Data-driven approach of FS-SKPLS monitoring with application to wastewater treatment process

In this paper, a data-driven scheme of spherical kernel partial least squares based on feature subspace (FS-SKPLS) will be applied to the wastewater treatment process (WWTP). First, select appropriate data variables. Utilize the benchmark simulation model no. 1 (BSM1) to obtain large amounts of training and testing data needed in the process monitoring. Then, introduce the feather subspace method into spherical kernel partial least squares (SKPLS) to get FS-SKPLS approach. Finally, adopt FS-SKPLS to achieve the aims of the off-line modeling and the on-line process monitoring.

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

[2]  Shen Yin,et al.  Adaptive Fuzzy Control of Strict-Feedback Nonlinear Time-Delay Systems With Unmodeled Dynamics , 2016, IEEE Transactions on Cybernetics.

[3]  Peter A. Vanrolleghem,et al.  Towards a simulation-benchmark for evaluating respirometry-based control strategies , 1997 .

[4]  Yi Hu,et al.  Robust Online Monitoring Based on Spherical-Kernel Partial Least Squares for Nonlinear Processes with Contaminated Modeling Data , 2013 .

[5]  Shi Hongbo.  Online nonlinear process monitoring using kernel partial least squares , 2011 .

[6]  C. Yoo,et al.  Nonlinear process monitoring using kernel principal component analysis , 2004 .

[7]  W. Gujer,et al.  Activated sludge model No. 3 , 1995 .

[8]  Hongbo Shi,et al.  Improved Kernel PLS-based Fault Detection Approach for Nonlinear Chemical Processes , 2014 .

[9]  Min Wang,et al.  Adaptive fuzzy control of nonlinear time-delay systems , 2008, 2008 Chinese Control and Decision Conference.

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

[11]  P. Rousseeuw,et al.  A fast algorithm for the minimum covariance determinant estimator , 1999 .

[12]  D. G. Simpson,et al.  Robust principal component analysis for functional data , 2007 .

[13]  Shen Yin,et al.  Performance Monitoring for Vehicle Suspension System via Fuzzy Positivistic C-Means Clustering Based on Accelerometer Measurements , 2015, IEEE/ASME Transactions on Mechatronics.

[14]  Min Woo Lee,et al.  Robust Adaptive Partial Least Squares Modeling of a Full-Scale Industrial Wastewater Treatment Process , 2007 .

[15]  Huijun Gao,et al.  Passivity-preserving model reduction with finite frequency H∞ approximation performance , 2014, Autom..

[16]  Chi Ma,et al.  Fault diagnosis of nonlinear processes using multiscale KPCA and multiscale KPLS , 2011 .

[17]  ChangKyoo Yoo,et al.  Dynamic Monitoring Method for Multiscale Fault Detection and Diagnosis in MSPC , 2002 .

[18]  P. Rousseeuw,et al.  Alternatives to the Median Absolute Deviation , 1993 .

[19]  Renquan Lu,et al.  Fault Identification of Nonlinear Processes , 2013 .

[20]  B. Ripley,et al.  Robust Statistics , 2018, Encyclopedia of Mathematical Geosciences.

[21]  S. Wold.  Cross-Validatory Estimation of the Number of Components in Factor and Principal Components Models , 1978 .

[22]  Huijun Gao,et al.  Data-Driven Process Monitoring Based on Modified Orthogonal Projections to Latent Structures , 2016, IEEE Transactions on Control Systems Technology.

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

[24]  Xi Zhang,et al.  Nonlinear Multivariate Quality Estimation and Prediction Based on Kernel Partial Least Squares , 2008 .

[25]  Johan A. K. Suykens,et al.  Basic Methods of Least Squares Support Vector Machines , 2002 .

[26]  Mia Hubert,et al.  Detecting influential observations in Kernel PCA , 2010, Comput. Stat. Data Anal..

[27]  Yingwei Zhang,et al.  Multivariate process monitoring and analysis based on multi-scale KPLS , 2011 .

[28]  James Lam,et al.  An Improved Incremental Learning Approach for KPI Prognosis of Dynamic Fuel Cell System , 2016, IEEE Transactions on Cybernetics.

[29]  C Rosen,et al.  Multivariate and multiscale monitoring of wastewater treatment operation. , 2001, Water research.

[30]  R. Rosipal,et al.  Kernel Partial Least Squares for Nonlinear Regression and Discrimination , 2002 .

[31]  Hae Woo Lee,et al.  Multi-scale extension of PLS algorithm for advanced on-line process monitoring , 2009 .

[32]  Wenyou Du,et al.  Process Fault Detection Using Directional Kernel Partial Least Squares , 2015 .

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

[34]  Jose A. Romagnoli,et al.  Robust multi-scale principal components analysis with applications to process monitoring , 2005 .

[35]  J. Shao.  Linear Model Selection by Cross-validation , 1993 .

[36]  Huijun Gao,et al.  Data-Based Techniques Focused on Modern Industry: An Overview , 2015, IEEE Transactions on Industrial Electronics.