A hybrid kernel PCA, hypersphere SVM and extreme learning machine approach for nonlinear process online fault detection

This paper presents a hybrid approach for online fault detection in nonlinear processes. To solve the possible monitoring difficulties caused by nonlinear characteristics of industrial process data, two applications of the Kernel Method: Hypersphere Support Vector Machine (HSSVM) and Kernel Principal Component Analysis (KPCA) are used as fault detection methods. On top of that, to obtain the adaptive models for online monitoring and fault detection in unsteady-stage conditions, instead of the static ones established by traditional HSSVM and KPCA, multiple methods are adopted, including Recursive KPCA, Adaptive Control Limit (ACL) and Online Sequential Extreme Learning Machine (OS-ELM), all of which update the detection model in real time with dynamically adjusting. The T2 control limit of Recursive KPCA, the classification hyperspheres of HSSVM and the single hidden layer feedforward network (SLFN) trained with OS-ELM work collaboratively in monitoring the real time process data to detect the possible faults. The proposed approach was tested and validated via a set of experimental data collected from a bearing test rig. Experimental results show that this approach is adequate for fault detection while meets the needs of real time performance.

[1]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[2]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[3]  Vincent Choqueuse,et al.  Diagnosis of Three-Phase Electrical Machines Using Multidimensional Demodulation Techniques , 2012, IEEE Transactions on Industrial Electronics.

[4]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[5]  Shuang Chen,et al.  Feature extraction of X-ray chest image based on KPCA , 2012, Proceedings of 2012 2nd International Conference on Computer Science and Network Technology.

[6]  Hao Wu,et al.  A longitudinal-standardization multi-period PCA fault detection strategy based-on adaptive confidence limit , 2014, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society.

[7]  Hai Qiu,et al.  Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics , 2006 .

[8]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[9]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[10]  Norhaliza Abdul Wahab,et al.  Fault detection and monitoring using Multiscale PCA , 2013, 2013 IEEE 4th Control and System Graduate Research Colloquium.

[11]  Lei Xie,et al.  Adaptive KPCA Modeling of Nonlinear Systems , 2015, IEEE Transactions on Signal Processing.

[12]  Hao Xu,et al.  A PCA-mRVM fault diagnosis strategy and its application in CHMLIS , 2014, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society.

[13]  Robert P. W. Duin,et al.  Data domain description using support vectors , 1999, ESANN.

[14]  Elhoussin Elbouchikhi,et al.  Cascaded H-Bridge Multilevel Inverter System Fault Diagnosis Using a PCA and Multiclass Relevance Vector Machine Approach , 2015, IEEE Transactions on Power Electronics.

[15]  J. Koenderink.  Q… , 2014, Les noms officiels des communes de Wallonie, de Bruxelles-Capitale et de la communaute germanophone.