Prediction of Insulator ESDD Based on Meteorological Feature Mining and AdaBoost-MEA-ELM Model

In order to obtain the pollution condition of transmission line insulators in time, a method of insulator equivalent salt deposit density (ESDD) prediction based on meteorological data is proposed in this paper. The meteorological features that are more closely related to insulator pollution degree...

Full description

Saved in:
Bibliographic Details
Main Authors: Yaoping WANG, Te LI, Kaihua JIANG, Wenhui LI, Qiang WU, Yu WANG
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2023-09-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202303084
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850228482351562752
author Yaoping WANG
Te LI
Kaihua JIANG
Wenhui LI
Qiang WU
Yu WANG
author_facet Yaoping WANG
Te LI
Kaihua JIANG
Wenhui LI
Qiang WU
Yu WANG
author_sort Yaoping WANG
collection DOAJ
description In order to obtain the pollution condition of transmission line insulators in time, a method of insulator equivalent salt deposit density (ESDD) prediction based on meteorological data is proposed in this paper. The meteorological features that are more closely related to insulator pollution degree are mined, and the importance of each meteorological feature is evaluated by the random forest algorithm. Combined with the sequential forward search method, the optimal subset of meteorological features for ESDD prediction model could be determined. Based on the natural pollution test data of Taizhou City, the basic ESDD prediction model was established by using extreme learning machine (ELM), and its initial weights and thresholds were optimized by the mind evolution algorithm (MEA). Then the AdaBoost algorithm was applied to further improve the accuracy of the model. The results show that the average absolute error of ESDD prediction of AdaBoost-MEA-ELM model is 0.0032 mg/cm2, which is 58.97% lower than that of the original ELM model. Compared with other common models, the performance of the proposed model and the rationality of the combination of these three algorithms are verified. The variation of prediction error when training data changed was obtained by k-fold verification method, which further prove the generalization performance and stability of the model.
format Article
id doaj-art-b1f24b9c99c44acca200faac779aa997
institution OA Journals
issn 1004-9649
language zho
publishDate 2023-09-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-b1f24b9c99c44acca200faac779aa9972025-08-20T02:04:31ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492023-09-0156915716710.11930/j.issn.1004-9649.202303084zgdl-56-08-yaoPrediction of Insulator ESDD Based on Meteorological Feature Mining and AdaBoost-MEA-ELM ModelYaoping WANG0Te LI1Kaihua JIANG2Wenhui LI3Qiang WU4Yu WANG5School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaState Grid Zhejiang Electric Power Research Institute, Hangzhou 310014, ChinaState Grid Zhejiang Electric Power Research Institute, Hangzhou 310014, ChinaState Grid Taizhou Power Supply Company, Taizhou 318000, ChinaSchool of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaSchool of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaIn order to obtain the pollution condition of transmission line insulators in time, a method of insulator equivalent salt deposit density (ESDD) prediction based on meteorological data is proposed in this paper. The meteorological features that are more closely related to insulator pollution degree are mined, and the importance of each meteorological feature is evaluated by the random forest algorithm. Combined with the sequential forward search method, the optimal subset of meteorological features for ESDD prediction model could be determined. Based on the natural pollution test data of Taizhou City, the basic ESDD prediction model was established by using extreme learning machine (ELM), and its initial weights and thresholds were optimized by the mind evolution algorithm (MEA). Then the AdaBoost algorithm was applied to further improve the accuracy of the model. The results show that the average absolute error of ESDD prediction of AdaBoost-MEA-ELM model is 0.0032 mg/cm2, which is 58.97% lower than that of the original ELM model. Compared with other common models, the performance of the proposed model and the rationality of the combination of these three algorithms are verified. The variation of prediction error when training data changed was obtained by k-fold verification method, which further prove the generalization performance and stability of the model.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202303084esdd predictionmeteorological characteristicsrandom forestextreme learning machinemind evolution algorithmadaboost algorithm
spellingShingle Yaoping WANG
Te LI
Kaihua JIANG
Wenhui LI
Qiang WU
Yu WANG
Prediction of Insulator ESDD Based on Meteorological Feature Mining and AdaBoost-MEA-ELM Model
Zhongguo dianli
esdd prediction
meteorological characteristics
random forest
extreme learning machine
mind evolution algorithm
adaboost algorithm
title Prediction of Insulator ESDD Based on Meteorological Feature Mining and AdaBoost-MEA-ELM Model
title_full Prediction of Insulator ESDD Based on Meteorological Feature Mining and AdaBoost-MEA-ELM Model
title_fullStr Prediction of Insulator ESDD Based on Meteorological Feature Mining and AdaBoost-MEA-ELM Model
title_full_unstemmed Prediction of Insulator ESDD Based on Meteorological Feature Mining and AdaBoost-MEA-ELM Model
title_short Prediction of Insulator ESDD Based on Meteorological Feature Mining and AdaBoost-MEA-ELM Model
title_sort prediction of insulator esdd based on meteorological feature mining and adaboost mea elm model
topic esdd prediction
meteorological characteristics
random forest
extreme learning machine
mind evolution algorithm
adaboost algorithm
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202303084
work_keys_str_mv AT yaopingwang predictionofinsulatoresddbasedonmeteorologicalfeatureminingandadaboostmeaelmmodel
AT teli predictionofinsulatoresddbasedonmeteorologicalfeatureminingandadaboostmeaelmmodel
AT kaihuajiang predictionofinsulatoresddbasedonmeteorologicalfeatureminingandadaboostmeaelmmodel
AT wenhuili predictionofinsulatoresddbasedonmeteorologicalfeatureminingandadaboostmeaelmmodel
AT qiangwu predictionofinsulatoresddbasedonmeteorologicalfeatureminingandadaboostmeaelmmodel
AT yuwang predictionofinsulatoresddbasedonmeteorologicalfeatureminingandadaboostmeaelmmodel