, the internal energy storage efficiency data of the industrial energy storage is predicted to generate the industrial energy storage energy efficiency prediction data; the industrial energy storage energy efficiency prediction data is autonomously warned and regulated by the internal environment abnormal warning data and the external environment abnormal warning data, thereby generating the industrial energy storage management and control strategy to execute the industrial energy storage system management operation.

[0076] The present invention improves the consistency and availability of data by acquiring and preprocessing comprehensive multi-source data, and classifying it into internal environment data and external environment data after standardization, thereby providing a solid foundation for accurate analysis and decision-making. The internal environment data is divided into equipment status, which can effectively distinguish the normal and abnormal operation status of the equipment, and generate internal environment abnormality warning data, which enhances the real-time monitoring capability of the equipment operation status, timely discovers potential faults, and reduces the risk of equipment downtime. By performing network integration of electric energy storage units and energy storage efficiency analysis on the normal operation status data of the equipment, internal energy storage efficiency data is generated, the integration and management of electric energy storage units are optimized, and the overall efficiency and performance of the energy storage system are improved. The external environment data is feature extracted to generate industrial energy storage external environment feature data, so that the system can comprehensively monitor and evaluate the impact of the external environment on the energy storage system, and ensure the stable operation of the system under different environmental conditions. The normal and abnormal environment monitoring data generated by abnormal environment monitoring, as well as the second warning of abnormal environment data, can issue an alarm in time when the environment changes, reducing the negative impact of the external environment on the energy storage system. Based on the energy efficiency prediction of normal environmental monitoring data, and the autonomous warning control combined with internal and external abnormal warning data, an industrial energy storage management and control strategy is generated, which realizes the dynamic and intelligent management of the energy storage system and improves the accuracy of energy efficiency prediction and the flexibility of control. The management and control strategy generated by the above process can accurately and specifically manage the energy storage system, optimize resource allocation and operation, reduce operating costs, extend the service life of the system, and improve the overall reliability and economic benefits of the energy storage system. Therefore, the present invention improves the comprehensiveness and accuracy of industrial energy storage system management through systematic data preprocessing, comprehensive equipment and environmental monitoring, intelligent energy efficiency prediction and dual warning mechanism.

[0077] In the embodiment of the present invention, reference Figure 1The above is a schematic diagram of the steps of a method for managing an industrial energy storage system based on multi-source data according to the present invention. In this example, the method for managing an industrial energy storage system based on multi-source data includes the following steps:

[0078] Step S1: Acquire comprehensive multi-source data of industrial energy storage; perform data preprocessing on the comprehensive multi-source data of industrial energy storage to generate standard comprehensive multi-source data of industrial energy storage; perform environmental data classification on the standard comprehensive multi-source data of industrial energy storage to generate internal environmental data of industrial energy storage and external environmental data of industrial energy storage;

[0079] In an embodiment of the present invention, data of an industrial energy storage system is collected from different data sources, including but not limited to sensor data, equipment logs, environmental monitoring data, operation records, etc., including equipment operating status data, battery performance data, ambient temperature and humidity data, load data, energy flow data, etc. Process missing values, outliers and noise in the data. For example, interpolation is used to fill missing data, and filters are applied to reduce noise. Data from different sources are converted to a unified format and scale. For example, the sensor data unit is normalized, temperature data is converted to degrees Celsius, and voltage data is converted to volts. Data from different sensors and systems are integrated into a unified data set. Data fusion techniques such as weighted average or data merging algorithms are used to ensure data consistency and integrity. The processed data is stored in a database to ensure that the data is structured and queryable. A relational database or data warehouse system is used for storage. Ensure that the data is saved in a standardized format, such as CSV, JSON or a database table, for subsequent analysis and processing. Environmental data classification is performed on the standard industrial energy storage integrated multi-source data, and the internal environmental data includes operating status data inside the energy storage device, such as battery voltage, current, temperature, charge and discharge status, etc. External environmental data includes environmental impact data outside the energy storage system, such as external temperature, humidity, air pressure, environmental pollution level, etc. Use data classification technology to classify standardized data. Machine learning algorithms, such as K-means clustering and decision tree classifiers, can be used to automate the classification process. During the classification process, labels are added to each piece of data to mark the internal or external environment category to which it belongs, ensuring the accuracy and effectiveness of the classification results.

[0080] Step S2: divide the internal environment data of industrial energy storage into equipment operation states, and obtain equipment normal operation state data and equipment abnormal operation state data; perform a first warning on the equipment abnormal operation state data, and generate internal environment abnormal warning data; perform electric energy storage unit network integration on the equipment normal operation state data, and generate an electric energy storage unit integrated network; perform energy storage efficiency analysis on the electric energy storage unit integrated network, and generate internal energy storage efficiency data of industrial energy storage;

[0081] In an embodiment of the present invention, internal environmental data, such as battery voltage, current, temperature, charge and discharge status, etc., are collected from sensors and monitoring systems of the energy storage system. Normal operating status data is the operating data of the device under normal operating conditions. By setting normal operating thresholds (such as voltage, current, and temperature range), statistical analysis or machine learning algorithms are used to identify data that meets these thresholds. Abnormal operating status data is the operating data of the device under abnormal conditions. Abnormal data can be identified by readings, fault reports, or historical data that exceed normal thresholds. Anomaly detection algorithms (such as isolation forests and Z-Score analysis) are used to classify data. Based on historical data and the recommendations of equipment manufacturers, abnormal warning rules are defined. For example, set the voltage to be lower than the minimum threshold or the temperature to be higher than the maximum threshold to trigger an alarm. Analyze the equipment operating data in real time and compare it with the alarm rules. Use a real-time data stream processing platform (such as Apache Kafka, Apache Flink) for data stream processing. When the data triggers an abnormal condition, internal environmental abnormal warning data is generated, including information such as warning time, abnormal type, severity, etc., and the relevant operators are notified through system alarms, emails, or SMS. The normal operating status data of each electric energy storage unit is integrated into a unified network. Use network integration technologies, such as data fusion or integrated computing architecture, to aggregate the data of each unit. Establish an integrated network model of energy storage units, and use graph theory or network analysis methods to model the relationship between energy storage units. Analyze the data in the integrated network of energy storage units and calculate the energy storage efficiency of each energy storage unit. Analyze the battery's charging efficiency, discharge efficiency, energy loss, etc., generate energy storage efficiency data, such as energy storage and release per unit time, overall system efficiency, etc., evaluate the overall performance of the energy storage system based on the analysis results, and identify performance bottlenecks and optimization points.

