Fault recording multistage information fusion method

Abstract

The invention relates to the technical field of information fusion, and discloses a fault recording multistage information fusion method, which comprises the following steps of collecting data including fault recording, geographic information, meteorological information and the like from multiple sources, and performing preprocessing such as decomposition, cleaning, alignment and the like. According to the fault recording multi-level information fusion method, in order to enable the device to further improve the stability and accuracy of the whole fault recording multi-level information fusion system, a data acquisition and storage module is arranged, and a data acquisition and processing unit and a data storage management unit cooperatively operate, so that the fault recording multi-level information fusion system is more stable and reliable. Therefore, the effect of providing a high-quality data footstone for fault recording multi-level information fusion is achieved, the data acquisition and processing unit widely collects data from multiple sources, covers fault recording, geographic information, meteorological information and the like, pretreatments such as decomposition, key feature extraction, cleaning and the like are carried out on the data, and the data purity and availability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of information fusion, and particularly to a multi-level information fusion method for fault recording. Background Technique

[0002] The multi-level information fusion method for fault recording is an advanced power system fault diagnosis technology, and its core function is to achieve a comprehensive and accurate diagnosis of power system faults by fusing data from multiple information sources.

[0003] The working process of the multi-level information fusion method for fault recording includes steps such as multi-source fault information collection, information preprocessing, feature extraction, information fusion, and fault diagnosis. Its structure is usually composed of a fault recording device, a data switch, a protection information substation, a protection information server, and a protection information workstation, etc. This method captures electrical quantity information such as current and voltage before and after the fault occurs in real time, extracts fault feature quantities by using multi-level information processing technology, and realizes information fusion and fault diagnosis through algorithms such as Bayesian.

[0004] Most of the current systems on the market are poor in the stability and accuracy of the entire multi-level information fusion system for fault recording, and the fault handling efficiency and accuracy are relatively low. In view of this, we propose a multi-level information fusion method for fault recording. Summary of the Invention

[0005] The purpose of the present invention is to provide a multi-level information fusion method for fault recording to solve the problems raised in the above background technique.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A multi-level information fusion method for fault recording includes the following steps:

[0008] S1. Collect data including fault recording, geographical information, meteorological information, etc. from multiple sources, and perform preprocessing such as decomposition, cleaning, and alignment to significantly improve the data quality and lay a solid foundation for subsequent information processing and fault analysis;

[0009] S2. Design and implement an efficient storage strategy to ensure data security, fast access and backup recovery, and at the same time strengthen data security management to ensure data integrity and availability, providing reliable data support for the stable operation of the entire system;

[0010] S3. Construct a fusion model to integrate multi-source data, use substation domain and power grid wide-area information to finely correct the original data, improve data accuracy and integrity, enhance the comprehensive value of the data, and provide comprehensive support for subsequent processing;

[0011] S4. Comprehensively verify the fused data. By comparing actual cases with theoretical models, ensure the accuracy and consistency of the data, conduct verification and analysis of the data, improve data reliability, and provide strong guarantee for fault identification and early warning.

[0012] S5. Deeply analyze the power grid fault waveforms and historical fault causes. For typical fault scenarios, accurately extract key features such as AC quantities, and provide rich, accurate and targeted data support for the fault identification algorithm.

[0013] S6. Develop a fast and accurate identification algorithm based on multi-source data fusion, establish and maintain a feature database containing various fault characteristic values, continuously optimize the algorithm performance, improve the identification efficiency, and provide strong technical support for fault early warning.

[0014] S7. Real-time monitor the power grid status, use advanced algorithms to timely warn of potential faults, provide scientific and timely decision-making suggestions for maintenance personnel, ensure the safe and stable operation of the power grid, and improve the efficiency and accuracy of fault handling.

[0015] Preferably, the multi-level information fusion method for fault recording: The multi-level information fusion method for fault recording includes:

[0016] Data acquisition and storage module: The data acquisition and storage module is responsible for obtaining data from multiple sources, including fault recording, geographical information, meteorological information, etc., and performing data preprocessing, such as decomposition, extraction of key information, alignment and sorting, etc. At the same time, this module designs an efficient data storage scheme to ensure the safe and fast access of data, and provides a solid data foundation for subsequent information processing and fault analysis, including a data acquisition and processing unit and a data storage and management unit.

[0017] Information fusion and verification module: The information fusion and verification module is responsible for integrating multi-source data, constructing an information fusion model to improve data quality. This module also uses other information sources to correct fault data to ensure data accuracy. Finally, through data verification and validation, ensure that the fused data is consistent and reliable, and provide strong support for subsequent fault identification, including a data information fusion unit, an information correction and improvement unit, and a data verification and validation unit.

