Abstract
The objective of this work was to develop the novel approach for fault detection using neural network in industrial actuator for DAMADICS benchmark case. This neural network model has the ability to produce effective result for fault detection. In this paper, a model-based technique is proposed for the residual generation which results from the deviation of fault-free behavior of actuator from faulty behavior on actuator. The actuator is the multi-input–multi-output (MIMO) system which is designed using four kinds of neural network architectures (NNARX, NNARMAX, NNRARX, and feed forward), and best structure is chosen based on performance indices. The actuator faults can be grouped using k-means clustering technique. This technique is applied to the DAMADICS benchmark case.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
C.D. Bocaniala, Sa da Costa.: application of a novel fuzzy classifier to fault detection and isolation of DAMADICS benchmark problem. Control Eng. Pract. 14(6), 653–669 (2006)
J.J. Gertler, Fault Detection and Diagnosis in Engineering Systems (Marcel Dekker Inc, New York, 1998)
Y. Kourd, Guersi, N., Lefebvre, D.: Neuro-fuzzy approach for fault diagnosis: application to the DAMADICS, in Proceedings of ICINCO 2010 (2010)
R. Sundarmahesh, B. Kannapiran, Fault diagnosis of pneumatic valve with DAMADICS simulator using ANN based classifier approach. Int. J. Comput. Appl. 11–17 (2013)
K. Prabakaran, U. Mageshwari, D. Prakash, A. Suguna, Fault diagnosis in process control valve using artificial neural network. Int. J. Innov. Appl. Stud. 3(1), 138–144 (2013)
J. Chen, R.J. Patton, Robust Model-Based Fault Diagnosis for Dynamic Systems (Kluwer Academic Publishers, Dordrecht, 1999)
S. Haykin, Neural networks. A comprehensive foundation (1999)
Y. Kourd, D. Lefebvre, N. Guersi, Early FDI based on residuals design according to the analysis of models of faults: application to DAMADIC. Hindawi Publishing Corporation Advances in Artificial Neural (2011), pp. 1–10
R. Isermann, Process fault detection based on modeling and estimation method-a survey. Automatica 20, 387–404 (1984)
Y. Kourd, D. Lefebvre, N. Guersi.: Fault diagnosis based on neural networks and decision trees: application to Samadics. Int. J. Innov. Comput. Inf. Control 9(8) (2013)
M. Bartys, R. Patton, M. Syfert, S. De las Heras, J. Quevedo, Introduction to the DAMADICS actuator FDI benchmark study. Control Eng. Pract. 14, 577–596 (2006)
M. Syfert, M. Bartys, J. Quevedo, Benchmark definition. http://diag.mchtr.pw.edu.pl/damadics (2002)
R. Isermann, Fault Diagnosis Systems: An Introduction from Fault Detection to Fault Tolerance (Springer, New York, 2006)
H. Demuth, M. Beale, Neural network toolbox for use with MATLAB. User’s Guide Version 3
C. Boutsidis, M.W. Mahoney, Unsupervised Feature Selection for the k-means Clustering Problem
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer India
About this paper
Cite this paper
Elakkiya, V., Ram Kumar, K., Gomathi, V., Rakesh Kumar, S. (2015). Investigation of Fault Detection Techniques for an Industrial Pneumatic Actuator Using Neural Network: DAMADICS Case Study. In: Suresh, L., Dash, S., Panigrahi, B. (eds) Artificial Intelligence and Evolutionary Algorithms in Engineering Systems. Advances in Intelligent Systems and Computing, vol 324. Springer, New Delhi. https://doi.org/10.1007/978-81-322-2126-5_27
Download citation
DOI: https://doi.org/10.1007/978-81-322-2126-5_27
Published:
Publisher Name: Springer, New Delhi
Print ISBN: 978-81-322-2125-8
Online ISBN: 978-81-322-2126-5
eBook Packages: EngineeringEngineering (R0)