A high-voltage prefabricated substation intelligent debugging data management method and system

Abstract

The present invention discloses a method and system for intelligent debugging data management of a high-voltage prefabricated substation, and relates to the technical field of data management. The management method determines the data acquisition frequency based on a frequency multi-layer analysis method, and performs multi-source heterogeneous data acquisition based on the determined data acquisition frequency; after data preprocessing, the collected multi-source heterogeneous data is transmitted to a remote management center and stored; multi-source data analysis is performed based on the preprocessed multi-source heterogeneous data stored in the remote management center to determine the working conditions of the high-voltage prefabricated substation, which include the equipment failure type, equipment failure development trend and equipment failure cause; and the substation maintenance plan is determined based on the working conditions of the high-voltage prefabricated substation. The present invention can realize accurate and efficient equipment maintenance, reduce the probability of failure, reduce maintenance costs, improve the reliability and stability of substation operation, extend the service life of equipment, and ensure the safety and continuity of power supply.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a method and system for intelligent debugging data management of a high-voltage prefabricated substation. Background Art

[0002] With the rapid economic and social development, the demand for electric energy is increasing, power grid construction is advancing, and the application of high-voltage prefabricated substations is becoming increasingly widespread. The integration of grid control and regulation has become a key development direction for the power industry, placing higher demands on the intelligence level of substations, including intelligent and efficient commissioning data management. Prefabricated substations utilize a modular design approach, rationally modularizing a fully functional substation. Each module is prefabricated in a modern factory, with wiring and module commissioning completed within the factory. On-site substation work only requires external connections and overall coordinated commissioning, significantly reducing on-site workload and improving construction quality.

[0003] However, the existing intelligent commissioning data management technology for high-voltage prefabricated substations has deficiencies in data management. Traditional substation commissioning data management often relies on manual recording and organization. When faced with large amounts of data, it is not only inefficient but also prone to errors and omissions. It is difficult to ensure the accuracy and completeness of the data, and it is difficult to achieve real-time collection, transmission and processing of commissioning data, and it is impossible to provide accurate decision support for operation and maintenance personnel in a timely manner. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides a method and system for intelligent debugging data management of high-voltage prefabricated substations, which can achieve accurate and efficient equipment maintenance, reduce the probability of failure, reduce maintenance costs, and improve the reliability and stability of substation operation.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0006] A method for intelligent commissioning data management of a high-voltage prefabricated substation comprises the following steps:

[0007] Determine the data collection frequency based on the frequency multi-layer analysis method, and collect multi-source heterogeneous data based on the determined data collection frequency. The multi-source heterogeneous data includes equipment operating parameters, environmental parameters, equipment assets, and document data;

[0008] After data preprocessing, the collected multi-source heterogeneous data is transmitted to the remote management center and stored;

[0009] Perform multi-source data analysis based on pre-processed multi-source heterogeneous data stored in the remote management center to determine the operating conditions of the high-voltage prefabricated substation, including equipment failure types, equipment failure development trends, and equipment failure causes;

[0010] Determine the substation maintenance plan based on the operating conditions of the high-voltage prefabricated substation.

[0011] Preferably, determining the data acquisition frequency based on the frequency multi-layer analysis method includes the following steps:

[0012] Perform a frequency analysis based on equipment operating parameters and environmental parameters to obtain a primary data collection frequency based on the equipment operating parameters and environmental parameters. The equipment operating parameters include transformer operating data, high-voltage switchgear operating data, low-voltage switchgear operating data, and capacitor compensation device operating data.

[0013] Perform secondary frequency analysis based on data change trends to obtain secondary data collection frequencies based on data change trends. Data change trends include equipment operating parameter change trends and environmental parameter change trends.

[0014] Performing three-frequency analysis based on the grid operation conditions to obtain three-frequency data acquisition frequencies based on the grid operation conditions;

[0015] Determine the maximum value among the primary data collection frequency, the secondary data collection frequency, and the tertiary data collection frequency, and determine the maximum value as the to-be-determined collection frequency;

[0016] Determine whether the pending acquisition frequency is greater than the original acquisition frequency:

[0017] If the pending acquisition frequency is greater than the original acquisition frequency, the pending acquisition frequency is determined as the data acquisition frequency;

[0018] If the undetermined acquisition frequency is not greater than the original acquisition frequency, the original acquisition frequency is determined as the data acquisition frequency.

[0019] Preferably, performing a frequency analysis based on the equipment operating parameters and the environmental parameters to obtain a data collection frequency based on the equipment operating parameters and the environmental parameters comprises the following steps:

[0020] Standardize the equipment operating parameters and environmental parameters to obtain the standardized primary frequency determination data;

[0021] Based on the set hierarchical structure, the normalized frequency determination data is divided to obtain the judgment matrix A. , n is the number of indicators in the frequency-determined data after standardization, Indicates the importance of the i-th indicator relative to the j-th indicator, ;

[0022] Solve the characteristic equation of judgment matrix A , where I represents the identity matrix, Represents the eigenvalue of A and obtains the maximum eigenvalue and The corresponding eigenvector W, , T is the transpose symbol, The value representing the relative importance of the i-th indicator;

[0023] After normalizing the feature vector W, we get the weight vector P of the indicator. , , represents the weight of the i-th indicator;

[0024] Calculate the consistency index CI and random consistency ratio CR, perform consistency test, and judge the rationality of the matrix:

[0025] , where RI is the average random consistency index corresponding to n stored in the database. If CR is less than the exceeding threshold stored in the database, the judgment matrix is ​​considered reasonable. If CR is not less than the exceeding threshold stored in the database, the judgment matrix is ​​considered unreasonable and the judgment matrix A is readjusted;

[0026] Assume that the status level of substation equipment is divided into H levels. For the i-th indicator , its membership function Indicates the degree to which the indicator belongs to the hth state level, , let the value range of the hth state level be , then the membership function for:

[0027] ;

[0028] in, is the lower limit threshold of the value range of the h-th state level, is the parameter threshold of the value range of the hth state level, is the upper threshold of the value range of the hth state level, 、 and are all constants;

[0029] Based on the membership function of each indicator, the membership of each indicator to each state level is calculated and the fuzzy evaluation matrix R is constructed. ,in, ;

[0030] The weight vector P is combined with the fuzzy evaluation matrix R to obtain the comprehensive evaluation vector D. , ;

[0031] According to the maximum membership principle, the state level corresponding to the element with the largest membership in the comprehensive evaluation vector D is selected as the final state level of the substation equipment;

[0032] The frequency of data collection for obtaining the final status level stored in the database is defined as one-time data collection frequency.

