Contact life evaluation system and method based on multi-source data and neural network

Abstract

The invention provides a contact life evaluation system and method based on multi-source data and a neural network. The contact life evaluation system comprises a multi-source data acquisition module,a multi-source data processing module, a feature value extraction module and a learning evaluation module, Wherein the multi-source data acquisition module acquires contact parameters in a switching-off process, and outputting feature values to the learning evaluation module after the contact parameters are processed by the multi-source data processing module and extracted by the feature value extraction module; the learning evaluation module enables the feature values to form a data set and trains a neural network; and inputting the feature value of a to-be-tested circuit breaker contact into the trained neural network, and outputting the residual life of the to-be-tested circuit breaker contact by using the neural network. According to the contact life evaluation system and the method,the feature values of the contact are comprehensively processed and analyzed to obtain a huge data set; the neural network is trained by using the data set, and the residual life of the contact evaluated by using the trained neural network; and the contact life evaluation system and the method integrate multi-source data, and are rich in data set, rigorous in evaluation rule and visual and accurate in result.

Description

technical field [0001] The invention relates to the technical field of high-voltage circuit breaker testing, and more specifically, to a contact life evaluation system and method based on multi-source data and neural networks. Background technique [0002] High-voltage circuit breaker is an extremely important part in the power system. It has the advantages of strong breaking capacity, fast action, and small size. It is often used in the field of reactive power compensation in power systems. When the circuit breaker is opened, the arcing contact is connected before the main contact, and a pre-breakdown arc is generated, which causes material loss on the end surface of the arcing contact; when the circuit breaker is closed, the high-temperature static arcing contact is inserted after arc ablation The moving arc contact will cause mechanical wear and material loss; due to the frequent switching of the capacitor bank for reactive power compensation, the closing inrush current d...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a contact life evaluation system and method based on multi-source data and neural network in order to overcome the single defect of the prior art for evaluating the life of contacts

Images