Power transmission line defect risk modeling and prediction method based on support vector machine

Abstract

The invention discloses a power transmission line defect risk modeling and prediction method based on a support vector machine, and the method comprises the steps: firstly enabling a power transmission line to be subdivided into a plurality of parts, and defining a defect risk value as an evaluation index of a line defect condition under the condition of considering the number of defects and the severity degree of the defects; secondly, screening out important factors influencing the defect risk value of each part through correlation coefficients, introducing a support vector machine machine learning method, and predicting the future defect risk value of the line by utilizing the advantage that the small sample learning problem can be effectively solved. The size of the defect risk prediction value reflects the defect condition of the power transmission line in the future, and an important reference can be provided for the work of related departments.

Description

technical field [0001] The invention relates to the field of power system analysis and control, in particular to a transmission line defect risk modeling and prediction method based on a support vector machine. Background technique [0002] Effective prediction of defect development is the basis and core of scientific inspection and maintenance of transmission lines. At present, the discovery of transmission line defects mainly depends on the alarm and regular maintenance of online monitoring equipment, and the formulation of inspection and maintenance plans often relies on human experience. This method often leads to waste of manpower, material resources and other resources and lack of targeted maintenance. happened. Therefore, how to scientifically process defect data and predict the future development of transmission line defects, so as to arrange maintenance work in a targeted manner, is an important issue facing the line management department at present. [0003] At p...

AI Technical Summary

Problems solved by technology

[0005] With the gradual improvement of the safety performance of the power grid, the incidence of hidden dangers such as defects in transmission lines is further reduced. Therefore, the statistical sample size of data such as defects in lines is relatively scarce, which brings certain difficulties to the prediction of defects in transmission lines.

Images