[0033] Preferably, performing a secondary frequency analysis based on the data change trend to obtain a secondary data collection frequency based on the data change trend includes the following steps:

[0034] Assume that the equipment operating parameters have Q equipment indicators, which are recorded as , represents the value of the qth equipment index at time t, and the environmental parameters have K environmental indicators, which are respectively , represents the value of the kth environmental indicator at time t, , ;

[0035] For time interval , in the time interval Calculate the equipment operating parameter change rate of the qth equipment indicator , the environmental data change rate of the kth environmental indicator , the acceleration of device data change of the qth device indicator and the acceleration of environmental data change of the kth environmental indicator ;

[0036] Determine the comprehensive change trend assessment value :

[0037] ;

[0038] Among them, F1 and F2 are both transit functions. is the weight of the qth device indicator, is the weight of the kth environmental indicator, for The weight of for The weight of for The weight of for The weight of

[0039] Get The frequency of data collection corresponding to that stored in the database is defined as the secondary data collection frequency.

[0040] Preferably, performing three-frequency analysis based on the grid operation condition to obtain three-frequency data acquisition frequencies based on the grid operation condition includes the following steps:

[0041] Get the ratio of the current grid load to the historical maximum load value ;

[0042] For each node in the power grid, the difference between its injected power and outflow power is calculated, and then the difference of all nodes is normalized to obtain the node power imbalance of the entire network. ;

[0043] Get the ratio of the absolute value of the difference between the current node voltage and the rated voltage to the rated voltage ;

[0044] Get the absolute value of the difference between the current grid frequency and the rated frequency ;

[0045] Determine the comprehensive working condition evaluation index S:

[0046] ,in, for The weight factor, for The weight factor, for The weight factor, for The weight factor of

[0047] Get S corresponding to the data collection frequency stored in the database, which is defined as three data collection frequencies.

[0048] Preferably, the collected multi-source heterogeneous data is pre-processed and then transmitted to a remote management center and stored, which includes the following steps:

[0049] Edge computing nodes deployed near various devices in high-voltage prefabricated substations preprocess the collected raw multi-source heterogeneous data to obtain preprocessed multi-source heterogeneous data. Preprocessing includes data cleaning and format conversion.

[0050] The edge computing node transmits the pre-processed multi-source heterogeneous data to the local aggregation layer device via the industrial field bus or industrial Ethernet;

[0051] The local convergence layer device aggregates and verifies the pre-processed multi-source heterogeneous data, and classifies the pre-processed original multi-source heterogeneous data according to the data type and pre-set priority to obtain the classified multi-source heterogeneous data;

[0052] The local aggregation layer equipment transmits the classified multi-source heterogeneous data to the remote management center through an encrypted optical fiber network or 5G communication link;

[0053] In the remote management center, the real-time data and short-term historical data in the classified multi-source heterogeneous data are stored in an in-memory database.

[0054] For long-term historical data in classified multi-source heterogeneous data, a distributed file system combined with a relational database is used for storage:

[0055] The classified multi-source heterogeneous data is stored in blocks according to time series, and each block of data contains multi-source heterogeneous data within a set time range;

[0056] The relational database is used to store the metadata of classified multi-source heterogeneous data. The metadata includes the storage location of the data block, the data collection time range, and the device identification.

[0057] Preferably, performing multi-source data analysis based on pre-processed multi-source heterogeneous data stored in a remote management center to determine the operating condition of the high-voltage prefabricated substation includes the following steps:

[0058] Clean the pre-processed equipment operating parameters, pre-processed environmental parameters, and pre-processed equipment assets and document data in the pre-processed multi-source heterogeneous data, remove duplicate data, correct erroneous data, process missing values, and perform standardization;

[0059] Based on the AE autoencoder, feature extraction is performed on the numerical data to obtain feature G1. Based on the convolutional neural network, feature extraction is performed on the image data to obtain feature G2. G1 and G2 are concatenated to obtain the fused feature vector G3.

[0060] Input the fused feature vector G3 into the trained support vector machine fault classification model to determine the equipment fault type corresponding to the fused feature vector G3;

[0061] Based on the equipment failure type, time series data related to the equipment failure type is extracted from the pre-processed multi-source heterogeneous data. This time series data is processed according to the determined time step and then input into the trained LSTM time series prediction model to obtain the future development trend of equipment failures.

[0062] Input the equipment failure type, equipment failure development trend and fusion feature vector G3 into the trained random forest failure cause analysis model to obtain the equipment failure cause;

[0063] The equipment failure type, equipment failure development trend and equipment failure cause are defined as the high-voltage prefabricated substation working conditions.

[0064] Preferably, determining a substation maintenance plan based on the working condition of the high-voltage prefabricated substation includes the following steps:

[0065] Comparing the high-voltage prefabricated substation operating conditions with the high-voltage prefabricated substation set operating conditions stored in the database, and determining an initial maintenance plan set corresponding to the high-voltage prefabricated substation operating conditions;

[0066] Obtain historical data of high-voltage prefabricated substation equipment, including historical operating data, basic equipment information and maintenance records;

[0067] The initial maintenance plan set is screened based on historical data to obtain the final substation maintenance plan.

[0068] Preferably, screening the initial maintenance plan set based on historical data to obtain a final substation maintenance plan includes the following steps:

[0069] Obtain the historical parameter data corresponding to each initial maintenance plan in the initial maintenance plan set, including parameter historical operation data, basic information of the parameter equipment, and parameter maintenance records;

[0070] Based on the Jaccard similarity function, the Jaccard similarity value between the basic information of the equipment and the basic information of each parameter equipment is determined, and the initial maintenance plan set is screened to obtain the maintenance plan set after preliminary screening;

[0071] Determine the Euclidean distance value between the historical operation data and each of the preliminarily screened maintenance plans in the preliminarily screened maintenance plan set based on the Euclidean distance function, perform a secondary screening on the preliminarily screened maintenance plan set, and obtain a secondary screened maintenance plan set;

[0072] Determine the cosine similarity value between the maintenance record and each secondary screening maintenance plan in the secondary screening maintenance plan set based on the cosine similarity function, perform a tertiary screening on the secondary screening maintenance plan set to obtain a tertiary screening maintenance plan set;

[0073] Perform weighted summation of the remaining life of substation equipment after maintenance and the inverse of the maintenance cost stored in the database for each three-times-screened maintenance plan in the three-times-screened maintenance plan set to obtain a maintenance plan determination coefficient;

[0074] The maximum value among the determination coefficients of the maintenance plans is determined, and the maintenance plan after three screenings corresponding to the maintenance plan determination coefficient corresponding to the maximum value is determined as the substation maintenance plan.

[0075] A high-voltage prefabricated substation intelligent commissioning data management system, used to implement the above method, includes a data acquisition frequency determination module, a data storage module, a substation operating condition determination module, and a substation maintenance plan determination module, wherein:

[0076] The data collection frequency determination module is used to determine the data collection frequency based on the frequency multi-layer analysis method, and to collect multi-source heterogeneous data based on the determined data collection frequency. The multi-source heterogeneous data includes equipment operating parameters, environmental parameters, and equipment assets and document data.