[0018] Fault identification and decision-making module: The fault identification and decision-making module analyzes the preprocessed data, extracts fault features, and uses advanced algorithms to quickly and accurately identify faults. This module can timely warn of potential faults and provide decision-making support to help maintenance personnel take effective measures in a timely manner to ensure the safe and stable operation of the power grid, including a fault feature extraction unit, a fault identification unit, and a fault early warning unit.

[0019] Preferably, the data acquisition and processing unit in the data acquisition and storage module is responsible for collecting data from multiple sources such as fault recording devices and geographic information systems, including AC quantities, equipment status and other information. This unit preprocesses the data, such as decomposition, extraction of key features, cleaning, etc., to remove noise and improve data quality, laying a solid foundation for subsequent information processing and fault analysis.

[0020] Preferably, the data storage and management unit in the data acquisition and storage module focuses on designing and implementing an efficient data storage strategy to ensure the safe and rapid access of massive data. This unit is also responsible for data backup, recovery and security management to ensure data integrity and availability, providing reliable data support for the stable operation of the entire system.

[0021] Preferably, the data information fusion unit in the information fusion and verification module is responsible for constructing mathematical and information models suitable for multi-source data fusion. By integrating information from different data sources, it realizes the deep integration and optimization of data, improves the comprehensive value of data, and provides comprehensive and accurate data support for subsequent information processing and decision-making analysis.

[0022] Preferably, the information correction and improvement unit in the information fusion and verification module is committed to finely correcting the original data using multi-source information, including using substation area information and power grid wide-area information, to improve the accuracy and integrity of the data. This unit ensures data quality by optimizing the data processing process, providing a solid data foundation for fault identification and early warning. Error matrix calculation: v = A - B×x, where v is the error matrix, A is the initial matrix, B is the coefficient matrix, and x is the known quantity. This formula is used to calculate the error in the fusion process and is related to the information fusion and correction unit. Variance matrix calculation: F = ∑i = 1nvi2, where F is the variance matrix and vi is the element in the error matrix v. This formula is used to evaluate the accuracy of the fusion result and is related to the information fusion and correction unit.

[0023] Preferably, the data verification and validation unit in the information fusion and verification module is responsible for comprehensively verifying the fused data. By comparing actual fault cases with theoretical models, it ensures the accuracy and consistency of the data. This unit also conducts verification analysis of the data to improve data reliability, providing a strong guarantee for fault identification and early warning and ensuring the safe and stable operation of the power grid.

[0024] Preferably, the fault feature extraction unit in the fault identification and decision-making module focuses on in-depth analysis of power grid fault waveforms and historical fault causes. For typical fault scenarios, it accurately extracts key features such as AC quantities. This unit provides rich feature data for fault identification algorithms and is an important foundation for building an efficient fault identification system.

[0025] Preferably, the fault identification unit in the fault identification decision module is responsible for researching and developing a fast and accurate fault identification algorithm based on multi-source data fusion, and at the same time establishing and maintaining a feature database containing characteristic values of various types of faults. This unit provides strong technical support for fault warning and decision support, ensuring that power grid faults can be identified in a timely and accurate manner.

[0026] Preferably, the fault warning unit in the fault identification decision module is based on advanced fault identification algorithms and a rich feature database, which can monitor the power grid status in real time, timely warn of potential faults, and provide scientific decision-making suggestions for operation and maintenance personnel. This unit is a key link in ensuring the safe and stable operation of the power grid, and effectively improves the efficiency and accuracy of fault handling.

[0027] Compared with the prior art, the present invention provides a multi-level information fusion method for fault recording, which has the following beneficial effects:

[0028] 1. In order to further improve the stability and accuracy of the entire fault recording multi-level information fusion system, the fault recording multi-level information fusion method is equipped with a data acquisition and storage module. Through the coordinated operation of the data acquisition and processing unit and the data storage management unit, the effect of providing a high-quality data foundation for the fault recording multi-level information fusion is achieved. The data acquisition and processing unit collects data from multiple sources, covering fault recordings, geographic information, meteorological information, etc., and performs pre-processing such as decomposition, extraction of key features and cleaning to improve data purity and availability.

