基于IPSO-HP-ELM水泥磨单位电耗预测  

Prediction of Unit Power Consumption for Cement Mills Based on IPSO-HP-ELM

作　　者：郝晓辰[1] 杨旭年 李东栩 韩辉 陈白[1] 史鑫[1] 黄高璐 HAO Xiao-chen;YANG Xu-nian;LI Dong-xu;HAN Hui;CHEN Bai;SHI Xin;HUANG Gao-lu(School of Electrical Engineering,Yanshan University,Qinhuangdao 066000,China)

机构地区：[1]燕山大学电气工程学院,河北秦皇岛066000

出　　处：《控制工程》2022年第4期600-610,共11页Control Engineering of China

基　　金：国家自然科学基金资助项目(62073281);河北省自然科学基金资助项目(F2019203385);河北省重点研发计划项目(No.19211602D);河北省第二批青年拔尖人才支持项目(5042250);秦皇岛市科学技术研究与发展计划项目(201902A024)。

摘　　要：水泥磨是水泥生产中主要的耗电设备,水泥磨单位电耗的精准预测对水泥厂节能降耗至关重要,因此提出一种基于改进粒子群优化算法的高性能极限学习机(IPSO-HPELM)的水泥磨单位电耗预测方法。首先,针对水泥磨大时延、强耦合特性,通过互信息确定影响单位电耗的关键因素;其次,建立蕴含时序特征的输入层,解决水泥磨中的时变时延问题;最后,采用改进粒子群优化(IPSO)算法对高性能极限学习机(HP-ELM)模型参数进行优化,建立基于IPSO-HP-ELM的水泥磨单位电耗预测模型,并验证了预测模型的有效性。实验结果表明,所提基于IPSO-HP-ELM的水泥磨单位电耗预测模型能够有效提高水泥磨单位电耗的预测精度。Cement mill is the main power-consuming equipment in cement production.The accurate prediction of unit power consumption for cement mills is essential for energy saving and consumption reduction in cement plants.Therefore,a prediction method of unit power consumption for cement mills based on high performance extreme learning machine with improved particle swarm optimization algorithm(IPSO-HP-ELM)is proposed in this paper.Firstly,the key factors affecting unit power consumption are determined by mutual information for the large time delay and strong coupling characteristics of cement mills.Secondly,an input layer with time sequence characteristics is established to solve the time-varying and time delay problems in cement mills.Finally,an improved particle swarm optimization(IPSO)algorithm is used to optimize the parameters of the high performance extreme learning machine(HP-ELM)model and a prediction model of unit power consumption for cement mills based on IPSO-HP-ELM is established.The validity of the prediction model is verified.The experimental results show that the prediction model can effectively improve the prediction accuracy of unit power consumption of cement mills.

关 键 词：水泥磨 单位电耗预测 极限学习机 粒子群优化算法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]