[0077] The data storage module is used to pre-process the collected multi-source heterogeneous data and transmit it to the remote management center for storage;

[0078] The substation operating condition determination module is used to perform multi-source data analysis based on pre-processed multi-source heterogeneous data stored in the remote management center to determine the operating conditions of the high-voltage prefabricated substation, including equipment failure types, equipment failure development trends, and equipment failure causes;

[0079] The substation maintenance plan determination module is used to determine the substation maintenance plan based on the working conditions of the high-voltage prefabricated substation.

[0080] The present invention has the following beneficial effects:

[0081] The present invention determines a reasonable data collection frequency through a frequency multi-layer analysis method, and can accurately obtain multi-source heterogeneous data such as equipment operating parameters, environmental parameters, equipment assets and documents, thereby avoiding problems of insufficient or excessive data collection. The collected data is pre-processed and remotely stored to ensure data quality and traceability. Multi-source data analysis can accurately determine the type, development trend and cause of equipment failures, and provide comprehensive and timely equipment operating condition information to operation and maintenance personnel. Ultimately, the maintenance plan is determined based on the operating conditions, which can achieve accurate and efficient equipment maintenance, reduce the probability of failures, reduce maintenance costs, improve the reliability and stability of substation operation, extend the service life of equipment, and ensure the safety and continuity of power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 This is a flow chart of the intelligent debugging data management method for a high-voltage prefabricated substation according to the present invention;

[0083] Figure 2 This is a module connection diagram of the intelligent debugging data management system for a high-voltage prefabricated substation according to the present invention. DETAILED DESCRIPTION

[0084] This embodiment uses a high-voltage prefabricated substation intelligent commissioning data management method and system to achieve the effect of using a frequency multi-layer analysis method to reasonably determine the data collection frequency and determine the maintenance plan.

[0085] Example 1:

[0086] like Figure 1 As shown, a method for intelligent commissioning data management of a high-voltage prefabricated substation includes the following steps: determining a data acquisition frequency based on a frequency multi-layer analysis method, and acquiring multi-source heterogeneous data based on the determined data acquisition frequency, wherein the multi-source heterogeneous data includes equipment operating parameters, environmental parameters, and equipment assets and document data;

[0087] Perform a frequency analysis based on equipment operating parameters and environmental parameters to obtain a primary data collection frequency based on the equipment operating parameters and environmental parameters. The equipment operating parameters include transformer operating data, high-voltage switchgear operating data, low-voltage switchgear operating data, and capacitor compensation device operating data.

[0088] The equipment operating parameters and environmental parameters are standardized to obtain the standardized primary frequency determination data; the equipment operating parameters and environmental parameters are standardized to make data of different dimensions and magnitudes on the same scale, which is convenient for comparison and analysis and improves the accuracy and efficiency of subsequent analysis.

[0089] Based on the set hierarchical structure, the normalized frequency determination data is divided to obtain the judgment matrix A. , n is the number of indicators in the frequency-determined data after standardization, Indicates the importance of the i-th indicator relative to the j-th indicator, . Use the 1-9 standard method to assign values, for example:

[0090] scale meaning 1 The i-th indicator is as important as the j-th indicator 3 The i-th indicator is slightly more important than the j-th indicator 5 The i-th indicator and the j-th indicator are obviously important 7 The i-th indicator is strongly important to the j-th indicator 9 The i-th indicator and the j-th indicator are extremely important 2，4，6，8 The median value of the above adjacent judgments

[0091] The 1-9 standard method is used to construct the judgment matrix A to determine the relative importance of each indicator. This can quantify people's subjective judgment on the importance of each indicator, making the analysis more scientific and objective, and avoiding the arbitrariness of determining weights based solely on experience or intuition.

[0092] Solve the characteristic equation of judgment matrix A , where I represents the identity matrix, Represents the eigenvalue of A and obtains the maximum eigenvalue and The corresponding eigenvector W, , T is the transpose symbol, The value representing the relative importance of the i-th indicator; the weight vector P of the indicator is obtained by normalizing the feature vector W. , , represents the weight of the i-th indicator;

[0093] Calculate the consistency index CI and random consistency ratio CR, perform consistency test, and judge the rationality of the matrix:

[0094] , where RI is the average random consistency index corresponding to n stored in the database. If CR is less than the exceeding threshold stored in the database, the judgment matrix is ​​considered reasonable. If CR is not less than the exceeding threshold stored in the database, the judgment matrix is ​​considered unreasonable and the judgment matrix A is readjusted. Readjusting the judgment matrix A ensures the accuracy and reliability of weight determination, making subsequent weight-based analysis results more credible.

[0095] Assume that the status level of substation equipment is divided into H levels. For the i-th indicator , its membership function Indicates the degree to which the indicator belongs to the hth state level, , let the value range of the hth state level be , then the membership function for:

[0096] ;

[0097] in, is the lower limit threshold of the value range of the h-th state level, is the parameter threshold of the value range of the hth state level, is the upper threshold of the value range of the hth state level, 、 and They are all constants and can be set according to actual needs;

[0098] Based on the membership function of each indicator, the membership of each indicator to each state level is calculated and the fuzzy evaluation matrix R is constructed. ,in, (That is, use To represent The fuzzy evaluation matrix R is used to comprehensively consider the membership of each indicator, which is in line with the characteristics that the status of substation equipment is often fuzzy and uncertain. It can more accurately describe the actual operating status of the equipment and is more in line with the actual situation than the traditional deterministic evaluation method.

[0099] The weight vector P is combined with the fuzzy evaluation matrix R to obtain the comprehensive evaluation vector D. , According to the maximum membership principle, the status level corresponding to the element with the largest membership in the comprehensive evaluation vector D is selected as the final status level of the substation equipment. The data collection frequency of the final status level stored in the database is obtained, which is defined as the primary data collection frequency. The weight vector P is combined with the fuzzy evaluation matrix R to obtain the comprehensive evaluation vector D. The final status level of the equipment is then determined according to the maximum membership principle. This can comprehensively consider the weights and membership of each indicator to obtain an evaluation result that comprehensively reflects the overall status of the equipment, providing a strong basis for determining a reasonable data collection frequency.

[0100] This system considers multiple indicators, including substation equipment and the environment, and constructs a membership function for each indicator to represent its degree of belonging to different status levels. This allows for a comprehensive and detailed portrayal of the equipment's operating status, avoiding the incomplete assessment of equipment status that results from focusing on a single indicator. It also adjusts the data collection frequency to suit different equipment operating states and environmental conditions. By deriving the corresponding data collection frequency based on the final status level, the frequency matches the actual equipment operating state, achieving precise and intelligent data collection, ensuring both data validity and the rational use of resources.

[0101] Perform secondary frequency analysis based on data change trends to obtain secondary data collection frequencies based on data change trends. Data change trends include equipment operating parameter change trends and environmental parameter change trends.

