Phase modifier insulation fault prediction method and system

Abstract

The invention provides a phase modifier insulation fault prediction method and system. The method comprises the steps of firstly obtaining electrical aging data, thermal aging data, mechanical aging data and environmental aging data of a diagnosed phase modifier insulation; then performing data preprocessing to eliminate obvious singular points in the data; determining a learning sample set and structural parameters of a neural network; and then starting wavelet neural network modeling and performing network training until a wavelet neural network with a determined structure and weight is obtained. According to the method and the system, for the problem of difficult phase modifier insulation maintenance, insulation state diagnosis analysis of a phase modifier can be performed by integrating phase modifier insulation electrical aging, thermal aging, mechanical aging and environmental aging parameters, so that the phase modifier insulation fault trend prediction efficiency is greatly improved, a guarantee is provided for safe and reliable operation of the phase modifier, the phase modifier insulation operation and maintenance cost is reduced, and the feasibility is provided for intelligent health management of the phase modifier.

Description

technical field [0001] The invention belongs to the technical field of motor insulation diagnosis, and in particular relates to a method and system for predicting an insulation fault of a condenser. Background technique [0002] With the continuous increase of DC transmission scale, the problem of power quality becomes more prominent, and the demand for reactive power in the grid system is increasing day by day. As a dedicated reactive power compensation source, the synchronous condenser has the advantages of continuous control of the output reactive power, flexible adjustment, high precision, and zero-difference adjustment. [0003] A synchronous condenser is a synchronous motor with no mechanical load and under special working conditions. By changing the magnitude of its excitation current, it can be controlled whether it absorbs reactive power from the power system or outputs reactive power. Under the condition of no compensation, the rotor excitation winding current is ...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention: Aiming at the above-mentioned problems in the prior art, a method and system for predicting the insulation failure of the condenser are provided. The present invention aims at the problem of difficult maintenance of the insulation of the condenser, and can comprehensively integrate the insulation electrical aging, thermal aging, The mechanical aging and environmental aging parameters are used to diagnose and analyze the insulation state of the condenser, which has the advantages of an accurate and comprehensive diagnostic structure, and can monitor the insulation state of the condenser in time and predict failures, so that corresponding measures can be taken

Images