基于自编码-反向传播神经网络的LF钢水硫含量预测  

Autoencoder-back propagation neural network based sulfur content prediction of liquid steel in LF

作　　者：马亮[1,2] 王梦伟[1,2] 彭开香 MA Liang;WANG Mengwei;PENG Kaixiang(School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China;Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education,Beijing 100083,China)

机构地区：[1]北京科技大学自动化学院,北京100083 [2]工业过程知识自动化教育部重点实验室,北京100083

出　　处：《冶金自动化》2023年第6期15-20,共6页Metallurgical Industry Automation

基　　金：国家重点研发计划项目(2021YFB3301200);国家自然科学基金项目(62003030,U21A20112,U21A20483)。

摘　　要：钢包精炼炉(ladle furnace,LF)钢水硫含量预测对于精炼成品钢水成分的精准控制和产品质量的提升具有重要意义。针对LF机理复杂、多变量、非线性等特点,提出了一种基于自编码-反向传播神经网络(autoencoder-back propagation neural network,AE-BPNN)的LF钢水硫含量预测方法。首先,通过AE网络对数据降维和特征提取,消除噪声和缺失值的影响;然后,利用BPNN预测钢水硫含量。通过现场实际数据验证表明,所提出方法的均方根误差ERMS(root mean square error,RMSE)达1.403,平均绝对误差EMA(mean absolute error,MAE)达1.083,相关系数R2达0.824,具有良好的预测性能。The prediction of sulfur content of liquid steel in ladle furnace(LF)is of great signifi-cance for the precise control of the composition of refined molten steel and the improvement of prod-uct quality.In view of the complex mechanism,multi-variable,and nonlinear characteristics of LF,a prediction method of sulfur content in LF was proposed based on autoencoder-back propagation neural network(AE-BPNN).Firstly,the effects of noise and missing values are eliminated through AE net-work for data reduction and feature extraction.Then,the BPNN is used for predicting the sulfur con-tent of liquid steel in LF.The actual on-site data validation show that the ERMS,EMA and the correla-tion coefficient R2 are respectively up to 1.403,1.083 and 0.824,which has good prediction per-formance.

关 键 词：LF 钢水硫含量 预测 AE-BPNN 特征提取 数据建模 

分 类 号：TF769[冶金工程—钢铁冶金] TP183[自动化与计算机技术—控制理论与控制工程]