Yi Liu
Title: Smart Data-Driven Soft Sensor Model for Quality Prediction of Multigrade Processes
Abstract: Multigrade industrial processes have become increasingly important in satisfying the requirements of agile manufacturing and a diversified market. However, because of the unknown distribution discrepancy of multigrade process data, the development of reliable quality prediction models is still intractable, especially for the grades with limited quality measurements. In this work, several promising methods, including just-in-time probabilistic learning and transfer learning, have been proposed to develop smart soft sensors for the quality inferring of multigrade processes. A probabilistic analysis approach using the statistical property of steady-state grades is presented for description of the current state of a new sample. Additionally, an integrated probabilistic soft sensor modeling method which can select the suitable model for quality prediction of multigrade processes has been developed. By utilizing and transferring the useful information from different operating conditions to the existing soft sensor, the prediction domain is enlarged and the prediction accuracy is enhanced. Moreover, by reducing the data distribution discrepancy and enriching the information provided by the target domain, a domain adaptation-based supervised soft sensor outperforms conventional prediction models in terms of the range of prediction domains and prediction accuracy. Through simulated and industrial multigrade case studies, the feasibility of the developed methods was illustrated. The benefits of these soft sensors were discussed and highlighted.
Biography: Yi Liu received the Ph.D. degree in control theory and engineering from Zhejiang University, Hangzhou, China, in 2009. He was an Associate Professor with the Institute of Process Equipment and Control Engineering, Zhejiang University of Technology from 2011 to 2020. He was a Postdoctoral Researcher with the Department of Chemical Engineering, Chung-Yuan Christian University from February 2012 to June 2013. Since December 2020, He has been a Full Professor with Zhejiang University of Technology, Hangzhou, China. He has published over 50 research papers at IEEE Transactions and international journals in the field of process modeling and control. His research interests include data intelligence with applications to modeling, control, and optimization of industrial processes.
Abstract: Multigrade industrial processes have become increasingly important in satisfying the requirements of agile manufacturing and a diversified market. However, because of the unknown distribution discrepancy of multigrade process data, the development of reliable quality prediction models is still intractable, especially for the grades with limited quality measurements. In this work, several promising methods, including just-in-time probabilistic learning and transfer learning, have been proposed to develop smart soft sensors for the quality inferring of multigrade processes. A probabilistic analysis approach using the statistical property of steady-state grades is presented for description of the current state of a new sample. Additionally, an integrated probabilistic soft sensor modeling method which can select the suitable model for quality prediction of multigrade processes has been developed. By utilizing and transferring the useful information from different operating conditions to the existing soft sensor, the prediction domain is enlarged and the prediction accuracy is enhanced. Moreover, by reducing the data distribution discrepancy and enriching the information provided by the target domain, a domain adaptation-based supervised soft sensor outperforms conventional prediction models in terms of the range of prediction domains and prediction accuracy. Through simulated and industrial multigrade case studies, the feasibility of the developed methods was illustrated. The benefits of these soft sensors were discussed and highlighted.
Biography: Yi Liu received the Ph.D. degree in control theory and engineering from Zhejiang University, Hangzhou, China, in 2009. He was an Associate Professor with the Institute of Process Equipment and Control Engineering, Zhejiang University of Technology from 2011 to 2020. He was a Postdoctoral Researcher with the Department of Chemical Engineering, Chung-Yuan Christian University from February 2012 to June 2013. Since December 2020, He has been a Full Professor with Zhejiang University of Technology, Hangzhou, China. He has published over 50 research papers at IEEE Transactions and international journals in the field of process modeling and control. His research interests include data intelligence with applications to modeling, control, and optimization of industrial processes.