[0102] Assume that the equipment operating parameters have Q equipment indicators, which are recorded as , represents the value of the qth equipment index at time t, and the environmental parameters have K environmental indicators, which are respectively , represents the value of the kth environmental indicator at time t, , ; For time interval , in the time interval Calculate the equipment operating parameter change rate of the qth equipment indicator , the environmental data change rate of the kth environmental indicator , the acceleration of device data change of the qth device indicator and the acceleration of environmental data change of the kth environmental indicator ;

[0103] Determine the comprehensive change trend assessment value :

[0104] ;

[0105] Among them, F1 and F2 are both transit functions. is the weight of the qth device indicator, is the weight of the kth environmental indicator, for The weight of for The weight of for The weight of for The weight of The frequency of data collection stored in the database is defined as the secondary data collection frequency. By assigning weights to equipment and environmental indicators, as well as to the rate of change and acceleration of change, we can rationally balance the impact of different factors on the comprehensive trend assessment based on actual conditions. Different equipment and environmental indicators have varying degrees of importance to substation operations, and their rates of change and acceleration may also vary in their importance. By assigning weights, we can more scientifically reflect the relative importance of each factor, making the comprehensive assessment more reasonable.

[0106] Get The frequency of data collection corresponding to that stored in the database is defined as the secondary data collection frequency.

[0107] In terms of capturing data characteristics, the system considers both the rate of change of device operating parameters and environmental parameters, and also introduces the acceleration of device data changes and the acceleration of environmental data changes, comprehensively capturing the dynamic characteristics of data changes from multiple dimensions. The rate of change reflects the speed of data change over a certain period of time, while the acceleration further reflects whether the trend of change is accelerating or slowing down, making the description of data change trends more detailed and accurate. By comprehensively considering multiple factors, it can better adapt to the complex changes in data in actual operation and avoid misjudging data change trends due to focusing on a single factor.

[0108] Determining the data collection frequency based on the comprehensive trend assessment value closely aligns the collection frequency with the actual data changes. When data changes dramatically (i.e., when the comprehensive trend assessment value is high), the data collection frequency is increased accordingly to capture data changes more promptly and obtain more key information. When data changes are relatively stable, the collection frequency is reduced. This ensures data quality while conserving data collection and storage resources, achieving a precise and dynamic match between data collection frequency and data change trends.

[0109] Performing three-frequency analysis based on the grid operation conditions to obtain three-frequency data acquisition frequencies based on the grid operation conditions;

[0110] Get the ratio of the current grid load to the historical maximum load value For each node in the power grid, the difference between its injected power and outflow power is calculated, and then the difference of all nodes is normalized to obtain the node power imbalance of the entire network. ; Get the ratio of the absolute value of the difference between the current node voltage and the rated voltage to the rated voltage ; Get the absolute value of the difference between the current grid frequency and the rated frequency ; Determine the comprehensive working condition evaluation index S:

[0111] ,in, for The weight factor, for The weight factor, for The weight factor, for The weight factor of S is obtained; the data collection frequency stored in the database is obtained, which is defined as three data collection frequencies.

[0112] By considering , , and , which can comprehensively reflect the grid's operating conditions from various perspectives. These indicators cover key aspects such as grid load, power balance, voltage stability, and frequency stability, making monitoring of the grid's overall operating status more comprehensive and accurate. Calculating the comprehensive operating condition assessment index S based on multiple indicators fully utilizes the information contained in each indicator. Multiple indicators complement and reinforce each other, providing a more comprehensive and accurate reflection of the grid's true operating conditions, reducing misjudgments caused by fluctuations or errors in individual indicators. This improves the reliability of the comprehensive assessment and provides a more solid basis for determining data collection frequency.

[0113] Determining the data collection frequency based on the comprehensive operating condition assessment index S ensures that the data collection frequency is closely aligned with the actual operating conditions of the power grid. When the grid's operating conditions are complex or potential risks exist, that is, when the comprehensive operating condition assessment index S shows significant changes or anomalies, the data collection frequency is increased accordingly to more intensively monitor grid operating data and promptly identify and address potential problems. When the grid is operating relatively stably, the collection frequency is reduced. This ensures that critical information is obtained while effectively conserving resources such as data collection, transmission, and storage. This enables on-demand data collection and improves resource utilization efficiency.

[0114] Determine the maximum value among the primary data acquisition frequency, the secondary data acquisition frequency, and the tertiary data acquisition frequency, and determine the maximum value as the pending acquisition frequency; determine whether the pending acquisition frequency is greater than the original acquisition frequency: if the pending acquisition frequency is greater than the original acquisition frequency, determine the pending acquisition frequency as the data acquisition frequency; if the pending acquisition frequency is not greater than the original acquisition frequency, determine the original acquisition frequency as the data acquisition frequency.

[0115] After data preprocessing, the collected multi-source heterogeneous data is transmitted to the remote management center and stored;

[0116] Edge computing nodes deployed near various devices in high-voltage prefabricated substations preprocess the collected raw multi-source heterogeneous data to generate preprocessed multi-source heterogeneous data. Preprocessing includes data cleaning and format conversion. The raw data collected by various devices in high-voltage prefabricated substations often has various quality issues and format differences. Directly transmitting and storing this raw data can bring many difficulties to subsequent work, such as low data processing efficiency and inaccurate analysis results. By performing data cleaning and format conversion at edge computing nodes, data can be initially processed at the source, solving these problems.

[0117] Edge computing nodes transmit preprocessed, multi-source heterogeneous data to local aggregation layer devices via industrial fieldbuses (such as Profibus and Modbus) or industrial Ethernet. Industrial fieldbuses include Profibus and Modbus. Local aggregation layer devices aggregate and verify the preprocessed multi-source heterogeneous data and classify the preprocessed raw multi-source heterogeneous data based on data type and pre-set priority, generating classified multi-source heterogeneous data. Edge computing nodes are connected to local aggregation layer devices using industrial fieldbuses (such as Profibus and Modbus) or industrial Ethernet. These communication methods offer high reliability, real-time performance, and interference resistance, ensuring accurate and rapid transmission of preprocessed data to local aggregation layer devices. Local aggregation layer devices aggregate, verify, and classify the data, further ensuring its integrity and accuracy. Classification by data type and priority optimizes resource allocation for subsequent transmission and processing.

[0118] The local aggregation layer equipment transmits the classified multi-source heterogeneous data to the remote management center through an encrypted fiber optic network or 5G communication link; the classified data is transmitted to the remote management center using an encrypted fiber optic network or 5G communication link. The encrypted fiber optic network has the characteristics of high bandwidth, low latency and high security, and the 5G communication link has the advantages of high speed and flexibility, which can meet the needs of remote data transmission in different scenarios, ensuring that a large amount of multi-source heterogeneous data can be transmitted to the remote management center in a timely and secure manner for processing and storage.

[0119] Given the wide distribution of substation equipment, data needs to be transmitted from on-site to a remote management center for centralized management and analysis. Different communication methods are suitable for different scenarios and distances. This layered transmission design, combining multiple communication methods, allows the selection of the most appropriate transmission method based on actual conditions, ensuring stable and efficient data transmission. Furthermore, data aggregation, verification, and classification operations allow for further management and optimization during transmission, improving data quality and efficiency.

