Phase Partition and Online Monitoring for Batch Process Based on Multiway BEAM

Batch process can exhibit significantly different characteristics across different phases, hence it is significant to partition it reasonably and set up corresponding subphase models for online monitoring. Unlike traditional phase-partition algorithms that customarily exploit the result of PCA algorithm for advanced research, an innovative algorithm which directly extracts effective information from the covariance matrix is presented in this paper, which is called multiway beacon exception analysis for maintenance (MBEAM). Its theoretics and statistical characteristics are demonstrated adequately. Based on the accurate capture of the change in variable correlation caused by characteristic variance of the process, the algorithm can separate the process into major phases and transition patterns automatically. The time-varying characteristics will then remain relatively stable in each independent subphase and will be supervised by homologous monitoring model that reflects the inherent phase feature. Due to its simple and intuitive format, MBEAM has superior performance in computation efficiency and fault interpretation, which is illuminated later in this paper. Synthetical illustrations are given concerning the influences of major parameters on the monitoring performance. Comparison with the step-wise sequential phase partition algorithm is conducted for a clearer insight. Experiments are carried out to further confirm the validation of the proposed method.

[1]  Walter Ukovich,et al.  A simulation based Decision Support System for logistics management , 2015, J. Comput. Sci..

[2]  Chunhui Zhao,et al.  Improved Batch Process Monitoring and Quality Prediction Based on Multiphase Statistical Analysis , 2008 .

[3]  Jiankang Dong,et al.  Fault diagnosis for the landing phase of the aircraft based on an adaptive kernel principal component analysis algorithm , 2015, J. Syst. Control. Eng..

[4]  Age K. Smilde.  Comments on three‐way analyses used for batch process data , 2001 .

[5]  Heemin Yi Yang.  Advanced prognosis and health management of aircraft and spacecraft subsystems , 2000 .

[6]  José Luis Godoy,et al.  Relationships between PCA and PLS-regression , 2014 .

[7]  Walter Ukovich,et al.  Fault Detection by Labeled Petri Nets in Centralized and Distributed Approaches , 2013, IEEE Transactions on Automation Science and Engineering.

[8]  Shen Yin,et al.  Intelligent Particle Filter and Its Application to Fault Detection of Nonlinear System , 2015, IEEE Transactions on Industrial Electronics.

[9]  Chunhui Zhao,et al.  Adaptive Monitoring Method for Batch Processes Based on Phase Dissimilarity Updating with Limited Modeling Data , 2007 .

[10]  John F. MacGregor,et al.  Chemometrics and intelligent laboratory systems Multiway partial least squares in monitoring batch processes , 2003 .

[11]  Jian-Jiun Ding,et al.  Salient Region Detection Improved by Principle Component Analysis and Boundary Information , 2013, IEEE Transactions on Image Processing.

[12]  Youxian Sun,et al.  Step-wise sequential phase partition (SSPP) algorithm based statistical modeling and online process monitoring , 2013 .

[13]  Guang Wang,et al.  Quality-Related Fault Detection Approach Based on Orthogonal Signal Correction and Modified PLS , 2015, IEEE Transactions on Industrial Informatics.

[14]  Fumikazu Miwakeichi,et al.  Concurrent EEG/fMRI analysis by multiway Partial Least Squares , 2004, NeuroImage.

[15]  Peter A Vanrolleghem,et al.  Monitoring of a sequencing batch reactor using adaptive multiblock principal component analysis. , 2003, Biotechnology and bioengineering.

[16]  Okyay Kaynak,et al.  Big Data for Modern Industry: Challenges and Trends [Point of View] , 2015, Proc. IEEE.

[17]  Yi Zhu,et al.  Time-varying and anti-disturbance fault diagnosis for a class of nonlinear systems , 2015, J. Syst. Control. Eng..

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

[19]  Wang Shuqingi.  An Improved Adaptive Multi-way Principal Component Analysis for Monitoring Streptomycin Fermentation Process , 2004 .

[20]  Theodora Kourti,et al.  Analysis, monitoring and fault diagnosis of batch processes using multiblock and multiway PLS , 1995 .

[21]  Okyay Kaynak,et al.  Improved PLS Focused on Key-Performance-Indicator-Related Fault Diagnosis , 2015, IEEE Transactions on Industrial Electronics.

[22]  Cheng-Lin Wen,et al.  Fault Diagnosis Based on Information Incremental Matrix: Fault Diagnosis Based on Information Incremental Matrix , 2012 .

[23]  J.F. MacGregor,et al.  Multi-way PCA applied to an industrial batch process , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[24]  Theodora Kourti,et al.  Comparing alternative approaches for multivariate statistical analysis of batch process data , 1999 .

[25]  Fuli Wang,et al.  Improved calibration investigation using phase-wise local and cumulative quality interpretation and prediction , 2009 .

[26]  Walter Ukovich,et al.  Modelling alarm management workflow in healthcare according to IHE framework by coloured Petri Nets , 2012, Eng. Appl. Artif. Intell..

[27]  Wen Cheng.  Fault Diagnosis Based on Information Incremental Matrix , 2012 .