Terminal fault diagnosis method, device and system based on neural network

Abstract

The embodiment of the present application discloses a neural network-based terminal fault intelligent diagnosis method, device and system. The method includes: judging the credibility of each maintenance experience in the special rule base, if the credibility of each maintenance experience Less than the preset confidence threshold, store each maintenance experience into the general rule base; input the neural network according to the special rule base and the general rule base, train the neural network to form a neural network model, and store the neural network model into the general rule base ; Obtain the operating state parameters of the power distribution terminal, input them into the neural network, and obtain the corresponding fault diagnosis results according to the fault diagnosis data output by the neural network. This application can train the neural network to make the neural network establish the corresponding relationship between the state parameters of the distribution network terminal and the fault type variables. When performing terminal fault diagnosis, the corresponding fault type variables can be obtained by inputting the fault state parameters into the neural network. Intelligent diagnosis of distribution network terminal faults.

Description

technical field [0001] The invention relates to the technical field of distribution automation fault discrimination and processing, in particular to a neural network-based terminal fault diagnosis method, device and system. Background technique [0002] Nowadays, in the distribution network, the internal faults of the distribution terminals cannot be reported to the operation and maintenance personnel of the automation system as soon as possible, and the equipment failures are often discovered only after the distribution terminals are completely disconnected or the equipment refuses to move. This undoubtedly reduces the reliability of distribution automation. [0003] However, the current power distribution operation and maintenance team of the power supply bureau has limited personnel and uneven technical levels. The actual operation and maintenance of power distribution terminals has certain technical difficulties, and the lack of professional technical level often causes ...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a terminal fault diagnosis method, device and system based on a neural network, which can solve the problem in the prior art that the diagnosis of distribution network distribution terminals can only be performed manually, and the efficiency is low and the effect is general. technical issues

Images