[0029] 2. In order to enable the device to further maintain the safe and stable operation of the power grid, the multi-level information fusion method of the fault recording is equipped with an information fusion and verification module. It relies on the close cooperation of the data information fusion unit, the information correction and improvement unit and the data verification and validation unit. The data information fusion unit constructs a sophisticated mathematical and information model, deeply integrates information from different data sources, and lays a solid foundation for comprehensive information processing and accurate decision-making analysis. The information correction and improvement unit cleverly utilizes the substation area and the power grid wide area information to significantly improve the data accuracy and integrity, and create a solid data support for fault identification and early warning.

[0030] 3. The multi-level information fusion method of the fault recording is designed to further improve the efficiency and accuracy of fault handling of the device. By setting up a fault identification and decision-making module, the goal of efficient fault identification and timely warning decision-making is achieved through the coordinated cooperation of the fault feature extraction unit, the fault identification unit and the fault warning unit. The fault feature extraction unit deeply analyzes the grid fault waveform and the causes of historical faults, and accurately extracts key features such as AC quantity for typical fault scenarios. The fault identification unit fully develops a fast and accurate fault identification algorithm based on multi-source data fusion, providing a strong technical support for fault warning and decision support. Brief Description of the Drawings

[0031] Figure 1 Schematic diagram of a multi - level information fusion method for fault recording of the whole invention;

[0032] Figure 2 Schematic diagram of the data acquisition and storage module of the present invention;

[0033] Figure 3 Schematic diagram of the information fusion and verification module of the present invention;

[0034] Figure 4 Schematic diagram of the fault identification and decision - making module of the present invention;

[0035] Figure 5 Flowchart of the method of the present invention;

[0036] Figure 6 Schematic diagram of the step - by - step process of the present invention. Detailed Description of the Invention

[0037] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0038] Please refer to Figures 1-6 , the present invention provides a technical solution: a multi - level information fusion method for fault recording, including the following steps:

[0039] S1. The data acquisition and processing unit in the data acquisition and storage module collects data from multiple sources such as fault recording devices and geographic information systems, including AC quantities, equipment status, geographic information, meteorological information, etc. This unit pre - processes the data, such as decomposition, extraction of key features, cleaning, etc., to remove noise and improve data quality, laying a solid foundation for subsequent information processing and fault analysis;

[0040] S2. The data storage and management unit in the data acquisition and storage module designs and implements an efficient data storage strategy to ensure that massive data can be stored and retrieved safely and quickly. This unit is also responsible for data backup, recovery, and security management to ensure data integrity and availability, providing reliable data support for the stable operation of the entire system;

[0041] S3. The data information fusion unit in the information fusion verification module constructs mathematical and information models suitable for multi-source data fusion. By integrating information from different data sources, it realizes the deep integration and optimization of data, enhances the comprehensive value of data. At the same time, the information correction and improvement unit uses multi-source information to finely correct the original data, including using substation area information and power grid wide-area information, to improve the accuracy and integrity of the data;

[0042] S4. The data verification and validation unit in the information fusion verification module comprehensively verifies the fused data. By comparing actual fault cases with theoretical models, it ensures the accuracy and consistency of the data. This unit also conducts verification and analysis of the data to enhance the reliability of the data, providing strong support for fault identification and early warning;

[0043] S5. The fault feature extraction unit in the fault identification and decision-making module deeply analyzes the power grid fault waveforms and historical fault causes. For typical fault scenarios, it accurately extracts key features such as AC quantities. These feature data provide rich inputs for fault identification algorithms and are an important basis for building an efficient fault identification system;

[0044] S6. The fault identification unit in the fault identification and decision-making module researches and develops a fast and accurate fault identification algorithm based on multi-source data fusion. At the same time, it establishes and maintains a feature database containing various fault feature values. This unit uses the algorithm and the feature database to identify faults in the preprocessed data, providing strong technical support for fault early warning and decision-making support;

[0045] S7. The fault early warning unit in the fault identification and decision-making module, based on advanced fault identification algorithms and a rich feature database, real-time monitors the power grid status and timely warns of potential faults. This unit also provides scientific decision-making suggestions for maintenance personnel to help them take effective measures in a timely manner to ensure the safe and stable operation of the power grid. This step is a key link in ensuring the safe and stable operation of the power grid, effectively improving the efficiency and accuracy of fault handling.

