Search

CN-121995136-A - Full-automatic equipment defect positioning system and method for hydropower station relay protection system

CN121995136ACN 121995136 ACN121995136 ACN 121995136ACN-121995136-A

Abstract

The invention discloses a full-automatic equipment defect positioning system and method of a hydropower station relay protection system, and relates to the technical field of power system automation. The system comprises a data acquisition module, a data processing module, a defect positioning module, an early warning and alarming module, a database module and a man-machine interaction module. The system comprises a data acquisition module, a data processing module, a defect positioning module, an early warning and alarming module, a database module and a database module, wherein the data acquisition module acquires equipment operation data, the data processing module preprocesses and extracts characteristics of the data, the fault range is primarily analyzed, the defect positioning module fuses fault tree analysis and accurate fault positioning of an expert system and a neural network, the early warning and alarming module performs hierarchical early warning and triggers an emergency plan, and the database module adopts a hybrid architecture to store various data. And the defect positioning is realized through the steps of data acquisition, processing, positioning, early warning and interactive display. The full-automatic rapid diagnosis, accurate positioning and effective treatment of the faults of the relay protection system are realized, the reliability and stability of the relay protection system are improved, and the method has remarkable economic and social benefits.

Inventors

  • Yue Shoujun
  • QU WEIHUA
  • YE HUASONG
  • XIE QIANG
  • SUN NA

Assignees

  • 中国长电国际(香港)有限公司

Dates

Publication Date
20260508
Application Date
20260106

Claims (20)

