Process Monitoring Approach Based on Lifting Wavelet and Multi-way Principal Component Analysis

A novel technique of batch process monitoring based on lifting wavelet and multi-way principal component analysis (LWMPCA) is developed in this paper. The proposed technique consists of a preprocessing unit based on lifting wavelets transform in combination with MPCA. The superiority of the proposed method is illustrated by applying it to the simulation benchmark of fed-batch penicillin fermentation process with more reliable monitoring charts. The results of simulation clearly demonstrate the effectiveness and feasibility of the proposed method, which detects various faults more promptly with desirable reliability.

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

[2]  Rajagopalan Srinivasan,et al.  Online monitoring of multi-phase batch processes using phase-based multivariate statistical process control , 2008, Comput. Chem. Eng..

[3]  G. Rong,et al.  Learning a data-dependent kernel function for KPCA-based nonlinear process monitoring , 2009 .

[4]  Paul Nomikos,et al.  Detection and diagnosis of abnormal batch operations based on multi-way principal component analysis World Batch Forum, Toronto, May 1996 , 1996 .

[5]  Xiaoling Zhang,et al.  Multiway kernel independent component analysis based on feature samples for batch process monitoring , 2009, Neurocomputing.

[6]  Yuan Jing-qi,et al.  Online Supervision of Penicillin Cultivations Based on Rolling MPCA , 2007 .

[7]  Ning Li,et al.  Anti-aliasing lifting scheme for mechanical vibration fault feature extraction , 2009 .

[8]  Fuli Wang,et al.  On-line batch process monitoring using batch dynamic kernel principal component analysis , 2010 .

[9]  Jingqi Yuan,et al.  Batch process monitoring with tensor factorization , 2009 .

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

[11]  Jin Chen,et al.  Bearing performance degradation assessment based on lifting wavelet packet decomposition and fuzzy c-means , 2010 .

[12]  Xi Zhang,et al.  Nonlinear biological batch process monitoring and fault identification based on kernel fisher discriminant analysis , 2007 .