Power distribution equipment defect automatic discrimination method and system based on deep learning

Abstract

The invention relates to a power distribution equipment defect automatic discrimination method and system based on deep learning. The power distribution equipment defect automatic discrimination method comprises the steps: collecting an inspection data set, and obtaining a defect information set corresponding to a manual discrimination inspection data set; constructing a neural network deep learning model based on the operation and maintenance specification data; training the neural network deep learning model by using the inspection data set and the defect information set to obtain a final neural network deep learning model; and performing defect discrimination on the inspection data to be discriminated based on the final neural network deep learning model to obtain defect information. According to the power distribution equipment defect automatic discrimination method, defect discrimination is carried out on inspection data to be discriminated by a neural network deep learning model;the problem that errors are prone to occurring due to the fact that workers conduct manual judgment can be avoided; the types and the grades of the defects can be automatically judged to belong to general exceptions, serious exceptions, crisis exceptions and the like; and meanwhile the operation and maintenance work quality can be effectively improved.

Description

technical field [0001] The invention relates to the field of intelligent substation operation and maintenance detection, in particular to a method and system for automatically identifying defects of power distribution equipment based on deep learning. Background technique [0002] In recent years, with the continuous acceleration of power grid construction, the number of power distribution equipment has increased rapidly, with various types and frequent updates. Operation and maintenance management. However, although the operation and maintenance period of power distribution equipment in my country is relatively short and the coverage is wide, the operation and maintenance efficiency is low, and it has not played a good role in preventing and discovering fault defects, wasting a lot of manpower and material resources, and grounding and short-circuit faults often occur , the failure rate remains high, causing large-scale power outages; at the same time, the quality of data en...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a method and system for automatic identification of defects in power distribution equipment based on deep learning, which can avoid problems that are prone to errors caused by manual identification by staff, and can effectively improve the quality of operation and maintenance work

Images