基于主成分分析-BP神经网络的热精轧带钢跑偏预测研究  

Prediction of Deviation in Hot Finish Rolling Strip Based on Principal Component Analysis-BP Neural Network

作　　者：于景辉[1] 赵德琦 王少[1] YU Jinghui;ZHAO Deqi;WANG Shao(The Manufacturing Department of Ma’anshan Iron and Steel Co., Ltd., Ma’anshan 243003, China;Design and Research Institute of USTB Co., Ltd., Beijing 100083, China)

机构地区：[1]马鞍山钢铁股份有限公司制造部,安徽马鞍山243000 [2]北京科技大学设计研究院有限公司,北京100083

出　　处：《山东冶金》2019年第4期44-47,共4页Shandong Metallurgy

摘　　要：由于带钢热轧过程中跑偏的影响因素复杂,传统的机理预测模型难以保证跑偏预测的准确性。本文从数据驱动的角度出发,结合带钢轧制过程跑偏产生原理和实际生产数据,提出了一种基于主成分分析(PCA)与BP神经网络的组合模型用于预测带钢跑偏。该模型精度较高,对提高热连轧成品质量和轧制设备的寿命都具有重大意义。Due to the complex factors affecting the deviation of the strip during hot rolling, traditional physical prediction model is hard to guarantee the accuracy of the deviation prediction. From the perspective of data driven, considered with the principle of deviation generation and actual production data of strip rolling process, a combined model based on PCA and BP neural network is proposed to predict strip deviation. The high precision of the model has great significance for improving the quality of hot rolled products and the life of rolling equipment.

关 键 词：带钢 轧制 主成分分析 BP神经网络 跑偏预测 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]