[0120] In the remote management center, the real-time data and short-term historical data in the classified multi-source heterogeneous data are stored in an in-memory database, including Redis. The long-term historical data in the classified multi-source heterogeneous data are stored in a distributed file system combined with a relational database, including Ceph, and the relational database including PostgreSQL. The classified multi-source heterogeneous data are divided into blocks and stored according to time series, and each block of data contains multi-source heterogeneous data within a set time range. The relational database is used to store the metadata of the classified multi-source heterogeneous data, which includes the storage location of the data block, the data collection time range, and the device identification.

[0121] Multi-source, heterogeneous data has different characteristics and application requirements. Real-time data and short-term historical data require fast access and processing, while long-term historical data requires extensive storage space and effective organization and management. Using different storage technologies and approaches can optimize storage based on data characteristics, meeting the data storage and access requirements of different businesses while improving the performance and scalability of the entire data storage system.

[0122] Perform multi-source data analysis based on pre-processed multi-source heterogeneous data stored in the remote management center to determine the operating conditions of the high-voltage prefabricated substation, including equipment failure types, equipment failure development trends, and equipment failure causes;

[0123] The preprocessed multi-source heterogeneous data, including preprocessed equipment operating parameters, preprocessed environmental parameters, and preprocessed equipment asset and document data, is cleaned to remove duplicate data, correct erroneous data, address missing values, and perform standardization. Feature extraction is performed on the numerical data using the AE autoencoder to obtain feature G1, and feature extraction is performed on the image data using a convolutional neural network to obtain feature G2. G1 and G2 are then concatenated to obtain a fused feature vector G3. Multi-source heterogeneous data includes various types of data, such as equipment operating parameters, environmental parameters, and equipment asset and document data. The data quality varies, and different types of data have different characteristics and structures. Through targeted data preprocessing and feature extraction methods, the value of different types of data can be fully explored, improving data availability and feature validity, thereby enhancing the accuracy and reliability of the entire analysis process.

[0124] The fused feature vector G3 is input into the trained support vector machine fault classification model to determine the equipment fault type corresponding to the fused feature vector G3; based on the equipment fault type, time series data related to the equipment fault type is extracted from the preprocessed multi-source heterogeneous data, and the time series data related to the equipment fault type is processed according to the determined time step and input into the trained LSTM time series prediction model to obtain the future equipment failure development trend; the equipment failure type, equipment failure development trend and fused feature vector G3 are input into the trained random forest fault cause analysis model to obtain the equipment failure cause; the equipment failure type, equipment failure development trend and equipment failure cause are defined as the high-voltage prefabricated substation operating condition.

[0125] In high-voltage prefabricated substations, equipment failures can be diverse, and accurate fault identification is crucial for implementing timely maintenance measures and ensuring safe grid operation. Support vector machines, as a mature classification algorithm, can effectively handle high-dimensional data and complex classification problems. Combined with fusion feature vectors, they can better adapt to the characteristics of multi-source heterogeneous data and achieve accurate fault classification.

[0126] The support vector machine (SVM) fault classification model is a supervised learning model that can be used to classify and identify equipment fault types. The SVM model is trained using a fused feature vector as input and the equipment fault type label as output. During training, hyperparameters such as the kernel function (such as the linear kernel or radial basis kernel) and the penalty parameter C are adjusted to optimize the model's classification performance. For example, using the radial basis kernel function and selecting an appropriate C value through cross-validation enables the SVM model to accurately distinguish between different types of transformer faults, such as overheating and short circuit faults.

[0127] LSTM is a recurrent neural network suitable for processing time series data. Time series data from multiple sources (such as equipment temperature and current, which change over time) is fed into the LSTM model to predict future trends in equipment operating parameters. During training, appropriate hyperparameters such as the time step size and number of hidden layer neurons are determined to enable the model to accurately capture the temporal dependencies of the data. For example, an LSTM model can be used to predict the changing trend of transformer oil temperature over the next several hours.

[0128] A random forest is an ensemble learning model composed of multiple decision trees. The random forest model is trained using the fused feature vector and known fault cause labels as input. During training, hyperparameters such as the number of decision trees and the maximum depth of each tree are adjusted to improve the model's analytical accuracy. For example, a random forest model can be used to analyze possible causes of transformer overheating faults, such as cooling system failures and winding short circuits.

[0129] In a specific embodiment, the steps for obtaining the operating conditions of the high-voltage prefabricated substation are as follows:

[0130] From the fused feature vector dataset, divide the training and test sets into a certain proportion (e.g., 70%-30% or 80%-20%). Ensure that the distribution of samples for each fault type in the training and test sets is relatively balanced to avoid model bias. For example, if there are three types of faults: overheating, short circuit, and insulation fault, the number of samples for each type in the training set should be roughly the same. Normalize the fused feature vectors in the training and test sets so that their eigenvalues ​​are within the range of [0, 1] or [-1, 1].

[0131] Kernel Function Selection: Common kernel functions include linear kernels, radial basis kernels (RBFs), and polynomial kernels. Generally, start with the radial basis kernel because it is more adaptable to data distributions. Hyperparameter Tuning: Use cross-validation, such as 5-fold cross-validation, to divide the training set into five subsets. Four subsets are used for training the model at a time, and one subset is used for validation. For different hyperparameter combinations, calculate the model accuracy on the validation set. Select the hyperparameter combination with the highest accuracy as the optimal hyperparameter combination.

[0132] Train the SVM model using the optimal hyperparameters and training set. Call the corresponding machine learning library (such as the SVC class in Scikit-learn) and pass in the training data and labels to train the model. Evaluate the trained SVM model using the test set, calculating metrics such as accuracy, precision, recall, and F1 score.

[0133] Extract time series data related to equipment operating parameters, such as transformer oil temperature and current, from multiple data sources. Normalize this time series data, using min-max or Z-score normalization. Convert the time series data into a format suitable for LSTM model input. For example, determine a time step length, X, and divide the time series data into multiple segments of length X. The last value of each segment is used as the prediction target, and the preceding X-1 values ​​are used as input features.

[0134] Similarly, divide the training and test sets into a specific ratio. Determine hyperparameters (determine the time step, number of hidden layer neurons, and learning rate). Build an LSTM model using a deep learning framework such as Keras or PyTorch, and set the structure of the input, LSTM, and output layers. Train the model using the training set, setting an appropriate number of training epochs (e.g., 100-200 epochs) and batch size (e.g., 32, 64). Evaluate the trained model using the test set, calculating metrics such as mean squared error (MSE) and root mean squared error (RMSE) to assess the model's predictive accuracy.

[0135] Combine the fused feature vectors and known fault cause labels into a dataset, and divide the dataset into training and test sets. Feature selection can be performed on the feature vectors to remove features that contribute less to fault cause analysis, improving model training efficiency and accuracy. You can use methods based on feature importance ranking, such as the feature importance evaluation function built into the random forest algorithm, to select the top features with the highest importance.