[0082] Step S3: extracting environmental features from the external environmental data of the industrial energy storage to obtain external environmental feature data of the industrial energy storage; performing abnormal environmental monitoring on the industrial energy storage system according to the external environmental feature data of the industrial energy storage through the electric energy storage unit integrated network to generate normal environmental monitoring data and abnormal environmental monitoring data, and performing a second warning on the abnormal environmental monitoring data to generate external environmental abnormal warning data;

[0083] In an embodiment of the present invention, external environmental data including temperature, humidity, air pressure, wind speed, light intensity, etc. are collected from environmental monitoring sensors. The external environmental data is cleaned and missing values ​​and outliers are processed. The data is converted into a unified format and scale. The environmental features that have the greatest impact on the operation of the energy storage system are extracted through statistical analysis or machine learning methods (such as principal component analysis PCA, feature selection algorithm). For example, key features such as temperature change rate and humidity fluctuation are extracted to generate additional features such as moving average, trend analysis, and periodic features of environmental data to enhance the prediction ability of the model. The extracted external environmental feature data is input into the integrated network of the electric energy storage unit. The network can be an artificial neural network (ANN), a convolutional neural network (CNN), or other suitable models. The model is trained using historical data to enable it to identify the impact of different environmental features on the energy storage system. A supervised learning method is used during the training process to train with labeled normal and abnormal environmental data. The real-time external environmental feature data is input into the trained model for real-time monitoring. The model outputs normal environmental monitoring data and abnormal environmental monitoring data. Normal data indicates that the environment is within the expected range, while abnormal data indicates that the environmental conditions are beyond the normal range. Set thresholds for external environmental anomalies. For example, the temperature exceeds the set range, the humidity is too high or too low, etc., as conditions for triggering warnings. Analyze abnormal environmental monitoring data to identify whether warning rules are triggered. When external environmental data triggers abnormal warning rules, generate external environmental abnormal warning data, including warning time, abnormal type, severity, and other information. Notify relevant operators through system alarms, emails, or text messages to ensure timely response and handling of external environmental anomalies.

[0084] Step S4: Based on the normal environment monitoring data, the internal energy storage efficiency data of the industrial energy storage is predicted to generate the industrial energy storage energy efficiency prediction data; the industrial energy storage energy efficiency prediction data is autonomously warned and regulated by the internal environment abnormal warning data and the external environment abnormal warning data, thereby generating the industrial energy storage management and control strategy to execute the industrial energy storage system management operation.

[0085] In an embodiment of the present invention, monitoring data under normal environmental conditions are obtained, including external environmental feature data and normal environmental monitoring data in the integrated network of electric energy storage units. The internal energy storage efficiency data generated in step S2 is used as the target variable for prediction. A suitable prediction model is selected, such as linear regression, support vector regression (SVR), random forest regression, neural network, etc. Feature engineering is performed on normal environmental monitoring data to generate feature inputs required for the prediction model. Including preprocessing operations such as standardization and normalization of environmental data. The prediction model is trained using historical normal environmental data and corresponding energy storage efficiency data. Ensure that the model can accurately predict energy efficiency according to normal environmental conditions. The performance of the model is verified by cross-validation or retention method, and the model parameters are adjusted to improve the prediction accuracy. The real-time normal environmental monitoring data is input into the trained prediction model to generate energy efficiency prediction data of the industrial energy storage system, and generate prediction results including energy efficiency prediction values, confidence intervals, etc. The internal environment abnormality warning data generated in step S2 and the external environment abnormality warning data generated in step S3 are obtained, and these warning information are combined with the energy efficiency prediction data to form comprehensive warning and control information. The energy efficiency prediction results are adjusted according to the warning data. For example, when an abnormality occurs in the internal or external environment, the energy efficiency forecast value is adjusted to reflect the energy efficiency loss. The control rules are applied to the energy efficiency forecast data to generate an adjusted energy efficiency forecast value. Specific management and control strategies are generated based on the adjusted energy efficiency forecast data. Strategies include adjusting the operating mode of the energy storage system, optimizing energy distribution, setting additional safety thresholds, etc. The generated management and control strategies are applied to industrial energy storage systems. The execution system involves adjusting the operating parameters of the energy storage equipment, modifying the charging and discharging plans, implementing system optimization measures, etc., monitoring the execution effect of the control strategy in real time, and collecting feedback data. The control strategy is further adjusted and optimized based on the feedback data.

[0086] Preferably, step S1 comprises the following steps:

[0087] Step S11: Acquire comprehensive multi-source data of industrial energy storage;

[0088] Step S12: performing data cleaning on the comprehensive multi-source data of industrial energy storage to generate comprehensive multi-source cleaned data of industrial energy storage;

[0089] Step S13: Fill missing values ​​in the industrial energy storage comprehensive multi-source cleaned data to generate industrial energy storage comprehensive multi-source filled data;

[0090] Step S14: Standardize the industrial energy storage comprehensive multi-source data by using the Z-score method to generate standard industrial energy storage comprehensive multi-source data; classify the environmental data of the standard industrial energy storage comprehensive multi-source data to generate industrial energy storage internal environmental data and industrial energy storage external environmental data.

[0091] In an embodiment of the present invention, industrial energy storage related data including but not limited to equipment operation data, power data, temperature and humidity data, air pressure data, geographic location information, etc. are obtained from different sensors, equipment logs, monitoring systems, and external environment monitoring systems. Low-pass filtering, mean filtering, and other methods are used to remove noise from the data. The 3σ principle or anomaly detection algorithm based on machine learning is used to identify and process outliers. Duplicate data is removed by hashing or duplicate detection algorithms to ensure data uniqueness. For continuous data, the mean is used to fill missing values. Linear interpolation, spline interpolation, and other methods are used to fill missing values ​​for time series data. For important missing data, multiple interpolation algorithms are used to fill in to ensure the accuracy and reliability of the data. The mean (μ) and standard deviation (σ) of each feature are calculated. The Z-score formula Z=X−μ / σ is used to standardize the data so that the mean of the standardized data is 0 and the standard deviation is 1. According to the data source and characteristics, classification standards are formulated, and the standardized data is divided into industrial energy storage internal environment data and industrial energy storage external environment data according to the classification standards. The classification results are verified to ensure the accuracy of the classification. If there are errors, they are corrected.

