Norazwan Md Nor, Mohd Azlan Hussain, Che Rosmani Che Hassan


Effective fault monitoring, detection and diagnosis of chemical processes is important to ensure the consistency and high product quality, as well as the safety of the processes. Fault diagnosis problems can be considered as classification problems as these techniques have been proposed and greatly improved over the past few years. However, a chemical process is often characterized by large scale and non-linear behavior. When linear discriminant analysis is used for fault diagnosis in the system, a lot of incorrect diagnosis will occur. As solution, this paper presents a novel approach for feature extraction and classification framework in chemical process systems based on wavelet transformation and discriminant analysis. The proposed multi-scale kernel Fisher discriminant analysis (MSKFDA) method used the combination of kernel Fisher discriminant analysis (KFDA) and discrete wavelet transform (DWT) to improve the classification performance as compared to conventional approaches. A DWT is applied to extract the process dynamics at different scales by decomposed the data into multiple scales, analyzed by the KFDA and only dynamical characteristics with important information was reconstructed by inverse discrete wavelet transform (IDWT). Then, Gaussian mixture model (GMM) and K-nearest neighbor (KNN) method were individually applied for the fault classification using the output from the MSKFDA approach. These two classifiers are evaluated and compared based on their performance on the Tennessee Eastman process database. The proposed framework for GMM and KNN classifiers had achieved average classification accuracies of 84.72% and 82.00%, respectively, with the results show significant improvement over existing methods in fault detection and classification.


Fault Diagnosis, Discrete Wavelet Transform, Fisher discriminant analysis, Gaussian mixture model, K nearest neighbor

Full Text:



V. Venkatasubramanian, R. Rengaswamy, S. N. Kavuri, and K. Yin. 2003. A Review of Process Fault Detection and Diagnosis Part III: Process History Based Methods. Computers & Chemical Engineering. 27: 327-346.

I. Yélamos, G. Escudero, M. M. Graells, L. Puigjaner, I. Yelamos, and G. Escurado. 2009. Performance assessment of a Novel Fault Diagnosis System Based on Support Vector Machines. Computers & Chemical Engineering. 33(1): 244-255.

S. Verron, T. Tiplica, and A. Kobi. 2006. Fault Diagnosis with Bayesian Networks : Application to the Tennessee Eastman Process. IEEE International Conference on Industrial Technology. 98-103.

J. Liu and D.-S. Chen. 2009. Fault Detection and Identification Using Modified Bayesian Classification on PCA Subspace. Industrial and Engineering Chemistry Research. 48(6): 3059-3077.

A. D. Sagale and S. G. Kale. 2014. Hybrid Model For Intrusion Detection Using Naive Bayesian And Support Vector Machine. International Journal of Computing and Technology. 1(3): 56-59.

C. K. Lau, K. Ghosh, M. A. Hussain, and C. R. C. Hassan. 2013. Fault Diagnosis of Tennessee Eastman Process with Multi-scale PCA and ANFIS. Chemometrics and Intelligence Laboratory Systems. 120: 1-14.

K. Feng, Z. Jiang, W. He, and B. Ma. 2011. A Recognition and Novelty Detection Approach Based on Curvelet Transform, Nonlinear PCA and SVM with Application to Indicator Diagram diagnosis. Expert Systems with Applications. 38(10): 12721-12729.

L. H. Chiang, M. E. Kotanchek, and A. K. Kordon. 2004. Fault Diagnosis based on Fisher discriminant Analysis and Support Vector Machines. Computer & Chemical Engineering. 28: 1389-1401.

J. Li and P. Cui. 2009. Improved Kernel Fisher Discriminant Analysis for Fault Diagnosis. Expert Systems with Applications. 36(2): 1423-1432.

H. W. Lee, M. W. Lee, and J. M. Park. 2009. Multi-scale Extension of PLS Algorithm for Advanced On-line Process Monitoring. 2009. Chemometrics and Intelligence Laboratory Systems. 98(2): 201-212.

S. H. Fourie and P. De Vaal. 2000. Advanced Process Monitoring Using an On-lne Non-linear Multiscale Principal Component Analysis Methodology. Computers & Chemical Engineering. 24: 755-760.

A. Hajnayeb, A. Ghasemloonia, S. E. Khadem, and M. H. Moradi. 2011. Application and Comparison of an ANN-based Feature Selection Method and the Genetic Algorithm in Gearbox Fault Diagnosis. Expert Systems with Applications. 38(8): 10205-10209.

H. Keskes, A. Braham, and Z. Lachiri. 2013. Broken Rotor Bar Diagnosis in Induction Machines Through Stationary Wavelet Packet Transform and Multiclass Wavelet SVM. Electric Power Systems Research. 97: 151-157.

J. Yu. 2013. A New Fault Diagnosis Method of Multimode Processes Using Bayesian Inference Based Gaussian Mixture Contribution Decomposition. Engineering Applications of Artificial Intelligence. 26: 456-466.

T. Chen and J. Zhang. 2010. On-line Multivariate Statistical Monitoring of Batch Processes Using Gaussian Mixture Model. Computers & Chemical Engineering. 34: 500-507.

M. H. Gharavian, F. Almas Ganj, A. R. Ohadi, and H. Heidari Bafroui. 2013. Comparison of FDA-based and PCA-based Features in Fault Diagnosis of Automobile Gearboxes. Neurocomputing. 121: 150-159.

J. J. Downs and E. F. Vogel. 1993. A Plant-wide Industrial Process Control Problem. Computers & Chemical Engineering. 17: 245-255.

Y. Liu, L. Ye, P. Zheng, X. Shi, B. Hu, and J. Liang. 2010. Multiscale Classification and Its Application to Process Monitoring. Journal of Zhejiang University-SCIENCE C (Computers & Electronics). 11(6): 425-434.

DOI: http://dx.doi.org/10.11113/jt.v79.11332


  • There are currently no refbacks.

Copyright © 2012 Penerbit UTM Press, Universiti Teknologi Malaysia.
Disclaimer : This website has been updated to the best of our knowledge to be accurate. However, Universiti Teknologi Malaysia shall not be liable for any loss or damage caused by the usage of any information obtained from this web site.
Best viewed: Mozilla Firefox 4.0 & Google Chrome at 1024 × 768 resolution.