LS_SVM and PCA-based overhead power transmission line risk assessment method

Abstract

The present invention relates to the power equipment technology, and particularly relates to an LS_SVM and PCA-based overhead power transmission line risk assessment method. The method comprises the steps of 1, extracting the statistic features of all technical factors, performing the data pre-processing operation; 2, subjecting the processed statistic features to dimension-reduction treatment through the principal component analysis, and selecting n critical statistic features; 3, adopting one part of samples containing n critical statistic features as training data to be input into LS_SVM for training purpose, then constructing a classifier and establishing an LS_SVM model for the overall risk assessment of the operation environment of an overhead transmission line; adopting the rest samples containing n critical statistic features as test data for testing purpose, comparing the test data with an original evaluation result and obtaining a prediction accuracy; 4, inputting newly obtained overhead transmission line statistic features input the risk assessment LS_SVM model established in the step 3, and obtaining a new level for evaluating the risk state of the overhead power transmission line. In this way, the risk assessment method for the operation environment of the overhead transmission line is simplified, and both the difficulty and the complexity are reduced.

Description

technical field [0001] The invention belongs to the technical field of electric power equipment, and in particular relates to an overhead transmission line risk assessment method based on LS_SVM and PCA. Background technique [0002] Due to the wide distribution of transmission lines and the complex operating environment, it is difficult to collect characteristic parameter information of technical factors, and the workload is huge. The scheme of risk assessment of transmission lines using the national grid rules is also relatively cumbersome. When natural disasters occur, there is a great correlation between technical factors. For example, under ice and snow disasters, the impacts of dance, ice disaster and ice damage on the line are superimposed on each other. In order to avoid double calculation of the impact of relevant technical factors on the line, simplify the risk assessment of the line, and reduce the workload of data collection, it is necessary to select key technic...

AI Technical Summary

Problems solved by technology

[0003] In the overall risk assessment process of the operating environment, too many features need to be assessed and collected, which will increase the difficulty and complexity of the analysis problem

Images