Application of Temperature Inference Method Based on Soft Sensor Technique to Plate Production Process  

作　　者：DING Jing-guo QU Li-li HU Xian-lei LIU Xiang-hua 

机构地区：[1]State Key Laboratory of Rolling and Automation,Northeastern University,Shenyang 110004,Liaoning,China [2]Shenyang Blower Ventilation Co Ltd,Shenyang 110041,Liaoning,China

出　　处：《Journal of Iron and Steel Research International》2011年第3期24-27,共4页

基　　金：Item Sponsored by National Natural Science Foundation of China(50104004)

摘　　要：There is a certain extent of measuring error for each pyrometer in plate production process,which has a great impact on process control system.A soft sensor technique is used to calculate the confidence interval of measuring temperature data from pyrometers and an inference estimator is designed by partial least square method,then the pyrometer with highest confidence is considered as the reference one,with which inference estimation for measured data on-line of other pyrometers is started and the measuring error is conformed.From actual application it can be found that this method can improve the measuring accuracy by 3%-5%,and has high field application value.There is a certain extent of measuring error for each pyrometer in plate production process,which has a great impact on process control system.A soft sensor technique is used to calculate the confidence interval of measuring temperature data from pyrometers and an inference estimator is designed by partial least square method,then the pyrometer with highest confidence is considered as the reference one,with which inference estimation for measured data on-line of other pyrometers is started and the measuring error is conformed.From actual application it can be found that this method can improve the measuring accuracy by 3%-5%,and has high field application value.

关 键 词：plate mill soft sensor temperature inference partial least square 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置] TP18[自动化与计算机技术—控制科学与工程]