[0136] We adjusted hyperparameters (the number of decision trees and the maximum depth of each tree) and used the RandomForestClassifier class in Scikit-learn to train the model, passing in the training set data and labels. We then evaluated the trained model using the test set, calculating metrics such as accuracy, precision, and recall to assess the model's accuracy in fault cause analysis.

[0137] After training is complete, the normalized fused feature vector is input into the trained SVM fault classification model. Based on the classification boundaries obtained during training, the model calculates the score or probability that the input feature vector belongs to each fault type. The fault type with the highest score or the highest probability is selected as the preliminary diagnosis result. For example, if the calculated probability that the input feature vector belongs to an overheating fault is 0.8, the probability of a short circuit fault is 0.1, and the probability of an insulation fault is 0.1, then the preliminary diagnosis is that the equipment has an overheating fault.

[0138] Based on the initial diagnostic results of the SVM model, time series data related to the fault type is extracted from multiple data sources. For example, if the fault is diagnosed as overheating, the time series data for the transformer's oil temperature is extracted. This extracted time series data is processed according to the previously determined time step size and input into the trained LSTM time series prediction model. The model outputs predicted values ​​for equipment operating parameters over the next period of time, such as the predicted trend of transformer oil temperature over the next three hours. The prediction results can be plotted as a curve to visually demonstrate the fault's development trend.

[0139] The SVM model's classification results (such as fault type labels), the LSTM model's prediction results (such as parameter predictions for a specific time period), and the original fused feature vector are combined to form new input data. This new input data is then fed into the trained random forest fault cause analysis model. The model analyzes the specific cause of the fault based on the trained decision rules. The model outputs a probability or score for each fault cause and selects the cause with the highest probability or score as the primary fault cause. For example, if the model outputs a probability of 0.7 that a transformer overheating fault is due to a damaged cooling fan, a probability of 0.2 that a winding short circuit is caused, and a probability of 0.1 that an overload is caused, the primary fault cause is determined to be a damaged cooling fan.

[0140] Determine the substation maintenance plan based on the operating conditions of the high-voltage prefabricated substation.

[0141] The operating conditions of the high-voltage prefabricated substation are compared with the set operating conditions of the high-voltage prefabricated substation stored in the database to determine the initial maintenance plan set corresponding to the operating conditions of the high-voltage prefabricated substation; historical data of the high-voltage prefabricated substation equipment is obtained, and the historical data includes historical operating data (including but not limited to temperature, humidity, current, voltage, operating time, number of failures), basic equipment information (such as model, production date, installation date, etc.) and maintenance records (such as maintenance time, replacement of parts, etc.); the initial maintenance plan set is screened based on the historical data to obtain the final substation maintenance plan.

[0142] Comparing the current operating conditions of a high-voltage prefabricated substation with the pre-set operating conditions stored in the database allows rapid identification of similar pre-set operating conditions and their corresponding maintenance plans, making the initial maintenance plan collection highly targeted. The pre-set operating conditions and corresponding maintenance plans stored in the database are the result of extensive accumulation and summary, encompassing a wealth of practical experience and expertise. Comparing this historical data fully utilizes existing resources and improves the efficiency and quality of maintenance plan development.

[0143] Obtain historical parameter data corresponding to each initial maintenance plan in the initial maintenance plan set, including parameter historical operation data, parameter basic information of the parameter equipment and parameter maintenance records; determine the Jaccard similarity value between the basic information of the equipment and the basic information of each parameter equipment based on the Jaccard similarity function, screen the initial maintenance plan set, and obtain a preliminary screened maintenance plan set (when the Jaccard similarity value corresponding to one of the initial maintenance plans is greater than the first threshold stored in the database, the initial maintenance plan is used as one of the preliminary screened maintenance plan set); equipment of different models, production dates and installation dates may have large differences in performance, structure and usage, and the corresponding maintenance requirements and plans will also be different.

[0144] The Jaccard similarity function is suitable for processing categorical data. Basic equipment information (such as model, production date, and installation date) is often categorical or discrete. By calculating the Jaccard similarity between basic equipment information and that of reference equipment, maintenance plans can be screened for equipment with similar basic conditions. This helps eliminate plans that are inappropriate due to inherent differences in equipment characteristics, ensuring that the initially screened maintenance plan set is more tailored to the actual conditions of the substation equipment.

[0145] Based on the Euclidean distance function, the Euclidean distance values ​​between the historical operating data and each preliminary screening maintenance plan in the preliminary screening maintenance plan set are determined, and the preliminary screening maintenance plan set is secondary screened to obtain a secondary screening maintenance plan set (when the Euclidean distance value corresponding to one of the preliminary screening maintenance plans is not greater than the second threshold stored in the database, the preliminary screening maintenance plan is used as one of the secondary screening maintenance plan set); even if the basic information of the equipment is similar, its operating status may vary due to the actual use environment and operating conditions. The operating data reflects the current working status and performance of the equipment.

[0146] The Euclidean distance function is commonly used to measure the distance between continuous numerical data. Historical operating data (such as temperature, humidity, current, voltage, operating time, and number of faults) is continuous numerical data. By calculating the Euclidean distance between historical operating data and the initially selected maintenance plans, a secondary screening process can be performed to further select plans with similar operating conditions. This ensures that the secondary screening maintenance plan set is more closely aligned with the current substation in terms of equipment operating status.

[0147] Based on the cosine similarity function, the cosine similarity values ​​between the maintenance records and each secondary screening maintenance plan in the secondary screening maintenance plan set are determined. The secondary screening maintenance plan set is screened three times to obtain a tertiary screening maintenance plan set (when the cosine similarity value corresponding to one of the secondary screening maintenance plans is greater than the third threshold stored in the database, the secondary screening maintenance plan is used as one of the tertiary screening maintenance plan sets). The maintenance history of equipment is an important reflection of its operational reliability and failure modes. Similar maintenance records may mean similar failure causes and solutions.

[0148] The cosine similarity function measures the cosine of the angle between vectors and is suitable for processing high-dimensional vector data. Maintenance records (such as repair time and part replacement) can be considered a form of high-dimensional vector data. By calculating the cosine similarity between maintenance records and maintenance plans after secondary screening, a tertiary screening process can be performed to identify plans with similar maintenance histories. This helps to consider the equipment's past maintenance experience and troubleshooting methods, ensuring that the resulting tertiary screening maintenance plan set better meets the equipment's actual maintenance needs.

[0149] The weighted sum of the remaining life of the substation equipment after maintenance and the inverse of the maintenance cost stored in the database corresponding to each three-times-screened maintenance plan in the three-times-screened maintenance plan set is performed to obtain a maintenance plan determination coefficient; the maximum value among the various maintenance plan determination coefficients is determined, and the three-times-screened maintenance plan corresponding to the maintenance plan determination coefficient corresponding to the maximum value is determined as the substation maintenance plan.

