Transfer of Qualitative and Quantitative Knowledge for Similar Batch Process Monitoring

The operating conditions for industrial batch production often cover a wide range in order to produce different products. Inconsistent working conditions and recipes may change the data properties, but the generated batches may share similar mechanisms in terms of their qualitative and quantitative knowledge domains. In this paper, we propose a transfer learning framework for both domains to improve the efficiency of monitoring in similar batch scenarios. First, a statistical pattern clustering strategy is developed for assessing and separating similar conditions. Based on this strategy, the phase-based generalized Procrustes analysis and the ordinary Procrustes analysis are proposed to produce the nominal representations and also to transfer quantitative knowledge by accommodating batch-wise and recipe-wise discrepancies. Furthermore, a multiphase Bayesian network is constructed for qualitative knowledge transfer and statistical modeling with the nominal representations. Finally, a systematic monitoring flowchart is established for fault detection and isolation based on a just-in-time transfer strategy. Under this framework, the efforts required for similar process modeling can be reduced and the monitoring efficiency can be improved. The feasibility and effectiveness of the proposed diagram for industrial uses are validated on a fed-batch penicillin fermentation process.

[1]  Jiankang Dong,et al.  Phase Partition and Online Monitoring for Batch Process Based on Multiway BEAM , 2017, IEEE Transactions on Automation Science and Engineering.

[2]  Melody Y. Kiang,et al.  A two-stage clustering approach for multi-region segmentation , 2010, Expert Syst. Appl..

[3]  Yuan Yao,et al.  Statistical analysis and online monitoring for multimode processes with between-mode transitions , 2010 .

[4]  J. Macgregor,et al.  Monitoring batch processes using multiway principal component analysis , 1994 .

[5]  Dominique Bonvin,et al.  Framework for explicit drift correction in multivariate calibration models , 2010 .

[6]  Furong Gao,et al.  A survey on multistage/multiphase statistical modeling methods for batch processes , 2009, Annu. Rev. Control..

[7]  David J. Ketchen,et al.  THE APPLICATION OF CLUSTER ANALYSIS IN STRATEGIC MANAGEMENT RESEARCH: AN ANALYSIS AND CRITIQUE , 1996 .

[8]  Ali Cinar,et al.  Statistical monitoring of multistage, multiphase batch processes , 2002 .

[9]  Gülnur Birol,et al.  A modular simulation package for fed-batch fermentation: penicillin production , 2002 .

[10]  P. A. Taylor,et al.  Synchronization of batch trajectories using dynamic time warping , 1998 .

[11]  Furong Gao,et al.  Similar Batch Process Monitoring With Orthogonal Subspace Alignment , 2018, IEEE Transactions on Industrial Electronics.

[12]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

[13]  M. C. Jones,et al.  A reliable data-based bandwidth selection method for kernel density estimation , 1991 .

[14]  Furong Gao,et al.  Bayesian improved model migration methodology for fast process modeling by incorporating prior information , 2015 .

[15]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[16]  Si-Zhao Joe Qin,et al.  Survey on data-driven industrial process monitoring and diagnosis , 2012, Annu. Rev. Control..

[17]  Steven X. Ding,et al.  Data-driven monitoring for stochastic systems and its application on batch process , 2013, Int. J. Syst. Sci..

[18]  Jie Yu,et al.  A novel dynamic bayesian network‐based networked process monitoring approach for fault detection, propagation identification, and root cause diagnosis , 2013 .

[19]  Pierantonio Facco,et al.  Nearest-Neighbor Method for the Automatic Maintenance of Multivariate Statistical Soft Sensors in Batch Processing , 2010 .

[20]  Furong Gao,et al.  Process similarity and developing new process models through migration , 2009 .

[21]  Kaixiang Peng,et al.  A Quality-Based Nonlinear Fault Diagnosis Framework Focusing on Industrial Multimode Batch Processes , 2016, IEEE Transactions on Industrial Electronics.

[22]  S. Qin,et al.  Multiway Gaussian Mixture Model Based Multiphase Batch Process Monitoring , 2009 .

[23]  Yuan Yao,et al.  Phase and transition based batch process modeling and online monitoring , 2009 .

[24]  Fuli Wang,et al.  Two‐dimensional dynamic PCA for batch process monitoring , 2005 .

[25]  Furong Gao,et al.  Process Modeling Based on Process Similarity , 2008 .

[26]  Zhiqiang Ge,et al.  Data Mining and Analytics in the Process Industry: The Role of Machine Learning , 2017, IEEE Access.

[27]  Furong Gao,et al.  Bayesian migration of Gaussian process regression for rapid process modeling and optimization , 2011 .

[28]  John F. MacGregor,et al.  Product transfer between plants using historical process data , 2000 .

[29]  Salvador García Muñoz,et al.  Application of multivariate latent variable modeling to pilot-scale spray drying monitoring and fault detection: Monitoring with fundamental knowledge , 2009, Comput. Chem. Eng..

[30]  Furong Gao,et al.  Improved Nonlinear Quality Estimation for Multiphase Batch Processes Based on Relevance Vector Machine with Neighborhood Component Variable Selection , 2018 .

[31]  Zhiqiang Ge,et al.  Non-Gaussian Industrial Process Monitoring With Probabilistic Independent Component Analysis , 2017, IEEE Transactions on Automation Science and Engineering.

[32]  Jin Wang,et al.  Statistics pattern analysis: A new process monitoring framework and its application to semiconductor batch processes , 2011 .

[33]  Chenglin Wen,et al.  Fault Detection Using Random Projections and k-Nearest Neighbor Rule for Semiconductor Manufacturing Processes , 2015, IEEE Transactions on Semiconductor Manufacturing.

[34]  Pierantonio Facco,et al.  Transfer of Process Monitoring Models between Different Plants Using Latent Variable Techniques , 2012 .

[35]  Jing Li,et al.  Fault detection and isolation of faults in a multivariate process with Bayesian network , 2010 .

[36]  Yuan Yao,et al.  Mixed-effects Gaussian Process Modeling Approach With Application in Injection Molding Processes , 2018 .

[37]  Zhiqiang Ge,et al.  A comparative study of just-in-time-learning based methods for online soft sensor modeling , 2010 .

[38]  William A. Walters,et al.  Ultra-high-throughput microbial community analysis on the Illumina HiSeq and MiSeq platforms , 2012, The ISME Journal.

[39]  David Maxwell Chickering,et al.  Learning Bayesian Networks: The Combination of Knowledge and Statistical Data , 1994, Machine Learning.