摘要
针对基于物质流、能量流的能耗预测模型预测误差大和准确性低等问题,分析了有色金属冶金过程中的能耗情况,介绍了建立模型时用到的小波分析基本原理,在设计和优化小波神经网络的基础上,利用Matlab软件建立了小波神经网络能耗预测模型,对有色金属冶金过程中的能耗进行了仿真。结果表明:同基于物质流、能量流的能耗预测模型相比,基于小波神经网络的能耗预测模型只有一个预测指标存在很小误差,准确性优于物质流、能量流能耗预测模型。
Aiming at the problems of large prediction error and low accuracy of energy consumption prediction model based on material flow and energy flow,the energy consumption situation in non-ferrous metallurgy process was analyzed,and the basic principle of wavelet analysis used in establishing the model was introduced.On the basis of designing and optimizing the wavelet neural network,the wavelet was established by using the software of Matlab.Neural network energy consumption prediction model was used to simulate the energy consumption in non-ferrous metallurgical process.The results show that compared with the energy consumption prediction model based on material flow and energy flow,the energy consumption prediction model based on wavelet neural network has only one prediction index with a small error,and the accuracy is better than material flow and energy flow consumption prediction model.
作者
王焕伟
WANG Huanwei(School of Metallurgical Engineering,Anhui University of Technology,Maanshan 243002,China)
出处
《新乡学院学报》
2018年第12期50-54,共5页
Journal of Xinxiang University
关键词
有色金属冶金
小波神经网络
抗磨性能
模型设计
nonferrous metallurgy
wavelet neural network
wear resistance
model design