  1. 1. Full-automatic equipment defect positioning system of power station relay protection system, its characterized in that includes: The data acquisition module is used for acquiring the operation data of the relay protection system equipment and the key data of the power supply related equipment; The data processing module is used for preprocessing the acquired data, extracting the characteristics, constructing fault judgment logic and primarily analyzing the fault range; the defect positioning module comprises a fault tree analysis unit, an expert system unit and a neural network unit and is used for accurately positioning fault equipment; The early warning and alarming module is used for implementing grading early warning and alarming according to the fault severity degree and triggering an emergency plan; the database module is used for storing equipment operation data, historical fault data, equipment association relation data and fault processing method data; and the man-machine interaction module is used for providing parameter setting, data query, fault diagnosis results, fault processing method display and remote control operation interfaces for operation and maintenance personnel.
  2. 2. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1, wherein the data acquisition module adopts a high-precision sensor array to acquire data of a power transformer, a circuit breaker, a fuse, an electric element and equipment cabinet equipment, the acquired data is transmitted to the data processing module through an industrial Ethernet or an optical fiber, the sensor array has self-diagnosis and self-adaptive regulation functions, the working state of the sensor array can be monitored in real time, and when external interference or self-performance abnormality is detected, acquisition parameters are automatically regulated to ensure data accuracy.
  3. 3. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1, wherein the data processing module adopts a distributed computing architecture, utilizes a plurality of servers to process data in parallel, improves data processing efficiency, adopts an outlier detection algorithm based on deep learning in the data preprocessing process, accurately identifies and eliminates abnormal data, triggers an automatic checking flow by setting a threshold value when judging component faults, screens related equipment according to an equipment association relation table, extracts operation data characteristics, analyzes the operation data characteristics, and judges the equipment operation state related to the faulty equipment layer by layer.
  4. 4. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1 is characterized in that a fault tree analysis unit of the defect positioning module takes a fault phenomenon as a top event, related equipment faults are taken as an intermediate event and a bottom event, a refined fault tree model is built, positioning faults are gradually arranged and checked through top-down logic reasoning, an expert system unit converts field expert experience into a rule base, after fault data are acquired by the system, the fault range is gradually reduced through rule matching and reasoning, a neural network unit adopts a transfer learning technology to transfer model parameters trained on fault data of other similar power systems to the system, fine adjustment is carried out by combining historical fault data of the hydropower station, a high-precision fault diagnosis model suitable for the system is built, and the three are comprehensively diagnosed through an integrated decision module, so that positioning accuracy is improved.
  5. 5. The system for positioning defects of full-automatic equipment of a hydropower station relay protection system according to claim 1, wherein the early warning and alarming module has a fault trend prediction function, predicts the occurrence probability and time of a fault in advance through time sequence analysis of equipment operation data, sends early warning information in a fault germination stage, sets a grading early warning mechanism according to the severity of the fault, triggers corresponding early warning measures and starts a preset emergency plan.
  6. 6. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1, wherein the database module adopts a mixed architecture of a relational database and a non-relational database, the relational database is used for storing structured data such as equipment basic parameter data, historical fault data, defect case data and the like, the non-relational database is used for storing unstructured data such as real-time monitoring data, sensor original signals and the like, the database module is provided with a data encryption storage mechanism, sensitive information is encrypted and stored by adopting an AES256 encryption algorithm, meanwhile, a data desensitization tool is arranged, the sensitive data is desensitized when data service is provided externally, and the full-automatic backup and recovery functions of the data are provided.
  7. 7. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1, wherein the human-computer interaction module is developed based on a Web technology, a service interface is built at the rear end by adopting a Spring Boot frame, a visual interface is built at the front end by adopting a Vue.js frame, a multilingual switching function is supported, the system interface language can be switched in real time according to the setting of operation and maintenance personnel, and when a fault occurs, the position of the fault equipment, the coding of components, the analysis process of a fault tree and a corresponding fault processing method are displayed, so that the remote operation of the operation and maintenance personnel is supported.
  8. 8. The system for positioning defects of full-automatic equipment of a hydropower station relay protection system according to claim 1, wherein the system for positioning defects of the equipment further has a remote upgrading function, and continuously optimizes and updates the functions of the system by remotely downloading and installing software upgrading packages of a data acquisition module, a data processing module, a defect positioning module, an early warning and alarming module, a database module and a man-machine interaction module through a network.
  9. 9. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1, wherein the equipment defect positioning system is further provided with a safety protection module, and the system network communication and the data access are monitored and protected in real time by adopting a plurality of safety technologies such as an intrusion detection system IDS, a firewall and a safety audit, so that external illegal intrusion and data leakage are prevented.
  10. 10. The system for positioning defects of full-automatic equipment of a hydropower station relay protection system according to claim 1, wherein a message queue mechanism is adopted among the data acquisition module, the data processing module, the defect positioning module, the early warning and alarming module, the database module and the man-machine interaction module for data interaction, so that reliability and stability of data transmission are ensured, and data loss and repeated transmission are avoided.
  11. 11. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1, wherein the data acquisition card in the data acquisition module is a high-speed acquisition card with a multichannel synchronous sampling function, the sampling frequency is not lower than 10kHz, the A/D conversion precision reaches 16 bits, and the accuracy and the instantaneity of acquired data are ensured.
  12. 12. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1, wherein a TensorFlow framework is adopted by a neural network unit of the defect positioning module to build a multilayer convolutional neural network CNN model, an input layer is extracted equipment operation data characteristics, an output layer is a fault type and position prediction result, and an Adam optimizer and a cross entropy loss function are used for training the model.
  13. 13. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1, wherein the audible and visual alarm device of the early warning and alarm module is an industrial audible and visual alarm, is connected with a system server through an RS485 communication interface, is started and stopped by program control alarm, is realized by accessing an Arian cloud information service API, and sends mails by utilizing JavaMail API.
  14. 14. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1, wherein a relational database of the database module adopts MySQL, is configured into an 8-core CPU, a 32GB memory and a 1TB memory, adopts InnoDB memory engines, a non-relational database adopts MongoDB, adopts a slicing cluster architecture, deploys 3 slicing nodes, 2 configuration server nodes and2 arbitration nodes, and ensures high availability and expansibility of data storage.
  15. 15. The full-automatic equipment defect positioning system of the hydropower station relay protection system according to claim 1, wherein the man-machine interaction module uses ECharts to realize data visualization, comprises equipment operation parameter real-time curves, fault tree dynamic display, fault processing flow progress charts and the like, designs an interactive operation area, enables operation and maintenance personnel to check detailed analysis processes and processing methods by clicking fault tree nodes, adjusts equipment operation parameters by drag operation, and confirms execution of remote control instructions by popup.
  16. 16. A defect locating method of a fully automatic equipment defect locating system using the hydropower station relay protection system according to any one of claims 1 to 15, characterized by comprising the following steps: The method comprises the following steps that S1, a data acquisition module acquires operation data of relay protection system equipment and key data of power supply related equipment in real time through a high-precision sensor array and video monitoring equipment, and the acquired data is transmitted to a data processing module through an industrial Ethernet or optical fiber after A/D conversion; S2, preprocessing acquired data by a data processing module, reducing noise by using algorithms such as median filtering and Gaussian filtering, unifying data format and range by combining a normalization method, extracting data characteristics by technologies such as Fourier transform, wavelet transform and time sequence analysis, constructing fault judgment logic, screening related equipment according to an equipment association relation table, extracting operation data characteristics of the related equipment, and primarily analyzing a fault range by using a machine learning algorithm; S3, a fault tree analysis unit, an expert system unit and a neural network unit of the defect positioning module respectively process analysis results of the data processing module, the fault tree analysis unit builds a fault tree model to carry out logic reasoning, the expert system unit carries out matching reasoning on real-time data and a rule base, the neural network unit carries out prediction through a trained model, and fault equipment and fault reasons are obtained through integrated decision of the three components; s4, implementing grading early warning and alarming according to the diagnosis result of the defect positioning module by the early warning and alarming module and the fault severity, triggering a corresponding emergency plan, and updating fault state information in real time; And S5, the man-machine interaction module displays a fault positioning result, a fault reason and a corresponding fault processing method, and supports operation and maintenance personnel to perform parameter setting, data query and remote control operation.
  17. 17. The method for positioning defects of full-automatic equipment of a relay protection system of a hydropower station according to claim 16, wherein in the step S1, the data acquisition module monitors equipment related to power supply of components of the relay protection system, such as a power transformer, a circuit breaker, a fuse and the like, a 0.2S-stage voltage transformer and a 0.2-stage optical fiber current transformer are installed on the high-low voltage side of the power transformer, micro switch sensors are installed on the two ends of the circuit breaker operating mechanism and the fuse, and a high-precision video monitoring camera is installed in front of the components needing appearance monitoring.
  18. 18. The method for positioning defects of full-automatic equipment of a relay protection system of a hydropower station according to claim 16, wherein in the step S2, the machine learning algorithm comprises a random forest and a support vector machine, the data processing module sets a normal working threshold range in advance according to design parameters of components and actual operation experience when judging the failure of the components, and when the monitored data exceeds the threshold, the full-automatic failure detection process is triggered immediately.
  19. 19. The method for positioning defects of full-automatic equipment of a relay protection system of a hydropower station according to claim 16, wherein in the step S3, the integrated decision is made by adopting a weighted voting algorithm, and the final fault positioning result is obtained by integrating the fault tree analysis result, the expert system reasoning conclusion and the neural network prediction result.
  20. 20. The method for positioning defects of full-automatic equipment of a hydropower station relay protection system according to claim 16, wherein in the step S4, the hierarchical early warning mechanism comprises three-stage early warning, when the monitored data is reduced to 80% -90% of a threshold value, the first-stage early warning is triggered, prompt information and mails are sent, when the monitored data is reduced to 70% -80% of the threshold value, the second-stage early warning is triggered, audible and visual alarm prompt is increased, when the monitored data is reduced to 70% of the threshold value, the three-stage emergency warning is triggered, all emergency plans are started, and warning information is repeatedly pushed through short messages and mails.

