高压电器2024，Vol.60Issue(7)：163-172,190,11.DOI:10.13296/j.1001-1609.hva.2024.07.018
变压器油中乙炔门控循环单元网络多步预测超参数优化方法
Hyper-parameters Optimization Method for Multi-step Prediction of Acetylene in Power Transformer Oil by Gated Cyclic Unit Network
摘要
Abstract
Multi-step prediction of the acetylene dissolved in oil,one of the important discharge degree characteriza-tion parameters in power transformer,can provide an important basis for fault diagnosis and early warning of trans-former.The existing state prediction models mainly focus on single-step prediction and are insufficient for the predic-tion means with long time variation trend in the future.In addition,the hyper parameter selection of multi-step predic-tive model based on deep learning is mostly based on experience and the naive single control variable method,and the coupling relationship between hyper-parameters has not been fully studied.In this paper,a multi-step prediction model of gated recurrent unit(GRU)neural network based on a multi-output strategy is proposed.The coupling rela-tionship of the hyper parameters is studied by changing the structure hyper parameters and training hyper parameters of the model,and the multi-objective gray wolf optimization algorithm is used for hyper parameter optimization of GRU models with different prediction results tendency.The results show that the GRU model can accurately predict the acetylene content in transformer oil for 30 days.The influence of the hyper parameters of the GRU model on the output prediction results is not uniform and affects each other.The same set of hyper parameters cannot achieve mul-tiple goals optimization simultaneously.The multi-objective gray wolf optimization algorithm can optimize the selec-tion of suitable hyper parameters in accordance with the different prediction targets,which provides a reference for the selection of hyper parameters of artificial intelligence algorithms.关键词
变压器/乙炔/门控循环单元(GRU)/灰狼算法/多步预测Key words
transformer/acetylene/gated recurrent unit/gray wolf algorithm/multi-step prediction引用本文复制引用
赵军,高树国,何瑞东,相晨萌,芮逸凡,王亚林,尹毅..变压器油中乙炔门控循环单元网络多步预测超参数优化方法[J].高压电器,2024,60(7):163-172,190,11.基金项目
国网河北省电力有限公司科技成本项目(kjcb2020-013). Project Supported by Science and Technology Cost Project of State Grid Hebei Electric Power Co.,Ltd.(kjcb2020-013). （kjcb2020-013）