[0046] In an embodiment of the present invention, the data acquisition and storage module: The data acquisition and storage module is responsible for obtaining data from multiple sources, including fault recording, geographic information, meteorological information, etc., and performing data preprocessing, such as decomposition, extraction of key information, alignment and collation, etc. At the same time, this module designs an efficient data storage scheme to ensure the safe, fast access of data, providing a solid data foundation for subsequent information processing and fault analysis. It includes a data acquisition and processing unit and a data storage management unit. The data acquisition and processing unit in the data acquisition and storage module is responsible for collecting data from multiple sources such as fault recording devices and geographic information systems, including information such as AC quantities and equipment status. This unit preprocesses the data, such as decomposition, extraction of key features, cleaning, etc., to remove noise and improve data quality, laying a solid foundation for subsequent information processing and fault analysis. The data storage management unit in the data acquisition and storage module focuses on designing and implementing an efficient data storage strategy to ensure the safe and fast access of massive data. This unit is also responsible for data backup, recovery, and security management to ensure the integrity and availability of data, providing reliable data support for the stable operation of the entire system.

[0047] In an embodiment of the present invention, the information fusion verification module: The information fusion verification module is responsible for integrating multi-source data, constructing an information fusion model to improve data quality. This module also uses other information sources to correct fault data to ensure data accuracy. Finally, through data verification and validation, it ensures that the fused data is consistent and reliable, providing strong support for subsequent fault identification. It includes a data information fusion unit, an information correction and improvement unit, and a data verification and validation unit. The data information fusion unit in the information fusion verification module is responsible for constructing mathematical and information models suitable for multi-source data fusion. By integrating information from different data sources, it realizes the deep integration and optimization of data, improves the comprehensive value of data, and provides comprehensive and accurate data support for subsequent information processing and decision-making analysis. The information correction and improvement unit in the information fusion verification module is dedicated to finely correcting the original data using multi-source information, including using substation domain information and power grid wide-area information, to improve data accuracy and integrity. This unit ensures data quality by optimizing the data processing flow, providing a solid data foundation for fault identification and early warning. Error matrix calculation: v = A - B × x, where v is the error matrix, A is the initial matrix, B is the coefficient matrix, and x is the known quantity. This formula is used to calculate the error in the fusion process and is related to the information fusion and correction unit. Variance matrix calculation: F = ∑i = 1nvi2, where F is the variance matrix and vi is the element in the error matrix v. This formula is used to evaluate the accuracy of the fusion result and is related to the information fusion and correction unit. The data verification and validation unit in the information fusion verification module is responsible for comprehensively verifying the fused data. By comparing actual fault cases with the theoretical model, it ensures data accuracy and consistency. This unit also conducts verification analysis of the data to improve data reliability, providing strong guarantee for fault identification and early warning, and ensuring the safe and stable operation of the power grid.

[0048] In an embodiment of the present invention, there is a fault identification and decision-making module. The fault identification and decision-making module analyzes the preprocessed data, extracts fault features, and uses advanced algorithms to quickly and accurately identify faults. This module can provide real-time early warnings for potential faults and offer decision-making support to help operation and maintenance personnel take effective measures in a timely manner to ensure the safe and stable operation of the power grid. It includes a fault feature extraction unit, a fault identification unit, and a fault early warning unit. The fault feature extraction unit in the fault identification and decision-making module focuses on deeply analyzing the power grid fault waveforms and historical fault causes, and accurately extracts key features such as AC quantities for typical fault scenarios. This unit provides rich feature data for the fault identification algorithm and is an important foundation for building an efficient fault identification system. The fault identification unit in the fault identification and decision-making module is responsible for researching and developing a fast and accurate fault identification algorithm based on multi-source data fusion, and at the same time establishing and maintaining a feature database containing various fault feature values. This unit provides strong technical support for fault early warning and decision-making support to ensure that power grid faults can be identified in a timely and accurate manner. The fault early warning unit in the fault identification and decision-making module, based on advanced fault identification algorithms and a rich feature database, can monitor the power grid status in real time, timely warn of potential faults, and provide scientific decision-making suggestions for operation and maintenance personnel. This unit is a key link in ensuring the safe and stable operation of the power grid, effectively improving the efficiency and accuracy of fault handling.

[0049] The above has generally described the present invention in detail. However, based on the present invention, some modifications or improvements can be made, which are obvious to those of ordinary skill in the technical field. Therefore, modifications or improvements made without departing from the spirit and concept of the present invention are within the protection scope of the present invention.

Claims

1. A multi-level information fusion method for fault recording, characterized in that It includes the following steps: S1. Collect data from multiple sources, including fault recording, geographical information, etc., and perform preprocessing such as decomposition and cleaning to significantly improve data quality; S2. Design and implement an efficient storage strategy to ensure data security, fast access, backup and recovery, and guarantee data integrity and availability; S3. Build a fusion model to integrate multi-source data, and use substation area and power grid wide-area information to finely correct the original data to improve data accuracy; S4. Comprehensively verify the fused data. By comparing actual cases and theoretical models, ensure data accuracy and consistency, and further improve data reliability; S5. Deeply analyze power grid fault waveforms and historical causes, accurately extract key features such as AC quantities, and provide rich data support for fault identification algorithms; S6. Develop a fast and accurate identification algorithm based on multi-source data fusion, establish and maintain a feature database, and provide strong support for fault warning; S7. Real-time monitor the power grid status, use advanced algorithms to timely warn of potential faults, and provide scientific and timely decision-making suggestions for operation and maintenance personnel.

