Power grid geological settlement hidden danger risk prediction method based on machine learning

Abstract

The invention provides a power grid geological settlement hidden danger risk prediction method based on machine learning, and the method comprises the steps of determining a power grid geographic region, and dividing the power grid geographic region into geographic grids at preset intervals; obtaining first feature data in the sample geographic grid and performing corresponding processing; inputting the first feature data and the first prediction variable into a training model to obtain a classification prediction model of the power grid geological settlement hidden danger points; inputting the second feature data of the to-be-predicted geographic grid into the power grid geological settlement hidden danger point classification prediction model to obtain a second prediction variable; and if the second prediction variable is 1, determining that the to-be-predicted geographic grid has the power grid geological settlement hidden danger risk point. The invention can effectively solve the problem that the fixed-point monitoring period of a satellite is long, the obtained prediction result can provide auxiliary guidance for each emergency unit to deal with the geological settlement of the power grid, the hidden danger risk point of the geological settlement of the power grid can be found in time, and an emergency processing scheme can be made in advance.

Description

technical field [0001] The present application relates to the technical field of risk prediction of hidden dangers of geological subsidence in power grids, in particular to a method for predicting risks of hidden dangers of geological subsidence in power grids based on machine learning. Background technique [0002] Due to the wide distribution of equipment in the power grid, such as transmission lines and diverse geographical environments, geological subsidence disasters are a greater threat to the safe and reliable operation of power grid equipment under the influence of natural or human factors. Once substations or transmission towers in the power grid are affected by geological subsidence, serious equipment damage will be caused, resulting in huge economic and social losses. [0003] At present, the geological subsidence analysis of the power grid is mainly based on SAR satellite data for interference processing, but the processing accuracy of SAR satellite data is great...

AI Technical Summary

Problems solved by technology

[0004] This application provides a machine learning-based risk prediction method for hidden dangers of geological subsidence in power grids to solve the problems in the prior art that the hidden dangers of geological subsidence in the power grid cannot be discovered in time, which reduces the efficiency of power grid operation and maintenance personnel, and cannot Carry out the prevention and disposal of corresponding disasters in a timely manner, resulting in the problem of economic losses due to untimely investigation of hidden dangers

Images