Research and application of the distillation column process fault prediction based on the improved KPCA

With the development of modern intelligent, automation and integration of the increasingly complex industrial process control system, the traditional prediction methods of faults perform not well, so it has faced a huge challenge. In this paper, a new improved kernel principal component analysis method is presented which uses the concept of indiscernibility and eigenvector applied to distillation column process fault prediction. Compared with traditional statistical techniques, improved KPCA not only can remove variables with little or no correlation with the fault, but also can reduce the amount of datas calculated by K. Applying this new method to distillation column process fault prediction, the simulation results show that the proposed methods have great advantages. Compared with the traditional KPCA, the improved KPCA improves the ability to predict the process failure caused by small disturbance and becomes more effective.

[1]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[2]  Jin Wang,et al.  Fault Detection Using the k-Nearest Neighbor Rule for Semiconductor Manufacturing Processes , 2007, IEEE Transactions on Semiconductor Manufacturing.

[3]  Heeyoung Kim,et al.  Application of kernel principal component analysis to multi-characteristic parameter design problems , 2015, Annals of Operations Research.

[4]  Daoqiang Zhang,et al.  A New Discriminant Principal Component Analysis Method with Partial Supervision , 2009, Neural Processing Letters.

[5]  Serge Iovleff,et al.  Probabilistic auto-associative models and semi-linear PCA , 2012, Adv. Data Anal. Classif..

[6]  Hassan Ghassemian,et al.  Combining the spectral PCA and spatial PCA fusion methods by an optimal filter , 2016, Inf. Fusion.

[7]  Shaojiang Dong,et al.  Fault feature extraction method based on local mean decomposition Shannon entropy and improved kernel principal component analysis model , 2016 .

[8]  Seiichi Ozawa,et al.  Online feature extraction based on accelerated kernel principal component analysis for data stream , 2015, Evolving Systems.

[9]  Mayank Pandey,et al.  Hybrid classification and regression models via particle swarm optimization auto associative neural network based nonlinear PCA , 2013, Int. J. Hybrid Intell. Syst..

[10]  Ma Yao,et al.  On-line monitoring of batch processes using generalized additive kernel principal component analysis , 2015 .

[11]  Enrico Zio,et al.  Model-based and data-driven prognostics under different available information , 2013 .

[12]  Ping Zhang,et al.  A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process , 2012 .

[13]  Hassani Messaoud,et al.  Kernel principal component analysis with reduced complexity for nonlinear dynamic process monitoring , 2017 .

[14]  Nan Li,et al.  Ensemble Kernel Principal Component Analysis for Improved Nonlinear Process Monitoring , 2015 .

[15]  Zhu Xi-hu.  Sensor Fault Detection for EHA System Based on Adaptive Kernel Principal Component Analysis , 2014 .