[0092] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0093] Step S21: filtering the internal equipment operation data of the industrial energy storage internal environment data to obtain the internal equipment operation data of the industrial energy storage;

[0094] Step S22: dividing the internal equipment operation data of the industrial energy storage into equipment operation states, obtaining equipment normal operation state data and equipment abnormal operation state data; performing a first warning on the equipment abnormal operation state data, and generating internal environment abnormality warning data;

[0095] Step S23: using the electric energy sensor to collect equipment operation data according to the normal operation status data of the equipment, to obtain the electric energy equipment operation data;

[0096] Step S24: Performing electric energy storage unit network integration on the electric energy equipment operation data to generate an electric energy storage unit integrated network; performing energy storage efficiency analysis on the electric energy storage unit integrated network to generate internal energy storage efficiency data for industrial energy storage.

[0097] In an embodiment of the present invention, the screening criteria are defined according to the equipment operating parameters (such as temperature, pressure, current, power, etc.) and the operating status (such as in operation, standby, maintenance, etc.). The internal environmental data of the industrial energy storage is screened using a data filtering tool or a script (such as SQL query, Python data processing) to extract the internal equipment operating data that meets the standards. The screened data is stored in a database or data warehouse to ensure the accessibility and integrity of the data. The standards for normal operating status and abnormal operating status are defined according to the thresholds of the equipment operating parameters (such as the upper temperature limit, the lower power limit, etc.). The equipment operating data is classified by a classification algorithm (such as logistic regression, decision tree, random forest, etc.), and the data is divided into normal operating status data of the equipment and abnormal operating status data of the equipment. The abnormal operating status data of the equipment is analyzed by an early warning algorithm (such as statistical analysis, machine learning model) to identify potential abnormal situations. Internal environmental abnormality early warning data is generated according to the early warning analysis results, and the abnormal occurrence time, equipment ID, abnormality type and other information are recorded. Appropriate power sensors (such as current sensors, voltage sensors, power meters, etc.) are selected according to the equipment type and collection requirements. The sensors are installed on the equipment and calibrated to ensure the accuracy of the collected data. Set up a data acquisition system and define the data acquisition frequency and data storage format. Collect the operating data of the power equipment (such as voltage, current, power, energy, etc.) in real time and store the data in the data management system. Design the network topology of the electric energy storage unit according to the connection relationship and data flow of the power equipment. Integrate the collected power equipment operation data into the network, build an integrated network of electric energy storage units, and record the energy flow and interaction between each unit. Use data analysis methods (such as energy efficiency calculation formulas, optimization algorithms, etc.) to analyze the data in the integrated network of electric energy storage units and calculate the energy storage efficiency. Generate internal energy storage efficiency data for industrial energy storage, including information such as the energy storage efficiency of each energy storage unit and the overall energy storage efficiency.

[0098] Preferably, dividing the equipment operation status of the internal equipment operation data of the industrial energy storage device includes:

[0099] Monitor the real-time operation data of the internal equipment of the industrial energy storage system to obtain the real-time operation data of the internal equipment; read the historical operation data of the internal equipment of the industrial energy storage system to obtain the historical operation data of the internal equipment;

[0100] Conduct operation fluctuation analysis on real-time operation data of internal equipment to generate operation fluctuation data of internal equipment; conduct maintenance analysis on historical operation data of internal equipment to generate maintenance data of internal equipment;

[0101] Perform frequency calculation on internal equipment operation fluctuation data and internal equipment maintenance data to obtain internal equipment fluctuation frequency data and internal equipment maintenance frequency data; perform fast spectrum conversion on internal equipment fluctuation frequency data and internal equipment maintenance frequency data to generate internal equipment fluctuation spectrum curve and internal equipment historical maintenance spectrum curve;

[0102] Perform curve fitting on the internal equipment fluctuation spectrum curve and the internal equipment historical maintenance spectrum curve to generate an internal equipment fault fitting curve; map the internal equipment operation data of the industrial energy storage to the internal equipment fault fitting curve to perform deviation calculation to obtain equipment operation deviation data;

[0103] The equipment operation deviation data is compared with the preset deviation threshold. When the equipment operation deviation data is greater than the preset deviation threshold, the corresponding industrial energy storage internal equipment operation data is marked as equipment abnormal operation status data; when the equipment operation deviation data is less than or equal to the preset deviation threshold, the corresponding industrial energy storage internal equipment operation data is marked as equipment normal operation status data.

[0104] In an embodiment of the present invention, a suitable sensor is selected according to the parameters to be monitored (such as temperature, pressure, current, etc.). A suitable sensor is selected according to the parameters to be monitored (such as temperature, pressure, current, etc.). A data acquisition system (such as a data recorder, real-time monitoring software) is set up, and the data acquisition frequency and acquisition method are configured. The collected real-time equipment operation data is stored in a database for subsequent analysis. The historical operation data of the equipment is read from a historical data storage system (such as a data warehouse, a historical database), and the read historical data is formatted into a form suitable for analysis (such as CSV, Excel format). Analysis indicators (such as standard deviation, variance, amplitude, etc.) are determined to evaluate the volatility of equipment operation. Data analysis tools (such as Python's Pandas library, R language) are used to calculate the volatility of the real-time operation data of the internal equipment, and internal equipment operation fluctuation data is generated. The maintenance records of the equipment are collected, including information such as maintenance time, maintenance content, and maintenance results. The historical maintenance data is analyzed to identify common failure modes and maintenance frequencies, and internal equipment maintenance data is generated. The frequency of fluctuations in the equipment operation data is counted to generate internal equipment fluctuation frequency data. The frequency of occurrence of maintenance records of the equipment is counted to generate internal equipment maintenance frequency data. Apply fast Fourier transform (FFT) to the internal equipment fluctuation frequency data and maintenance frequency data to obtain the spectrum curve. Visualize the FFT results to generate the internal equipment fluctuation spectrum curve and the internal equipment historical maintenance spectrum curve. Select a suitable curve fitting algorithm (such as polynomial fitting, exponential fitting) to fit the spectrum curve. Perform curve fitting on the internal equipment fluctuation spectrum curve and the internal equipment historical maintenance spectrum curve to generate the internal equipment fault fitting curve. Map the equipment operation data to the internal equipment fault fitting curve, calculate the deviation degree of equipment operation, and generate equipment operation deviation data based on the deviation calculation result. Define a preset deviation threshold, set a reasonable threshold based on historical data and equipment specifications, and compare the equipment operation deviation data with the preset deviation threshold. When the equipment operation deviation data is greater than the preset deviation threshold, the corresponding equipment operation data is marked as equipment abnormal operation status data; when the equipment operation deviation data is less than or equal to the preset deviation threshold, the corresponding equipment operation data is marked as equipment normal operation status data.

