Local multi-model integrated soft sensor based on just-in-time learning for mechanical properties of hot strip mill process
作者机构：Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of EducationSchool of Automation and Electrical EngineeringUniversity of Science and Technology BeijingBeijing 100083China National Engineering Research Center for Advanced Rolling TechnologyUniversity of Science and Technology BeijingBeijing 100083China
出 版 物：《Journal of Iron and Steel Research International》 (J. Iron Steel Res. Int.)
年 卷 期：2021年第28卷第7期
页 面：830-841页
核心收录：
学科分类：08[工学] 080502[工学-材料学] 0805[工学-材料科学与工程（可授工学、理学学位）]
基 金：the National Natural Science Foundation of China(NSFC)under Grants 61773053,61873024 Fundamental Research Funds for the China Central Universities of USTB(FRF-TP-19-049A1Z) the National Key R&D Program of China(No.2017YFB0306403)
主 题：Soft sensor Just-in-time learning Multi-model Hot rolling
摘 要：The mechanical properties of hot rolled strip are the key index of product quality,and the soft sensing of them is an important decision basis for the control and optimization of hot rolling *** solve the problem that it is difficult to measure the mechanical properties of hot rolled strip in time and accurately,a soft sensor based on ensemble local modeling was ***,outliers of process data are removed by local outlier *** standardization and transformation,normal data that can be used in the model are ***,in order to avoid redundant variables participating in modeling and reducing performance of models,feature selection was applied combing the mechanism of hot rolling process and mutual information among ***,features of samples were extracted by supervised local preserving projection,and a prediction model was constructed by Gaussian process regression based on just-in-time learning(JITL).Other JITL-based models,such as support vector regression and gradient boosting regression tree models,keep all variables and make up for the lost information during dimension ***,the soft sensor was developed by integrating individual models through stacking *** and reliability of proposed soft sensors were verified by actual process data from a real hot rolling process.
维普期刊数据库