Description

Full-automatic equipment defect positioning system and method for hydropower station relay protection system Technical Field The invention relates to the technical field of power system automation, in particular to a full-automatic equipment defect positioning system and method of a hydropower station relay protection system. Background In modern power systems, hydropower stations serve as important power supply nodes, and safe and stable operation of the hydropower stations is significant in guaranteeing reliability of a power grid. The relay protection system is used as a 'safety guard' of hydropower station power equipment and bears the key task of rapidly acting and isolating a fault area when the equipment is abnormal or fails. However, as the scale of hydropower stations is continuously enlarged and the complexity of equipment is continuously improved, the fault risk of equipment of a relay protection system is also increased. Currently, the defect detection and positioning means of hydropower station relay protection equipment mainly depend on manual inspection and traditional monitoring technologies. The manual inspection mode is limited by the professional level, working experience and working state of inspection personnel, and the problems of low efficiency, high omission factor, untimely fault positioning and the like exist, so that the operation and maintenance requirements of the power system with extremely high real-time requirements are difficult to meet. The traditional monitoring technology is mostly based on single parameter threshold judgment, lacks comprehensive analysis and deep mining on the running state of equipment, cannot effectively identify potential fault hidden dangers, and is difficult to quickly and accurately locate the fault source when facing complex fault scenes. In addition, in the fault processing flow in the prior art, from fault discovery to positioning to processing, all links are loosely connected, and an automatic and intelligent linkage mechanism is lacked, so that the fault processing period is long, the cascading reaction of a power system is easy to cause, and a larger range of power failure accidents and economic losses are caused. Therefore, developing a set of system capable of realizing full-automatic, rapid and accurate fault diagnosis and positioning and providing an effective treatment scheme becomes an urgent need for improving the reliability and stability of the relay protection system of the hydropower station. Disclosure of Invention The invention aims to provide a full-automatic equipment defect positioning system and method of a hydropower station relay protection system, and aims to realize full-automatic, rapid and accurate fault cause judgment when the relay protection system fails, accurately position specific fault equipment, timely send out relevant information, and simultaneously provide a scientific and reasonable fault processing method, so that the problems of low equipment defect detection and positioning efficiency, poor accuracy and untimely processing in the prior art are thoroughly solved. In order to solve the technical problems, the invention adopts the following technical scheme: Full-automatic equipment defect positioning system of power station relay protection system includes: The data acquisition module is used for acquiring the operation data of the relay protection system equipment and the key data of the power supply related equipment; The data processing module is used for preprocessing the acquired data, extracting the characteristics, constructing fault judgment logic and primarily analyzing the fault range; the defect positioning module comprises a fault tree analysis unit, an expert system unit and a neural network unit and is used for accurately positioning fault equipment; The early warning and alarming module is used for implementing grading early warning and alarming according to the fault severity degree and triggering an emergency plan; the database module is used for storing equipment operation data, historical fault data, equipment association relation data and fault processing method data; and the man-machine interaction module is used for providing parameter setting, data query, fault diagnosis results, fault processing method display and remote control operation interfaces for operation and maintenance personnel. The data acquisition module adopts the high-precision sensor array to perform key data acquisition on equipment such as a power transformer, a circuit breaker, a fuse, an electric element, an equipment cabinet and the like, acquired data is transmitted to the data processing module through an industrial Ethernet or an optical fiber, the sensor array has self-diagnosis and self-adaptive adjustment functions, the working state of the sensor array can be monitored in real time, and when external interference or self-performance abnormality is detected, acquisition parameters are automatically adjusted