Optimizing kernel methods to reduce dimensionality in fault diagnosis of industrial systems

Five measures to adjust a RBF Kernel using KFDA and KPCA in FDI problems are compared.The influence of the KPCA and KFDA parameters in FDI problems are analyzed.The adjust of the kernel parameters with the measures , and is presented.The combination KFDA obtained the best results in the classification. Currently, industry needs more robust fault diagnosis systems. One way to achieve this is to complement these systems with preprocessing modules. This makes possible to reduce the dimension of the workspace by removing irrelevant information that hides faults in development or overloads the systems management. In this paper, a comparison between five performance measures in the adjustment of a Gaussian kernel used with the preprocessing techniques: Kernel Fisher Discriminant Analysis (KFDA) and Kernel Principal Component Analysis (KPCA) is made. The measures of performance used were: Target alignment, Alpha, Beta, Gamma and Fisher. The best results were obtained using the KFDA with the Alpha metric achieving a significant reduction in the dimension of the workspace and a high accuracy in the fault diagnosis. As fault classifier in the Tennessee Eastman Process benchmark an Artificial Neural Network was used.

[1]  Ridha Ziani,et al.  Bearing fault diagnosis using multiclass support vector machines with binary particle swarm optimization and regularized Fisher’s criterion , 2017, J. Intell. Manuf..

[2]  Jicong Fan,et al.  Online monitoring of nonlinear multivariate industrial processes using filtering KICA–PCA , 2014 .

[3]  Steven X. Ding,et al.  A Review on Basic Data-Driven Approaches for Industrial Process Monitoring , 2014, IEEE Transactions on Industrial Electronics.

[4]  Claus Weihs,et al.  Variable window adaptive Kernel Principal Component Analysis for nonlinear nonstationary process monitoring , 2011, Comput. Ind. Eng..

[5]  Youmin Zhang,et al.  Bibliographical review on reconfigurable fault-tolerant control systems , 2003, Annu. Rev. Control..

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

[7]  Chun-Chin Hsu,et al.  Integrating independent component analysis and support vector machine for multivariate process monitoring , 2010, Comput. Ind. Eng..

[8]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[9]  Wei Li,et al.  Fault diagnosis of rotating machinery with a novel statistical feature extraction and evaluation method , 2015 .

[10]  Jie Wang,et al.  Gaussian kernel optimization for pattern classification , 2009, Pattern Recognit..

[11]  Tao Li,et al.  Gaussian kernel optimization: Complex problem and a simple solution , 2011, Neurocomputing.

[12]  Ming Jian Zuo,et al.  An integrated framework for online diagnostic and prognostic health monitoring using a multistate deterioration process , 2014, Reliab. Eng. Syst. Saf..

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

[14]  Karl Johan Åström,et al.  Control: A perspective , 2014, Autom..

[15]  Steven X. Ding,et al.  Data-driven Design of Fault Diagnosis and Fault-tolerant Control Systems , 2014 .

[16]  Nina F. Thornhill,et al.  The impact of compression on data-driven process analyses , 2004 .

[17]  Jicong Fan,et al.  Fault detection and diagnosis of non-linear non-Gaussian dynamic processes using kernel dynamic independent component analysis , 2014, Inf. Sci..

[18]  Vojislav Kecman,et al.  Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models , 2001 .

[19]  Marcin Perzyk,et al.  Comparison of data mining tools for significance analysis of process parameters in applications to process fault diagnosis , 2014, Inf. Sci..

[20]  Rolf Isermann,et al.  Fault-Diagnosis Applications: Model-Based Condition Monitoring: Actuators, Drives, Machinery, Plants, Sensors, and Fault-tolerant Systems , 2011 .

[21]  Ning Wang,et al.  The optimization of the kind and parameters of kernel function in KPCA for process monitoring , 2012, Comput. Chem. Eng..

[22]  Pawel Chudzian,et al.  Evaluation measures for kernel optimization , 2012, Pattern Recognit. Lett..

[23]  Tianshun Chen,et al.  Optimizing the Gaussian kernel function with the formulated kernel target alignment criterion for two-class pattern classification , 2013, Pattern Recognit..

