D0I:10.13374.issn1001663.2013.02.011 第35卷第2期 北京科技大学学报 Vol.35 No.2 2013年2月 Journal of University of Science and Technology Beijing Feb.2013 基于正交信号校正和稳健回归的带钢酸洗浓度预测 模型 何飞12八，王保健，黎敏2)，赵广满) 1)北京科技大学国家板带生产先进装备工程技术研究中心，北京1000832)北京科技大学机械工程学院，北京1003 3)鞍钢股份有限公司冷轧厂，鞍山114030 心通信作者，E-mail:limin@ustb.cdu.cn 摘要为了实时获得冷轧带钢酸洗溶液的浓度值，便于进行酸浓度控制，采用软测量方法实时预测酸浓度.由于酸浓 度建模数据中无关成分和特异点会影响模型精度，利用正交信号校正和稳健回归相结合的方法来建立酸浓度预测模型 首先利用正交信号校正对建模数据进行预处理，去除自变量中与因变量无关的成分；然后采用基于迭代加权最小二乘 的稳健回归算法进行建模，降低特异点对模型的影响：最后将预测结果和多元线性回归、传统稳健问归方法和正交信 号校正多元线性回归进行比较.实验结果表明：采用正交信号校正-稳健回归方法后，模型预测能力得到提高，与多元 线性回归结果相比，亚铁离子质量浓度和氢离子质量浓度的相对预测误差分别从1.82%降低到1.17%、从5.87%降低到 4.73%.本文提出的方法具有更好的模型预测精度，可以满足工业应用要求. 关键词冷轧；带钢；酸洗：浓度：预测：数学模型 分类号TG335.12 Acid concentration prediction model of steel pickling process based on orthogonal signal correction and robust regression HE Fel2),WANG Bao-jian2),LI Min2),ZHAO Guang-man) 1)National Engineering Research Center of Flat Rolling Equipment,University of Science and Technology Beijing.Beijing 100083,China 2)School of Mechanical Engineering,University of Science and Technology Beijing,Beijing 100083.China 3)Cold Rolling Plant,Angang Steel Company Limited,Anshan 114030,China Corresponding author,E-mail:limin@ustb.edu.cn ABSTRACT In order to get and control acid concentration values in cold-rolled strip steel pickling.a soft mea- surement method was proposed for real-time predicting the acid concentration.Because of the influcuce of irrelevant components and outliers in acid concentration data on the accuracy of the acid concentration prediction model,orthog- onal signal correction (OSC)and iterative weighted least squares (IRLS)regression were combined to build the model Firstly,orthogonal signal correction was used to remove irrelevant components which have nothing to do with the mea- sured variables.Then robust regression based on the iteratively reweighted least squares algorithm was applied in the model to reduce the influence of outliers.Finally,the prediction results were compared with multiple linear regresssion (MLR),IRLS,and OSC-MLR.It is found that OSC-IRLS has the best prediction accuracy.In comparison with MLR. the relative error of OSC-IRLS decrease from 1.82%to 1.17%in predicting the concentration of ferrous ions and from 5.87%to 4.73%in predicting the concentration of hydrogen ions.The proposed method has a better model prexiction accuracy to meet the requirements of industrial applications. KEY WORDS cold rolling;strip steel;pickling;concentration;prediction:mathematical models 收稿日期：2012-1008 基金项目：国家自然科学基金资助项目（⑤1004013,51204018）：高等学校博1：学科点专项科研某金资助项目(20110006110027)：“| 二五”国家科技支撑计划资助项目(2012BAF04B02):中央高校基本科研业务费专项(FRF-TP-12-167A,FRF-AS-(0-008B)DOI ：10．13374／j ．issn1001－053x．2013．02．011