[0105] Preferably, step S24 includes the following steps:

[0106] Step S241: confirming the equipment base station address of the electric energy equipment operation data to obtain the equipment base station address data;

[0107] Step S242: allocating operation data of the electric energy equipment according to the equipment base station address data to generate electric energy storage unit data; constructing a network topology structure for the electric energy storage unit data to obtain network topology structure data of the electric energy storage unit;

[0108] Step S243: extracting power data from the electric energy storage unit data to obtain power characteristic data of the electric energy storage unit; performing charge and discharge energy analysis on the power characteristic data of the electric energy storage unit to obtain charging power data and discharging power data; and constructing edge connections based on the charging power data and the discharging power data to obtain network edge connection data;

[0109] Step S244: Integrate the electric energy storage unit network through network edge connection data and electric energy storage unit network topology data to generate an electric energy storage unit integrated network; perform energy storage efficiency analysis on the electric energy storage unit integrated network to generate internal energy storage efficiency data for industrial energy storage.

[0110] In an embodiment of the present invention, the base station address data of the device is obtained from the sensor and communication module of the electric energy device. The device base station address data is stored in a database as the basis for subsequent data allocation. The acquired device base station address data is verified to ensure the accuracy and completeness of the address data. If the address data is found to be incorrect, necessary corrections and supplements are made. According to the device base station address data, the operation data of the electric energy device is classified and allocated to each electric energy storage unit. The electric energy storage unit data is generated by the allocation result, and the data of each electric energy storage unit includes information such as the operation status and power of the device. The electric energy storage unit data is generated by the allocation result, and the data of each electric energy storage unit includes information such as the operation status and power of the device. The electric energy storage unit data is integrated into the network topology structure to generate the electric energy storage unit network topology structure data. The power characteristic data, including the charging and discharging amount of the battery, etc., is extracted from the electric energy storage unit data, and the extracted power data is organized into a format that is easy to analyze. The charging power data is analyzed to evaluate the charging performance of each electric energy storage unit, and the discharging power data is analyzed to evaluate the discharge performance of each electric energy storage unit. Based on the charging power data and discharging power data, use graph algorithms (such as the shortest path algorithm) to construct the edge connection data of the energy storage unit. Create network edge connection data to represent the energy transmission path between energy storage units. Use network edge connection data and energy storage unit network topology data to integrate each energy storage unit into a complete energy storage unit integrated network, and use network analysis tools (such as GraphX, NetworkX) for network integration and visualization. Perform energy storage efficiency analysis on the energy storage unit integrated network, including calculating the battery's charging and discharging efficiency, energy loss, etc. Based on the efficiency analysis results, generate internal energy storage efficiency data for industrial energy storage to evaluate the energy storage performance of the overall system.

[0111] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0112] Step S31: extracting environmental features from the external environmental data of the industrial energy storage to obtain external environmental feature data of the industrial energy storage, wherein the external environmental feature data of the industrial energy storage includes environmental temperature data, environmental humidity data and environmental air pressure data;

[0113] Step S32: Associating the geographical data of industrial energy storage equipment with the industrial energy storage system through the electric energy storage unit integrated network to generate geographical environment data of the industrial energy storage equipment;

[0114] Step S33: Performing a multi-factor external environmental impact analysis on the geographical environment data of the industrial energy storage equipment based on the ambient temperature data, the ambient humidity data, and the ambient air pressure data to generate an external environmental impact factor for the industrial energy storage;

[0115] Step S34: Perform abnormal environment monitoring on the external environment data of the industrial energy storage according to the external environment influencing factors of the industrial energy storage, generate normal environment monitoring data and abnormal environment monitoring data, perform a second warning on the abnormal environment monitoring data, and generate external environment abnormal warning data.

[0116] In the embodiment of the present invention, the environmental temperature sensor is used to obtain real-time temperature data from the external environment of the industrial energy storage system, the humidity sensor is used to obtain environmental humidity data, and the pressure sensor is used to measure environmental pressure data. The environmental data obtained from each sensor is aggregated to a unified data processing platform, and the data is converted into a unified format for subsequent processing and analysis. The processed environmental temperature data, humidity data and pressure data are combined to generate industrial energy storage external environmental characteristic data. The geographical location information of the device is obtained from the device's geographic information system (GIS). The geographical location information of the device is associated with the environmental characteristic data using the electric energy storage unit integrated network, and the integrated data generates the geographical environment data of the industrial energy storage device, which includes the geographical location and related environmental characteristic information of each device. The environmental temperature data is analyzed, the extreme low temperature and high temperature data are extracted, and the impact on the energy storage efficiency of the device is evaluated according to the extreme temperature data, and the environmental temperature impact factor is generated. The dryness of the device environment is calculated according to the environmental humidity data, and the stability impact analysis of the energy storage efficiency of the device is performed using the environmental dryness data, and the environmental humidity impact factor is generated. The device geographical environment data is converted to an elevation, the altitude data of the device is obtained, the relationship between the environmental pressure data and the altitude data of the device is analyzed, and the environmental pressure impact factor is generated. Integrate the environmental temperature influencing factors, humidity influencing factors and air pressure influencing factors to generate the external environmental influencing factors of industrial energy storage. Based on the external environmental influencing factors of industrial energy storage, monitor the environmental characteristic data, generate normal environmental monitoring data, identify and extract abnormal environmental data, and generate abnormal environmental monitoring data. Set early warning rules based on abnormal environmental monitoring data, generate external environmental abnormal early warning data, conduct detailed analysis of abnormal environments, update the early warning status in a timely manner, and implement corresponding environmental adjustment measures.