2. The fault recording multi-level information fusion method according to claim 1, wherein Through a fault recording multi-level information fusion method as described in claim 1: The fault recording multi-level information fusion method includes: Data acquisition and storage module: The data acquisition and storage module is responsible for obtaining data from multiple sources, including fault recording, geographical information, meteorological information, etc., and performing data preprocessing, such as decomposition, extraction of key information, alignment and sorting, etc. At the same time, this module designs an efficient data storage scheme to ensure the security and fast access of data, and provides a solid data foundation for subsequent information processing and fault analysis, including a data acquisition and processing unit and a data storage management unit; Information fusion and verification module: The information fusion and verification module is responsible for integrating multi-source data, building an information fusion model to improve data quality. This module also uses other information sources to correct fault data to ensure data accuracy. Finally, through data verification and validation, ensure that the fused data is consistent and reliable, and provide strong support for subsequent fault identification, including a data information fusion unit, an information correction and improvement unit, and a data verification and validation unit; Fault identification and decision-making module: The fault identification and decision-making module analyzes the preprocessed data, extracts fault features, and uses advanced algorithms to quickly and accurately identify faults. This module can real-time warn of potential faults and provide decision-making support to help operation and maintenance personnel take effective measures in a timely manner to ensure the safe and stable operation of the power grid. It includes a fault feature extraction unit, a fault identification unit, and a fault warning unit.

3. A multi-level information fusion method for fault recording according to claim 2, characterized in that: The data acquisition and processing unit in the data acquisition and storage module is responsible for collecting data from multiple sources such as fault recording devices and geographical information systems, including information such as AC quantities and equipment status, and this unit preprocesses the data.

4. A fault recording multi - level information fusion method according to claim 2, characterized in that: The data storage management unit in the data acquisition and storage module focuses on designing and implementing an efficient data storage strategy to ensure the safe and fast access of massive data.

5. A multi-level information fusion method for fault recording according to claim 2, characterized in that: The data information fusion unit in the information fusion verification module is responsible for constructing mathematical and information models suitable for multi-source data fusion. By integrating information from different data sources, it realizes the deep integration and optimization of data, enhances the comprehensive value of data, and provides comprehensive and accurate data support for subsequent information processing and decision-making analysis.

6. A fault recording multi-level information fusion method according to claim 2, characterized in that: The information correction and improvement unit in the information fusion verification module is committed to finely correcting the original data using multi-source information, including using substation area information and power grid wide-area information, to improve the accuracy and integrity of the data. Error matrix calculation: v = A - B × x, where v is the error matrix, A is the initial matrix, B is the coefficient matrix, and x is the known quantity. This formula is used to calculate the error during the fusion process and is related to the information fusion and correction unit. Variance matrix calculation: F = ∑i = 1nvi2, where F is the variance matrix and vi is the element in the error matrix v. This formula is used to evaluate the accuracy of the fusion result and is related to the information fusion and correction unit.

7. A fault recording multi - level information fusion method according to claim 2, characterized in that: The data verification and validation unit in the information fusion verification module is responsible for comprehensively verifying the fused data. By comparing actual fault cases with the theoretical model, it ensures the accuracy and consistency of the data.

8. A multi - level information fusion method for fault recording according to claim 2, characterized in that: The fault feature extraction unit in the fault identification and decision-making module focuses on deeply analyzing the power grid fault waveforms and historical fault causes, and accurately extracts key features such as AC quantities for typical fault scenarios.

9. A fault recording multi-level information fusion method according to claim 2, characterized in that: The fault identification unit in the fault identification and decision-making module is responsible for researching and developing a fast and accurate fault identification algorithm based on multi-source data fusion, and simultaneously establishing and maintaining a feature database containing various fault characteristic values.

10. A fault recording multi - level information fusion method according to claim 2, characterized in that: Based on advanced fault identification algorithms and a rich feature database, the fault warning unit in the fault identification and decision-making module can monitor the power grid status in real time, timely warn of potential faults, and provide scientific decision-making suggestions for maintenance personnel.

Images