基于NMWOA-LSTM的卷取温度预测模型  

Prediction model of coiling temperature based on NMWOA-LSTM

作　　者：周建新 霍彤明 Zhou Jianxin;Huo Tongming(College of Electrical Engineering,North China University of Science and Technology,Tangshan 063210,China)

机构地区：[1]华北理工大学电气工程学院,唐山063210

出　　处：《电子测量技术》2023年第18期60-66,共7页Electronic Measurement Technology

基　　金：河北省自然科学基金(F2018209201)项目资助

摘　　要：由于热连轧带钢卷取温度控制过程存在强非线性和时变性等因素影响,导致卷取温度控制精度和卷取命中率低。提出一种基于改进鲸鱼算法优化长短期记忆神经网络的方法,加入自适应参数优化和混合变异策略并融合小生境技术得到小生境技术混合变异策略的改进鲸鱼优化算法,建立改进鲸鱼算法优化LSTM的卷取温度预测模型,并与其他模型进行对比。仿真实验表明,在10个测试函数中,同其他先进算法相比,NMWOA算法具有更好的搜索能力和寻优精度;在卷取温度模型预测中,NMWOA-LSTM模型同其他4种模型相比,卷取温度高精度命中率达到97.50%,提高了卷取温度的预测精度。The coiling temperature control accuracy and coiling hit rate of hot strip rolling are low due to the influence of strong nonlinearity and time variation.This paper proposes a method to optimize long short-term memory(LSTM)neural network based on improved whale algorithm.The improved Whale optimization algorithm of niche technologymixed mutation strategy(NMWOA)was obtained by combining adaptive parameter optimization and hybrid mutation strategy with niche technology.The coiling temperature prediction model of LSTM optimized by improved whale algorithm was established and compared with other models.Simulation results show that the NMWOA algorithm has better search ability and optimization accuracy among the 10 test functions compared with other advanced algorithms.In the prediction of the coiling temperature model,compared with the other four models,the NMWOA-LSTM model has a high precision hit rate of 97.50%,which improves the prediction accuracy of the coiling temperature.

关 键 词：鲸鱼优化算法 小生境技术 混合变异策略 长短期记忆神经网络 预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]