[0117] Preferably, step S33 includes the following steps:

[0118] Step S331: extracting the extreme temperature of the geographical environment of the industrial energy storage equipment according to the ambient temperature data, generating extreme low temperature data and extreme high temperature data; performing performance impact analysis on the internal energy storage efficiency data of the industrial energy storage through the extreme low temperature data and the extreme high temperature data, generating an ambient temperature impact factor;

[0119] Step S332: Calculate the environmental dryness of the geographical environment data of the industrial energy storage equipment according to the environmental humidity data to obtain the equipment environmental dryness data; use the environmental equipment dryness data to perform stability impact analysis on the internal energy storage efficiency data of the industrial energy storage to generate an environmental humidity impact factor;

[0120] Step S333: Performing geographic elevation conversion on the geographic environment data of the industrial energy storage equipment to generate elevation data of the industrial energy storage equipment; performing altitude analysis on the elevation data of the industrial energy storage equipment to generate altitude data of the energy storage equipment; performing equipment structure impact analysis on the altitude data of the energy storage equipment through the ambient air pressure data to generate an ambient air pressure impact factor;

[0121] Step S334: Integrate the environmental temperature influence factor, the environmental humidity influence factor and the environmental pressure influence factor to generate the external environment influence factor of industrial energy storage.

[0122] In an embodiment of the present invention, extreme low temperature data and extreme high temperature data are extracted from the ambient temperature data. Using a statistical analysis tool, the lowest and highest values ​​in the ambient temperature data are identified, and thresholds are set to define what temperature values ​​are considered extreme (e.g., below the 5th percentile and above the 95th percentile). The extreme low temperature data and extreme high temperature data are compared with the energy storage efficiency data inside the industrial energy storage. The impact of extreme temperature conditions on the energy storage efficiency of the energy storage system is evaluated, and the impact of extreme temperature on the energy storage efficiency is analyzed using a statistical model or a machine learning algorithm. The impact assessment result is converted into an ambient temperature impact factor to reflect the comprehensive impact of temperature on energy efficiency. The dryness of the equipment environment is calculated based on the ambient humidity data, and the dryness is calculated using the humidity data. For example, the relative humidity of the equipment is calculated by standardizing the humidity data, and the dryness is divided into multiple categories (e.g., high dryness, normal humidity, and low dryness) for easy analysis. The ambient dryness data is compared with the energy storage efficiency data inside the industrial energy storage, and the impact of the ambient dryness on the stability of the energy storage system is evaluated. The impact of humidity changes on the stability of energy storage is analyzed using a statistical model or a machine learning algorithm. The stability analysis result is converted into an ambient humidity impact factor to reflect the impact of humidity on energy efficiency stability. Perform elevation conversion on the geographic environment data of industrial energy storage equipment, use GPS data or topographic map data to determine the geographic elevation of the equipment, convert the elevation data into altitude data, analyze the altitude data of the equipment, calculate the actual altitude of the equipment, analyze the altitude data of the equipment in combination with the ambient air pressure data, evaluate the impact of air pressure changes on the structure of the energy storage equipment, use statistical models or air pressure-altitude relationship models to analyze the impact of air pressure on the equipment, and convert the impact assessment results into ambient air pressure impact factors to reflect the impact of air pressure on the equipment. Comprehensively integrate the ambient temperature impact factor, ambient humidity impact factor, and ambient air pressure impact factor, use data fusion technology to perform weighted average or other comprehensive analysis methods on each impact factor, and generate the external environmental impact factor of industrial energy storage from the integrated factors to evaluate the overall impact of the external environment on the energy storage system.

[0123] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0124] Step S41: Integrate the internal environment abnormality warning data and the external environment abnormality warning data to generate comprehensive environment abnormality warning data;

[0125] Step S42: performing energy efficiency prediction on the internal energy storage efficiency data of the industrial energy storage based on the normal environment monitoring data to generate industrial energy storage energy efficiency prediction data;

[0126] Step S43: Setting a warning threshold for the industrial energy storage energy efficiency prediction data according to the comprehensive environmental abnormality warning data to obtain an energy efficiency prediction warning threshold; autonomously regulating the industrial energy storage energy efficiency prediction data using the energy efficiency prediction warning threshold, thereby generating an industrial energy storage management and regulation strategy to execute industrial energy storage system management operations.

[0127] In an embodiment of the present invention, the internal environment abnormality warning data obtained from step S22 and the external environment abnormality warning data obtained from step S34 are integrated, and the two types of data are integrated together using data fusion technology (such as weighted average, joint distribution analysis), and the integration method of the comprehensive environment abnormality warning data is determined, such as based on time series analysis or multivariate statistical analysis. Combined with the integration results of the internal and external environment abnormality warning data, comprehensive environment abnormality warning data is generated, and data verification is performed to ensure the accuracy and reliability of the comprehensive environment abnormality warning data, and the generated comprehensive environment abnormality warning data is used for subsequent energy efficiency prediction and management and control. The internal energy storage efficiency data of industrial energy storage is processed using normal environment monitoring data, and relevant features such as ambient temperature, humidity, air pressure, etc. are extracted from the normal environment monitoring data. Feature engineering methods (such as principal component analysis and feature selection) are applied to extract feature data related to energy efficiency and generate energy efficiency impact feature data. The extracted energy efficiency impact feature data is divided into a training set and a test set. Use machine learning algorithms (e.g., linear regression, support vector machine, neural network) to train the training set and generate an industrial energy storage energy efficiency prediction model. Use the test set to optimize and iterate the prediction model. Evaluate the prediction accuracy of the model and adjust the model parameters to improve the prediction performance. Input the internal energy storage efficiency data of the industrial energy storage into the optimized prediction model to generate industrial energy storage energy efficiency prediction data. Analyze the energy efficiency prediction data based on the comprehensive environmental abnormality warning data. Set the energy efficiency prediction warning threshold, for example, determine when to trigger the warning based on the historical distribution of the prediction data or the set standard threshold, and define the level of the warning (e.g., mild, moderate, severe). Use the energy efficiency prediction warning threshold to autonomously control the industrial energy storage system. Based on the warning threshold and energy efficiency prediction data, formulate corresponding control measures, such as adjusting the charging and discharging strategy of the energy storage system, optimizing the operating parameters, etc. Generate an industrial energy storage management control strategy for executing the management operations of the industrial energy storage system, including specific operation steps, adjustment plans and countermeasures to improve the energy efficiency and stability of the system.