[0150] During the three screening processes mentioned above:

[0151] If there is only one preliminary screening maintenance plan in the set of preliminary screening maintenance plans, then this preliminary screening maintenance plan is directly used as the substation maintenance plan. In addition, if there is no preliminary screening maintenance plan in the set of preliminary screening maintenance plans, then the initial maintenance plan corresponding to the largest Jaccard similarity value is used as the substation maintenance plan.

[0152] If there is only one secondary screening maintenance plan in the set of secondary screening maintenance plans, then this secondary screening maintenance plan is directly used as the substation maintenance plan. Otherwise, if there is no secondary screening maintenance plan in the set of secondary screening maintenance plans, then the primary screening maintenance plan corresponding to the smallest Euclidean distance value is used as the substation maintenance plan.

[0153] If there is only one triple-screened maintenance solution in the set, then that solution is directly used as the substation maintenance solution. If there is no triple-screened maintenance solution in the set, then the quadratic maintenance solution corresponding to the largest cosine similarity value is used as the substation maintenance solution.

[0154] Example 2:

[0155] like Figure 2 As shown, a high-voltage prefabricated substation intelligent debugging data management system is used to implement the method in Example 1, including a data acquisition frequency determination module, a data storage module, a substation operating condition determination module and a substation maintenance plan determination module, wherein: the data acquisition frequency determination module is used to determine the data acquisition frequency based on the frequency multi-layer analysis method, and perform multi-source heterogeneous data acquisition based on the determined data acquisition frequency, and the multi-source heterogeneous data includes equipment operating parameters, environmental parameters, and equipment assets and document data; the data storage module is used to preprocess the collected multi-source heterogeneous data, and then transmit it to a remote management center and store it; the substation operating condition determination module is used to perform multi-source data analysis based on the preprocessed multi-source heterogeneous data stored in the remote management center to determine the operating condition of the high-voltage prefabricated substation, including the equipment failure type, equipment failure development trend and equipment failure cause; the substation maintenance plan determination module is used to determine the substation maintenance plan based on the high-voltage prefabricated substation operating condition.

[0156] Example 3:

[0157] An electronic device includes: a processor; and a memory, wherein computer program instructions are stored in the memory, and when the computer program instructions are executed by the processor, the processor executes the method in embodiment 1.

[0158] Example 4:

[0159] A computer-readable storage medium is used to store a program, and when the program is executed by a processor, the method in embodiment 1 is implemented.

Claims

1. A method for intelligent commissioning data management of a high-voltage prefabricated substation, characterized in that: The following steps are involved: The data collection frequency is determined based on the frequency multi-level analysis method, including the following steps: Perform a frequency analysis based on equipment operating parameters and environmental parameters to obtain a primary data collection frequency based on the equipment operating parameters and environmental parameters. The equipment operating parameters include transformer operating data, high-voltage switchgear operating data, low-voltage switchgear operating data, and capacitor compensation device operating data. Perform secondary frequency analysis based on data change trends to obtain secondary data collection frequencies based on data change trends. Data change trends include equipment operating parameter change trends and environmental parameter change trends. Performing three-frequency analysis based on the grid operation conditions to obtain three-frequency data acquisition frequencies based on the grid operation conditions; Determine the maximum value among the primary data collection frequency, the secondary data collection frequency, and the tertiary data collection frequency, and determine the maximum value as the to-be-determined collection frequency; Determine whether the pending acquisition frequency is greater than the original acquisition frequency: If the pending acquisition frequency is greater than the original acquisition frequency, the pending acquisition frequency is determined as the data acquisition frequency; If the undetermined acquisition frequency is not greater than the original acquisition frequency, the original acquisition frequency is determined as the data acquisition frequency; Collect multi-source heterogeneous data based on a determined data collection frequency. The multi-source heterogeneous data includes equipment operating parameters, environmental parameters, equipment assets, and document data. After data preprocessing, the collected multi-source heterogeneous data is transmitted to the remote management center and stored; Multi-source data analysis is performed based on pre-processed multi-source heterogeneous data stored in the remote management center to determine the operating conditions of the high-voltage prefabricated substation, including the following steps: Clean the pre-processed equipment operating parameters, pre-processed environmental parameters, and pre-processed equipment assets and document data in the pre-processed multi-source heterogeneous data, remove duplicate data, correct erroneous data, process missing values, and perform standardization; Based on the AE autoencoder, feature extraction is performed on the numerical data to obtain feature G1. Based on the convolutional neural network, feature extraction is performed on the image data to obtain feature G2. G1 and G2 are concatenated to obtain the fused feature vector G3. Input the fused feature vector G3 into the trained support vector machine fault classification model to determine the equipment fault type corresponding to the fused feature vector G3; Based on the equipment failure type, time series data related to the equipment failure type is extracted from the pre-processed multi-source heterogeneous data. This time series data is processed according to the determined time step and then input into the trained LSTM time series prediction model to obtain the future development trend of equipment failures. Input the equipment failure type, equipment failure development trend and fusion feature vector G3 into the trained random forest failure cause analysis model to obtain the equipment failure cause; The equipment failure type, equipment failure development trend and equipment failure cause are defined as the high-voltage prefabricated substation operating conditions; Determine the substation maintenance plan based on the operating conditions of the high-voltage prefabricated substation.

2. A high-voltage prefabricated substation intelligent commissioning data management method according to claim 1, characterized in that: Performing a frequency analysis based on the equipment operating parameters and the environmental parameters to obtain a data collection frequency based on the equipment operating parameters and the environmental parameters includes the following steps: Standardize the equipment operating parameters and environmental parameters to obtain the standardized primary frequency determination data; Based on the set hierarchical structure, the normalized frequency determination data is divided to obtain the judgment matrix A. , n is the number of indicators in the frequency-determined data after standardization, Indicates the importance of the i-th indicator relative to the j-th indicator, ; Solve the characteristic equation of judgment matrix A , where I represents the identity matrix, Represents the eigenvalue of A and obtains the maximum eigenvalue and The corresponding eigenvector W, , T is the transpose symbol, The value representing the relative importance of the i-th indicator; After normalizing the feature vector W, we get the weight vector P of the indicator. , , represents the weight of the i-th indicator; Calculate the consistency index CI and random consistency ratio CR, perform consistency test, and judge the rationality of the matrix: , where RI is the average random consistency index corresponding to n stored in the database. If CR is less than the exceeding threshold stored in the database, the judgment matrix is ​​considered reasonable. If CR is not less than the exceeding threshold stored in the database, the judgment matrix is ​​considered unreasonable and the judgment matrix A is readjusted; Assume that the status level of substation equipment is divided into H levels. For the i-th indicator , its membership function Indicates the degree to which the indicator belongs to the hth state level, , let the value range of the hth state level be , then the membership function for: ； in, is the lower limit threshold of the value range of the hth state level, is the parameter threshold of the value range of the hth state level, is the upper threshold of the value range of the hth state level, 、 and are all constants; Based on the membership function of each indicator, the membership of each indicator to each state level is calculated and the fuzzy evaluation matrix R is constructed. ,in, ; The weight vector P is combined with the fuzzy evaluation matrix R to obtain the comprehensive evaluation vector D. , ; According to the maximum membership principle, the state level corresponding to the element with the largest membership in the comprehensive evaluation vector D is selected as the final state level of the substation equipment; The frequency of data collection for obtaining the final status level stored in the database is defined as one-time data collection frequency.

