基于半监督堆叠自编码器的轧制力预报建模研究  

Rolling Force Prediction Modeling Based on Semi-supervised Stacked Autoencoder

作　　者：任巍[1] 翟博豪 彭炜淞 REN Wei;ZHAI Bohao;PENG Weisong(Cold Rolling Plant of Shanxi Taigang Stainless Steel Co.,Ltd.,Taiyuan 030003,Shanxi,China;Tianjin Research Institute of Electric Science Co.,Ltd.,Tianjin 300180,China)

机构地区：[1]山西太钢不锈钢股份有限公司冷轧厂,山西太原030003 [2]天津电气科学研究院有限公司,天津300180

出　　处：《电气传动》2022年第14期70-74,80,共6页Electric Drive

基　　金：天津电气科学研究院自立项目(GY2020ZL001)。

摘　　要：随着计算机运算能力的提升,数据驱动技术被广泛应用于冶金工业过程中。基于该技术的轧制力预报有助于缩短带材的头尾长度,提高成材率。为了解决数据驱动模型在预训练过程中因特征提取盲目导致预测精度较低的问题,提出了一种基于半监督堆叠自编码器(SS-SAE)的深度分层监督预处理框架,用于轧制力预报建模研究。在SS-SAE中,依次训练多个半监督自编码器(SS-AE),分级提取目标相关特征。每个SS-AE将来自前一隐藏层的特征作为新的输入,以生成高阶特征。通过堆叠多个SS-AE的方式,可逐步学习深层目标相关特征,同时深度网络结构将逐步减少不相关信息。仿真结果表明,该模型预测精度可控制在2%以内,实现了轧制力的高精度预测。With the improvement of computer operation level,data-driven technology is widely used in metallurgical industry. Accurate prediction of rolling force is helpful to shorten the length of strip head and tail and improve the yield of strip. In order to solve the problem of low prediction accuracy of data-driven model due to blind feature extraction during pre-training,a deep hierarchical supervised preprocessing framework based on semisupervised stacked autoencoder(SS-SAE)was proposed for modeling rolling force prediction. In SS-SAE,several semi-supervised autoencoders(SS-AEs)were trained in turn to extract target related features. Each SS-AE took features from the previous hidden layer as new input to generate higher-order features. By stacking multiple SSAEs,the features related to deep targets could be gradually learned,while the deep network structure will gradually reduce the irrelevant information. The simulation results show that the prediction accuracy of this model can be controlled within 2%,and the high precision prediction of rolling force is realized.

关 键 词：深度学习 特征提取 自编码器 轧制力预报 

分 类 号：TG335.13[金属学及工艺—金属压力加工]