Real-time detection method for high-voltage electrical equipment based on RBF neural network and Bayesian network

Abstract

The embodiment of the invention provides a real-time detection method for high-voltage electrical equipment based on an RBF neural network and a Bayesian network. The method comprises the following steps: S1, acquiring contact temperature data of the high-voltage electrical equipment by using a temperature sensor, taking current, resistance and voltage of the high-voltage electrical equipment as to-be-diagnosed fault data, and performing normalization preprocessing; S2, performing basic probability allocation by using three RBF neural networks, and accurately classifying to-be-diagnosed faultdata; and S3, performing fault diagnosis on the high-voltage electrical equipment by using the Bayesian network. The Raman optical fiber sensor is used for measuring the temperature of the high-voltage electrical equipment; and an information fusion technology is applied to a high-voltage electrical equipment temperature monitoring and early warning system taking temperature as a main parameter and current and the like as auxiliary parameters, so that the reliability of diagnosis is effectively improved, and the uncertainty of diagnosis is reduced.

Description

technical field [0001] The invention relates to the field of on-line monitoring and fault diagnosis of power equipment in a smart grid environment, in particular to a real-time detection method for high-voltage electrical equipment based on an RBF neural network and a Bayesian network. Background technique [0002] With the rapid development of modern power systems, higher requirements are put forward for the safe, stable and reliable operation of its equipment. In enterprises such as metallurgy, chemical industry, and electric power, high-voltage electrical equipment such as high-voltage transformers, high-voltage switches, and high-voltage cable busbars are often prone to failure due to their high voltage, large load, and long running time. If a failure occurs, there will be immeasurable negative effects, which will seriously affect the production of the enterprise, and will also be accompanied by considerable economic losses. [0003] When high-voltage electrical equipme...

AI Technical Summary

Problems solved by technology

However, it is difficult to solve the problem of temperature change fault monitoring in irregular load systems, and the traditional method of detecting multi-source information is often to separately process or simply add the data generated by various sensors

First of all, this increases the workload of information processing; secondly, the collocation and combination of various sensors cannot be fully reflected in the data.

Therefore, the traditional detection method greatly wastes information resources and seriously reduces the accuracy and robustness of fault detection.

Images