3. A method for managing intelligent commissioning data of a high-voltage prefabricated substation according to claim 1, characterized in that: Performing secondary frequency analysis based on the data change trend to obtain the secondary data collection frequency based on the data change trend includes the following steps: Assume that the equipment operating parameters have Q equipment indicators, which are recorded as , represents the value of the qth equipment index at time t, and the environmental parameters have K environmental indicators, which are respectively , represents the value of the kth environmental indicator at time t, , ; For time interval , in the time interval Calculate the equipment operating parameter change rate of the qth equipment indicator , the environmental data change rate of the kth environmental indicator , the acceleration of device data change of the qth device indicator and the acceleration of environmental data change of the kth environmental indicator ; Determine the comprehensive change trend assessment value : ； Among them, F1 and F2 are both transit functions. is the weight of the qth device indicator, is the weight of the kth environmental indicator, for The weight of for The weight of for The weight of for The weight of Get The frequency of data collection corresponding to that stored in the database is defined as the secondary data collection frequency.

4. A method for managing intelligent commissioning data of a high-voltage prefabricated substation according to claim 1, characterized in that: Performing a three-frequency analysis based on the grid operation condition to obtain three-frequency data acquisition frequencies based on the grid operation condition includes the following steps: Get the ratio of the current grid load to the historical maximum load value ; For each node in the power grid, the difference between its injected power and outflow power is calculated, and then the difference of all nodes is normalized to obtain the node power imbalance of the entire network. ; Get the ratio of the absolute value of the difference between the current node voltage and the rated voltage to the rated voltage ; Get the absolute value of the difference between the current grid frequency and the rated frequency ; Determine the comprehensive working condition evaluation index S: ,in, for The weight factor, for The weight factor, for The weight factor, for The weight factor of Get S corresponding to the data collection frequency stored in the database, which is defined as three data collection frequencies.

5. A method for managing intelligent commissioning data of a high-voltage prefabricated substation according to claim 1, characterized in that: After data preprocessing, the collected multi-source heterogeneous data is transmitted to the remote management center and stored, including the following steps: Edge computing nodes deployed near various devices in high-voltage prefabricated substations preprocess the collected raw multi-source heterogeneous data to obtain preprocessed multi-source heterogeneous data. Preprocessing includes data cleaning and format conversion. The edge computing node transmits the pre-processed multi-source heterogeneous data to the local aggregation layer device via the industrial field bus or industrial Ethernet; The local convergence layer device aggregates and verifies the pre-processed multi-source heterogeneous data, and classifies the pre-processed original multi-source heterogeneous data according to the data type and pre-set priority to obtain the classified multi-source heterogeneous data; The local aggregation layer equipment transmits the classified multi-source heterogeneous data to the remote management center through an encrypted optical fiber network or 5G communication link; In the remote management center, the real-time data and short-term historical data in the classified multi-source heterogeneous data are stored in an in-memory database. For long-term historical data in classified multi-source heterogeneous data, a distributed file system combined with a relational database is used for storage: The classified multi-source heterogeneous data is stored in blocks according to time series, and each block of data contains multi-source heterogeneous data within a set time range; The relational database is used to store the metadata of classified multi-source heterogeneous data. The metadata includes the storage location of the data block, the data collection time range, and the device identification.

6. A method for managing intelligent commissioning data of a high-voltage prefabricated substation according to claim 1, characterized in that: Determine the substation maintenance plan based on the working conditions of the high-voltage prefabricated substation, including the following steps: Comparing the high-voltage prefabricated substation operating conditions with the high-voltage prefabricated substation set operating conditions stored in the database, and determining an initial maintenance plan set corresponding to the high-voltage prefabricated substation operating conditions; Obtain historical data of high-voltage prefabricated substation equipment, including historical operating data, basic equipment information and maintenance records; The initial maintenance plan set is screened based on historical data to obtain the final substation maintenance plan.

7. A method for managing intelligent commissioning data of a high-voltage prefabricated substation according to claim 6, characterized in that: The initial maintenance plan set is screened based on historical data to obtain the final substation maintenance plan, which includes the following steps: Obtain the historical parameter data corresponding to each initial maintenance plan in the initial maintenance plan set, including parameter historical operation data, basic information of the parameter equipment, and parameter maintenance records; Based on the Jaccard similarity function, the Jaccard similarity value between the basic information of the equipment and the basic information of each parameter equipment is determined, and the initial maintenance plan set is screened to obtain the maintenance plan set after preliminary screening; Determine the Euclidean distance value between the historical operation data and each of the preliminarily screened maintenance plans in the preliminarily screened maintenance plan set based on the Euclidean distance function, perform a secondary screening on the preliminarily screened maintenance plan set, and obtain a secondary screened maintenance plan set; Determine the cosine similarity value between the maintenance record and each secondary screening maintenance plan in the secondary screening maintenance plan set based on the cosine similarity function, perform a tertiary screening on the secondary screening maintenance plan set to obtain a tertiary screening maintenance plan set; Perform weighted summation of the remaining life of substation equipment after maintenance and the inverse of the maintenance cost stored in the database for each three-times-screened maintenance plan in the three-times-screened maintenance plan set to obtain a maintenance plan determination coefficient; The maximum value among the determination coefficients of the maintenance plans is determined, and the maintenance plan after three screenings corresponding to the maintenance plan determination coefficient corresponding to the maximum value is determined as the substation maintenance plan.

8. A high-voltage prefabricated substation intelligent commissioning data management system, used to implement the method according to any one of claims 1 to 7, characterized in that: It includes a data acquisition frequency determination module, a data storage module, a substation operating condition determination module, and a substation maintenance plan determination module, among which: The data collection frequency determination module is used to determine the data collection frequency based on the frequency multi-layer analysis method, and to collect multi-source heterogeneous data based on the determined data collection frequency. The multi-source heterogeneous data includes equipment operating parameters, environmental parameters, and equipment assets and document data. The data storage module is used to pre-process the collected multi-source heterogeneous data and transmit it to the remote management center for storage; The substation operating condition determination module is used to perform multi-source data analysis based on pre-processed multi-source heterogeneous data stored in the remote management center to determine the operating conditions of the high-voltage prefabricated substation, including equipment failure types, equipment failure development trends, and equipment failure causes; The substation maintenance plan determination module is used to determine the substation maintenance plan based on the working conditions of the high-voltage prefabricated substation.

Images