[0128] Preferably, step S42 includes the following steps:

[0129] Step S421: extracting energy efficiency impact features from the internal energy storage efficiency data of the industrial energy storage based on the normal environment monitoring data to obtain energy efficiency impact feature data;

[0130] Step S422: Divide the energy efficiency impact feature data into data sets to obtain a model training set and a model test set; perform model training on the model training set using a linear regression algorithm to generate an industrial energy storage energy efficiency training model; perform model optimization iteration on the industrial energy storage energy efficiency training model using the model test set to generate an industrial energy storage energy efficiency prediction model;

[0131] Step S423: Import the internal energy storage efficiency data of the industrial energy storage into the industrial energy storage energy efficiency prediction model to perform energy efficiency prediction and generate industrial energy storage energy efficiency prediction data.

[0132] In an embodiment of the present invention, the normal environmental monitoring data obtained from step S31 includes environmental temperature data, environmental humidity data and environmental pressure data. The internal energy storage efficiency data of industrial energy storage obtained from step S24. Select environmental monitoring data features related to energy efficiency, such as temperature variation range, humidity level, air pressure fluctuation, etc. Statistical methods and data analysis techniques are used to extract features that affect energy efficiency. For example, the standard deviation of ambient temperature, the average value of humidity, the rate of change of air pressure, etc. can be calculated. The extracted feature data are integrated into energy efficiency impact feature data to form a data set for model training. The energy efficiency impact feature data is divided into a model training set and a model test set. The common division ratio is 80% training set and 20% test set. Ensure the consistency of the feature distribution of the training set and the test set to avoid data deviation during the training process. Select a linear regression algorithm for model training. This is because linear regression can handle the linear relationship between features and target variables. Use the training set data to train the linear regression model and fit the industrial energy storage energy efficiency prediction model. Evaluate the performance of the training model and use methods such as cross-validation to verify the stability and accuracy of the model. Use the test set to test the training model and obtain the performance of the model on unseen data. Optimize the model according to the test results, including adjusting model parameters, adding features or performing feature selection, etc. After optimization iterations, generate the final industrial energy storage efficiency prediction model, input the internal energy storage efficiency data of industrial energy storage into the industrial energy storage efficiency prediction model, and perform necessary preprocessing on the input data, such as normalization or standardization, to meet the requirements of the prediction model. Use the final prediction model to predict the energy efficiency of the input data, calculate the prediction results, and organize the prediction results into industrial energy storage efficiency prediction data for subsequent analysis and management.

[0133] In this specification, an industrial energy storage system management system based on multi-source data is provided, which is used to execute the above-mentioned industrial energy storage system management method based on multi-source data. The industrial energy storage system management system based on multi-source data includes:

[0134] The environmental classification module is used to obtain comprehensive multi-source data of industrial energy storage; perform data preprocessing on the comprehensive multi-source data of industrial energy storage to generate standard comprehensive multi-source data of industrial energy storage; perform environmental data classification on the standard comprehensive multi-source data of industrial energy storage to generate internal environmental data of industrial energy storage and external environmental data of industrial energy storage;

[0135] The electric energy storage efficiency analysis module is used to divide the internal environmental data of industrial energy storage into equipment operation states, obtain equipment normal operation state data and equipment abnormal operation state data; perform the first warning on the abnormal operation state data of the equipment, and generate internal environment abnormal warning data; perform electric energy storage unit network integration on the normal operation state data of the equipment, and generate an electric energy storage unit integrated network; perform energy storage efficiency analysis on the electric energy storage unit integrated network, and generate internal energy storage efficiency data of industrial energy storage;

[0136] The abnormal environment monitoring module is used to extract environmental characteristics of the external environment data of the industrial energy storage to obtain the external environment characteristic data of the industrial energy storage; perform abnormal environment monitoring on the industrial energy storage system according to the external environment characteristic data of the industrial energy storage through the electric energy storage unit integrated network, generate normal environment monitoring data and abnormal environment monitoring data, and perform a second warning on the abnormal environment monitoring data to generate external environment abnormal warning data;

[0137] The energy efficiency management module is used to predict the energy efficiency of the internal energy storage efficiency data of industrial energy storage based on the normal environment monitoring data, and generate industrial energy storage energy efficiency prediction data; the industrial energy storage energy efficiency prediction data is autonomously monitored and regulated through the internal environment abnormal warning data and the external environment abnormal warning data, thereby generating an industrial energy storage management and control strategy to execute the industrial energy storage system management operations.