[24]  Shicheng Wang,et al.  Kernel Principal Component Analysis-Based Method for Fault Diagnosis of SINS , 2014 .

[25]  Mehryar Mohri,et al.  Algorithms for Learning Kernels Based on Centered Alignment , 2012, J. Mach. Learn. Res..

[26]  Ming Jian Zuo,et al.  A Non-Probabilistic Metric Derived From Condition Information for Operational Reliability Assessment of Aero-Engines , 2015, IEEE Transactions on Reliability.

[27]  Li Jiang,et al.  Feature extraction based on semi-supervised kernel Marginal Fisher analysis and its application in bearing fault diagnosis , 2013 .

[28]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[29]  Xuefeng Yan,et al.  Fault Diagnosis in Chemical Process Based on Self-organizing Map Integrated with Fisher Discriminant Analysis , 2013 .

[30]  Dongyuan Shi,et al.  Divisional fault diagnosis of large-scale power systems based on radial basis function neural network and fuzzy integral , 2013 .

[31]  Feng Zhao,et al.  Learning kernel parameters for kernel Fisher discriminant analysis , 2013, Pattern Recognit. Lett..

[32]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[33]  Amparo Alonso-Betanzos,et al.  Automatic bearing fault diagnosis based on one-class ν-SVM , 2013, Comput. Ind. Eng..

[34]  Bo-Suk Yang,et al.  Support vector machine in machine condition monitoring and fault diagnosis , 2007 .

[35]  Bogdan Gabrys,et al.  Data-driven Soft Sensors in the process industry , 2009, Comput. Chem. Eng..

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

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

[38]  Yuan Li,et al.  Fault Diagnosis Based on Improved Kernel Fisher Discriminant Analysis , 2012, J. Softw..

[39]  Alberto Prieto Moreno,et al.  Comparative evaluation of classification methods used in fault diagnosis of industrial processes , 2013 .

[40]  Dongxiang Jiang,et al.  Bearing fault diagnosis of wind turbine based on intrinsic time-scale decomposition frequency spectrum , 2014 .

[41]  Chris Aldrich,et al.  Unsupervised Process Monitoring and Fault Diagnosis with Machine Learning Methods , 2013, Advances in Computer Vision and Pattern Recognition.

[42]  M. Omair Ahmad,et al.  Optimizing the kernel in the empirical feature space , 2005, IEEE Transactions on Neural Networks.

[43]  B. Scholkopf,et al.  Fisher discriminant analysis with kernels , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[44]  Yan Yan Pang,et al.  Fault Diagnosis Method Based on KPCA and Selective Neural Network Ensemble , 2014 .

[45]  N. Cristianini,et al.  On Kernel-Target Alignment , 2001, NIPS.

[46]  Deyong You,et al.  WPD-PCA-Based Laser Welding Process Monitoring and Defects Diagnosis by Using FNN and SVM , 2015, IEEE Transactions on Industrial Electronics.

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

[48]  Yuichi Motai,et al.  Kernel Association for Classification and Prediction: A Survey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[49]  Magnus Löfstrand,et al.  Comparing a knowledge-based and a data-driven method in querying data streams for system fault detection: A hydraulic drive system application , 2014, Comput. Ind..

[50]  Zheng Bao,et al.  Optimizing the data-dependent kernel under a unified kernel optimization framework , 2008, Pattern Recognit..

[51]  Furong Gao,et al.  Review of Recent Research on Data-Based Process Monitoring , 2013 .

[52]  Ahmad Akbari,et al.  Evolutionary combination of kernels for nonlinear feature transformation , 2014, Inf. Sci..

[53]  Tu Bao Ho,et al.  An efficient kernel matrix evaluation measure , 2008, Pattern Recognit..

[54]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[55]  Richard D. Braatz,et al.  Fault Detection and Diagnosis in Industrial Systems , 2001 .

[56]  Joseph Mathew,et al.  Rotating machinery prognostics. State of the art, challenges and opportunities , 2009 .

[57]  Shaoze Yan,et al.  Feature generation method for fault diagnosis of closed cable loop used in deployable space structures , 2014 .

[58]  Zhi-Huan Song,et al.  A novel fault diagnosis system using pattern classification on kernel FDA subspace , 2011, Expert Syst. Appl..