Power transmission line fault reason intelligent identification method based on relevance vector machine

Abstract

The invention relates to a power transmission line fault reason intelligent identification method based on a relevance vector machine, and belongs to the field of power fault analysis. The method comprises the steps of determining a power transmission line fault cause type, constructing a fault sample set based on historical fault recording data of a power transmission line, performing resampling to obtain a capacity expansion sample set, obtaining a sample intrinsic dimension, dividing the capacity expansion sample set into subsets, obtaining a feature subset and a new sample set, and dividing a training sample set and a test sample set. And a fault reason identification module is constructed and trained, and the fault reason identification module identifies a single fault with an unknown fault reason. The method disclosed by the invention can effectively extract and screen typical fault features of the power transmission line, overcomes the problem that the number of samples of each fault reason type is unbalanced, can provide an intelligent identification conclusion for the fault reasons of the power transmission line and the accuracy of the conclusion for engineering technicians, and has higher fault reason identification accuracy compared with other prior art.

Description

technical field [0001] The invention belongs to the field of power failure analysis, in particular to an intelligent identification method for transmission line failure causes based on a correlation vector machine. Background technique [0002] As the basic facility for interconnection and power transmission between power grids, transmission lines are an important part of "optimizing the layout of power production and transmission channels" in my country's 2035 vision. my country's transmission line channel length and crossing area are constantly extending and expanding to make it cover a wide range, and the characteristics of the complex operating environment continue to deepen. According to the statistics of the State Grid Corporation of China, from 2012 to 2016, DC transmission line failures caused a total of 42 forced outages, accounting for 36.8% of the total outage scale. As my country is making great strides towards a "strong power grid", in 2018, 2,360 faults occurr...

AI Technical Summary

Problems solved by technology

[0005] In view of the above deficiencies in the prior art, the present invention aims to propose a method for intelligent identification of fault causes of transmission lines based on correlation vector machines, so as to solve the problem that the existing fault cause identification technology cannot overcome the unbalanced sample data volume, lack of feature evaluation standards, artificial Identify defects that are costly to fail and whose reliability is compromised by multiple factors

Images