[0138] The beneficial effect of the present invention is that standardized data is generated by acquiring and preprocessing multi-source data of industrial energy storage, providing a reliable basis for subsequent analysis and processing. Classifying the standardized data and separating the internal environment data and external environment data of industrial energy storage helps to better understand the operation of the system and the impact of the external environment. The internal environment data is divided into equipment states to distinguish between normal and abnormal operating states of the equipment. By issuing early warnings for abnormal state data, potential problems and faults can be discovered in a timely manner. The data of normal operating states is integrated into the electric energy storage unit network and the energy storage efficiency is analyzed to help evaluate the energy storage performance of the industrial energy storage system and provide a basis for subsequent energy efficiency prediction. The external environment characteristic data of the industrial energy storage system is extracted, and abnormal environment monitoring is performed in combination with the electric energy storage unit network to promptly discover the adverse effects of the external environment on the operation of the system. By analyzing the normal environment monitoring data and the abnormal environment monitoring data, the energy efficiency of industrial energy storage is predicted, and autonomous regulation is carried out according to the early warning data to formulate management strategies to ensure the efficient operation of the system. At the same time, the industrial energy storage system can better monitor and manage its operating status, timely discover and handle abnormal situations, improve energy storage efficiency, and achieve efficient energy management through autonomous regulation, thereby achieving the goals of energy conservation and emission reduction, cost reduction and system reliability improvement. Therefore, the present invention improves the comprehensiveness and accuracy of industrial energy storage system management through systematic data preprocessing, comprehensive equipment and environment monitoring, intelligent energy efficiency prediction and dual early warning mechanism.

[0139] 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.

[0140] 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 managing an industrial energy storage system based on multi-source data, characterized in that: The following steps are involved: Step S1: Acquire comprehensive multi-source data of industrial energy storage; perform data preprocessing on the comprehensive multi-source data of industrial energy storage to generate standard comprehensive multi-source data of industrial energy storage; perform environmental data classification on the standard comprehensive multi-source data of industrial energy storage to generate internal environmental data of industrial energy storage and external environmental data of industrial energy storage; Step S2: dividing the internal environment data of the industrial energy storage into equipment operation states, obtaining equipment normal operation state data and equipment abnormal operation state data; performing a first warning on the equipment abnormal operation state data, and generating internal environment abnormal warning data; Performing electric energy storage unit network integration on the normal operating status data of the equipment to generate an electric energy storage unit integrated network; Performing energy storage efficiency analysis on the integrated network of electric energy storage units to generate internal energy storage efficiency data of industrial energy storage; step S2 includes the following steps: Step S21: filtering the internal equipment operation data of the industrial energy storage internal environment data to obtain the internal equipment operation data of the industrial energy storage; Step S22: dividing the internal equipment operation data of the industrial energy storage into equipment operation states, obtaining equipment normal operation state data and equipment abnormal operation state data; performing a first warning on the equipment abnormal operation state data, and generating internal environment abnormality warning data; Step S23: using the electric energy sensor to collect equipment operation data according to the normal operation status data of the equipment, to obtain the electric energy equipment operation data; Step S24: Performing electric energy storage unit network integration on the electric energy equipment operation data to generate an electric energy storage unit integrated network; performing energy storage efficiency analysis on the electric energy storage unit integrated network to generate internal energy storage efficiency data for industrial energy storage; Step S24 includes the following steps: Step S241: confirming the equipment base station address of the electric energy equipment operation data to obtain the equipment base station address data; Step S242: allocating operation data of the electric energy equipment according to the equipment base station address data to generate electric energy storage unit data; constructing a network topology structure for the electric energy storage unit data to obtain network topology structure data of the electric energy storage unit; Step S243: extracting power data from the electric energy storage unit data to obtain power characteristic data of the electric energy storage unit; performing charge and discharge energy analysis on the power characteristic data of the electric energy storage unit to obtain charging power data and discharging power data; and constructing edge connections based on the charging power data and the discharging power data to obtain network edge connection data; Step S244: integrating the electric energy storage unit network through the network edge connection data and the electric energy storage unit network topology data to generate an electric energy storage unit integrated network; performing energy storage efficiency analysis on the electric energy storage unit integrated network to generate internal energy storage efficiency data for industrial energy storage; Step S3: extracting environmental features from the external environmental data of the industrial energy storage to obtain external environmental feature data of the industrial energy storage; performing abnormal environmental monitoring on the industrial energy storage system according to the external environmental feature data of the industrial energy storage through the electric energy storage unit integrated network to generate normal environmental monitoring data and abnormal environmental monitoring data, and performing a second warning on the abnormal environmental monitoring data to generate external environmental abnormal warning data; Step S4: Based on the normal environment monitoring data, the internal energy storage efficiency data of the industrial energy storage is predicted to generate the industrial energy storage energy efficiency prediction data; the industrial energy storage energy efficiency prediction data is autonomously warned and regulated by the internal environment abnormal warning data and the external environment abnormal warning data, thereby generating the industrial energy storage management and control strategy to execute the industrial energy storage system management operation.

2. The industrial energy storage system management method based on multi-source data according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire comprehensive multi-source data of industrial energy storage; Step S12: performing data cleaning on the comprehensive multi-source data of industrial energy storage to generate comprehensive multi-source cleaned data of industrial energy storage; Step S13: Fill missing values ​​in the industrial energy storage comprehensive multi-source cleaned data to generate industrial energy storage comprehensive multi-source filled data; Step S14: Standardize the industrial energy storage comprehensive multi-source data by using the Z-score method to generate standard industrial energy storage comprehensive multi-source data; classify the environmental data of the standard industrial energy storage comprehensive multi-source data to generate industrial energy storage internal environmental data and industrial energy storage external environmental data.

3. The industrial energy storage system management method based on multi-source data according to claim 1, characterized in that: The equipment operation status classification of the internal equipment operation data of industrial energy storage includes: Monitor the real-time operation data of the internal equipment of the industrial energy storage system to obtain the real-time operation data of the internal equipment; read the historical operation data of the internal equipment of the industrial energy storage system to obtain the historical operation data of the internal equipment; Conduct operation fluctuation analysis on real-time operation data of internal equipment to generate operation fluctuation data of internal equipment; conduct maintenance analysis on historical operation data of internal equipment to generate maintenance data of internal equipment; Perform frequency calculation on internal equipment operation fluctuation data and internal equipment maintenance data to obtain internal equipment fluctuation frequency data and internal equipment maintenance frequency data; perform fast spectrum conversion on internal equipment fluctuation frequency data and internal equipment maintenance frequency data to generate internal equipment fluctuation spectrum curve and internal equipment historical maintenance spectrum curve; Perform curve fitting on the internal equipment fluctuation spectrum curve and the internal equipment historical maintenance spectrum curve to generate an internal equipment fault fitting curve; map the internal equipment operation data of the industrial energy storage to the internal equipment fault fitting curve to perform deviation calculation to obtain equipment operation deviation data; The equipment operation deviation data is compared with the preset deviation threshold. When the equipment operation deviation data is greater than the preset deviation threshold, the corresponding industrial energy storage internal equipment operation data is marked as equipment abnormal operation status data; when the equipment operation deviation data is less than or equal to the preset deviation threshold, the corresponding industrial energy storage internal equipment operation data is marked as equipment normal operation status data.

