Open AccessPrediction of the Optimal Umbrella Shape of Insulators Based on Data Mining Technology
Author(s) -
Xing Xiang-rong
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/692/2/022067
Subject(s) - artificial neural network , arc flash , insulator (electricity) , voltage , genetic algorithm , process (computing) , power network , computer science , engineering , data mining , electric power system , machine learning , artificial intelligence , power (physics) , electrical engineering , physics , quantum mechanics , operating system
The insulator flashover process is affected by many factors. In order to better study the factors that affect the insulator flashover voltage, and then accurately predict the insulator flashover voltage. In this paper, 11 different types of composite insulators are studied through artificial pollution tests. Data mining technology has been widely used now. In order to better apply data mining in the prediction of insulation flashover voltage, this paper adopts the BP neural network in data mining technology to predict the flashover voltage of different umbrella-shaped insulators. In addition, in order to further improve the prediction accuracy of the model, this paper uses the global search capability of genetic algorithm to optimize the initial weights and thresholds of the BP neural network, and optimizes the BP neural network prediction model, and established an optimization model based on genetic algorithm to optimize BP neural network. Through this method, the flashover voltage of the insulator can be predicted in time, which is of great significance for maintaining the safe and stable operation of the power system.