Developing Tensor-Based Common and Special Feature Analysis for Comprehensive Monitoring of Complex Batch Processes

Liu, Jingxiang1; Sun, Deshun2; Xiao, Yeliang3; Chen, Junghui4

2022-07-20

10.1021/acs.iecr.2c00987

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH   影响因子和分区

0888-5885

To overcome the limitation of unfolding-based methods and handle the multiple data set and limited data problems in the complex processes, such as multigrade batch processes, a novel tensor-based common and special feature extraction method and a comprehensive monitoring framework are proposed. In the proposed method, the uneven-length three-dimensional data are directly analyzed by the comprehensive tensor-based method without unfolding. To handle the multiple data set modeling problem, the tensor-based common feature extraction methods are first proposed to obtain the common features shared among different grades. The special features are sequentially determined by conducting tensor principal component analysis (PCA) on the residuals of each grade. The data are thus divided into common, special, and residual subspaces. Three monitoring statistics are established respectively in each subspace for online fault detection. The merits and effectiveness of the proposed method are demonstrated by an injection molding process with both even-length and uneven-length data in comparison with traditional methods.

SCI ; EI

英语

其他

NSF China["62003071","62103287"] ; Fundamental Research Funds for the Central Universities[3132022106] ; Key Laboratory of Intelligent Control Optimization of Industrial Equipment, Ministry of Education Open Fund Projects[LICO2021TB01] ; Ministry of Science and Technology, Taiwan, R.O.C.[MOST 109-2221-E-033-013-MY3]

Engineering

Engineering, Chemical

WOS:000831686200001

AMER CHEMICAL SOC

20223112527649

Batch data processing ; Extraction ; Fault detection ; Feature extraction ; Injection molding ; Principal component analysis

Data Processing and Image Processing:723.2 ; Chemical Operations:802.3 ; Algebra:921.1 ; Mathematical Statistics:922.2

CHEMISTRY

Web of Science

1.Dalian Maritime Univ, Sch Marine Elect Engn, Dalian 116026, Peoples R China
2.Southern Univ Sci & Technol Hosp, Intelligent Med Innovat Ctr, Shenzhen 518071, Peoples R China
3.Dalian Neusoft Univ Informat, Sch Gen Educ, Dalian 116023, Peoples R China
4.Chung Yuan Christian Univ, Dept Chem Engn, Taoyuan 32023, Taiwan

Liu, Jingxiang,Sun, Deshun,Xiao, Yeliang,et al. Developing Tensor-Based Common and Special Feature Analysis for Comprehensive Monitoring of Complex Batch Processes[J]. INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH,2022,61(28):10156-10171.

Liu, Jingxiang,Sun, Deshun,Xiao, Yeliang,&Chen, Junghui.(2022).Developing Tensor-Based Common and Special Feature Analysis for Comprehensive Monitoring of Complex Batch Processes.INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH,61(28),10156-10171.

Liu, Jingxiang,et al."Developing Tensor-Based Common and Special Feature Analysis for Comprehensive Monitoring of Complex Batch Processes".INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH 61.28(2022):10156-10171.