4. The industrial energy storage system management method based on multi-source data according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: extracting environmental features from the external environmental data of the industrial energy storage to obtain external environmental feature data of the industrial energy storage, wherein the external environmental feature data of the industrial energy storage includes environmental temperature data, environmental humidity data and environmental air pressure data; Step S32: Associating the geographical data of industrial energy storage equipment with the industrial energy storage system through the electric energy storage unit integrated network to generate geographical environment data of the industrial energy storage equipment; Step S33: Performing a multi-factor external environmental impact analysis on the geographical environment data of the industrial energy storage equipment based on the ambient temperature data, the ambient humidity data, and the ambient air pressure data to generate an external environmental impact factor for the industrial energy storage; Step S34: Perform abnormal environment monitoring on the external environment data of the industrial energy storage according to the external environment influencing factors of the industrial energy storage, generate normal environment monitoring data and abnormal environment monitoring data, perform a second warning on the abnormal environment monitoring data, and generate external environment abnormal warning data.

5. The industrial energy storage system management method based on multi-source data according to claim 4 is characterized in that: Step S33 includes the following steps: Step S331: extracting the extreme temperature of the geographical environment of the industrial energy storage equipment according to the ambient temperature data, generating extreme low temperature data and extreme high temperature data; performing performance impact analysis on the internal energy storage efficiency data of the industrial energy storage through the extreme low temperature data and the extreme high temperature data, generating an ambient temperature impact factor; Step S332: Calculate the environmental dryness of the geographical environment data of the industrial energy storage equipment according to the environmental humidity data to obtain the equipment environmental dryness data; use the environmental equipment dryness data to perform stability impact analysis on the internal energy storage efficiency data of the industrial energy storage to generate an environmental humidity impact factor; Step S333: Performing geographic elevation conversion on the geographic environment data of the industrial energy storage equipment to generate elevation data of the industrial energy storage equipment; performing altitude analysis on the elevation data of the industrial energy storage equipment to generate altitude data of the energy storage equipment; performing equipment structure impact analysis on the altitude data of the energy storage equipment through the ambient air pressure data to generate an ambient air pressure impact factor; Step S334: Integrate the environmental temperature influence factor, the environmental humidity influence factor and the environmental pressure influence factor to generate the external environment influence factor of industrial energy storage.

6. The industrial energy storage system management method based on multi-source data according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Integrate the internal environment abnormality warning data and the external environment abnormality warning data to generate comprehensive environment abnormality warning data; Step S42: performing energy efficiency prediction on the internal energy storage efficiency data of the industrial energy storage based on the normal environment monitoring data to generate industrial energy storage energy efficiency prediction data; Step S43: Setting a warning threshold for the industrial energy storage energy efficiency prediction data according to the comprehensive environmental abnormality warning data to obtain an energy efficiency prediction warning threshold; autonomously regulating the industrial energy storage energy efficiency prediction data using the energy efficiency prediction warning threshold, thereby generating an industrial energy storage management and regulation strategy to execute industrial energy storage system management operations.

7. The industrial energy storage system management method based on multi-source data according to claim 6 is characterized in that: Step S42 includes the following steps: Step S421: extracting energy efficiency impact features from the internal energy storage efficiency data of the industrial energy storage based on the normal environment monitoring data to obtain energy efficiency impact feature data; Step S422: Divide the energy efficiency impact feature data into data sets to obtain a model training set and a model test set; perform model training on the model training set using a linear regression algorithm to generate an industrial energy storage energy efficiency training model; perform model optimization iteration on the industrial energy storage energy efficiency training model using the model test set to generate an industrial energy storage energy efficiency prediction model; Step S423: Import the internal energy storage efficiency data of the industrial energy storage into the industrial energy storage energy efficiency prediction model to perform energy efficiency prediction and generate industrial energy storage energy efficiency prediction data.

8. An industrial energy storage system management system based on multi-source data, characterized in that: Used to execute the industrial energy storage system management method based on multi-source data as claimed in claim 1, the industrial energy storage system management system based on multi-source data includes: The environmental classification module is used to obtain comprehensive multi-source data of industrial energy storage; perform data preprocessing on the comprehensive multi-source data of industrial energy storage to generate standard comprehensive multi-source data of industrial energy storage; perform environmental data classification on the standard comprehensive multi-source data of industrial energy storage to generate internal environmental data of industrial energy storage and external environmental data of industrial energy storage; The electric energy storage efficiency analysis module is used to divide the internal environmental data of industrial energy storage into equipment operation states, obtain equipment normal operation state data and equipment abnormal operation state data; perform the first warning on the abnormal operation state data of the equipment, and generate internal environment abnormal warning data; perform electric energy storage unit network integration on the normal operation state data of the equipment, and generate an electric energy storage unit integrated network; perform energy storage efficiency analysis on the electric energy storage unit integrated network, and generate internal energy storage efficiency data of industrial energy storage; The abnormal environment monitoring module is used to extract environmental characteristics of the external environment data of the industrial energy storage to obtain the external environment characteristic data of the industrial energy storage; perform abnormal environment monitoring on the industrial energy storage system according to the external environment characteristic data of the industrial energy storage through the electric energy storage unit integrated network, generate normal environment monitoring data and abnormal environment monitoring data, and perform a second warning on the abnormal environment monitoring data to generate external environment abnormal warning data; The energy efficiency management module is used to predict the energy efficiency of the internal energy storage efficiency data of industrial energy storage based on the normal environment monitoring data, and generate industrial energy storage energy efficiency prediction data; the industrial energy storage energy efficiency prediction data is autonomously monitored and regulated through the internal environment abnormal warning data and the external environment abnormal warning data, thereby generating an industrial energy storage management and control strategy to execute the industrial energy storage system management operations.

Images