Advertisement

Neural Network Based Model for Fault Diagnosis of Pneumatic Valve with Dimensionality Reduction

  • P. Subbaraj
  • B. Kannapiran
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7076)

Abstract

Fault detection and diagnosis of pneumatic valve used in cooler water spray system in cement industry is of great practical significance and paramount importance for the continued operation of the plant. This paper presents the design and development of Artificial Neural Network (ANN) based model for the fault detection of pneumatic valve in cooler water spray system in cement industry. Principal component analysis (PCA) is applied to reduce the input dimension. The training and testing data required for the development of ANN is generated in a laboratory grade experimental setup. The performance of the developed model is compared with the network trained with the original variables without any dimensionality reduction. From the comparison it is observed that the classification performance of the neural network has been improved due to the application of PCA and the training time of the neural network is reduced.

Keywords

Artificial Neural Network Dimensionality Reduction Fault Detection Neural Network Model Artificial Neural Network Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bayir, S.R., Bay, O.F.: Serial wound starter motor faults diagnosis using artificial neural network. In: IEEE ICM 2004, Istanbul, pp. 194–199 (2004)Google Scholar
  2. 2.
    Chang, Y.-W., Wang, Y.-C., Liu, T., Wang, Z.-J.: Fault diagnosis of a mine hoist using PCA and SVM techniques. Int. J. China Univ. Mining and Technology 18, 327–331 (2008)CrossRefGoogle Scholar
  3. 3.
    Demetgul, M.: Experiment based fault diagnosis on bottle filling plant with LVQ artificial neural network algorithm. Journal of Engineering Science 14, 92–100 (2008)Google Scholar
  4. 4.
    de Moura, E.P., Souto, C.R., Silva, A.A., Irmao, M.A.S.: Evaluation of principal component analysis and neural network performance for bearing fault diagnosis from vibration signal processed by RS and DF analyses. Journal of Mech. Systems and Signal Processing (2010)Google Scholar
  5. 5.
    Devaraj, D., Murthy, N., Yegnanarayana, B.: A fuzzy system model for plant condition monitoring. In: ASME International Conference, pp. 210–214 (1999)Google Scholar
  6. 6.
    Isermann, R.: Supervision, fault detection and fault diagnosis methods-an introduction. Int. J. Control Engineering Practice 5(5), 639–652 (1997)CrossRefGoogle Scholar
  7. 7.
    Isermann, R., Balle, P.: Trends in the application of Model-based fault detection and diagnosis of technical process. Int. J. Control Engineering Practice 5(5), 709–719 (1997)CrossRefGoogle Scholar
  8. 8.
    Karpenko, M., Sepehri, N.: Neural network classifiers applied to condition monitoring of a pneumatic process valve actuator. Engineering Applications of Artificial Intelligence 15(3-4), 273–283 (2002)CrossRefGoogle Scholar
  9. 9.
    Karpenko, M., Sepehri, N., Scuse, D.: Diagnosis of process valve actuator faults using a multilayer neural network. Control Engineering Practice 11(11), 1289–1299 (2003)CrossRefGoogle Scholar
  10. 10.
    Koj, J.: The Fault Sources of Pneumatic Servo-Motor-Control Valve Assembly. In: Proceedings of the III Polish Nat. Conf. on Diagnosis of Industrial Processes, Jurata, Poland, pp. 415–419 (1998)Google Scholar
  11. 11.
    Leonhardt, S., Ayoubi, M.: Methods of Fault diagnosis. Int. J. Control Engineering Practice 5(5), 683–692 (1997)CrossRefGoogle Scholar
  12. 12.
    Louro, R.: Fault Diagnosis of an Industrial Actuator Valve. MSc Dissertation, Technical University of Lisbon, Portugal (2003)Google Scholar
  13. 13.
    Rajakarunakaran, S., Venkumar, P., Devaraj, D., Rao, K.S.P.: Artificial neural network approach for fault detection in rotary system. Applied Soft Computing 8, 740–748 (2008)CrossRefGoogle Scholar
  14. 14.
    Seong, S.H., Hur, S., Kim, J.S., Kim, J.T., Park, W.M., Lee, U.C.: Development of diagnosis algorithm for the check valve with spectral estimations and neural network models using acoustic signals. Annals of Nuclear Energy 32, 479–492 (2005)CrossRefGoogle Scholar
  15. 15.
    Bouhouche, S., Yahi, M., Bast, J.: Combined use of principal component analysis and Self organisation map for condition monitoring in pickling process. Applied Soft Computing 11, 3075–3082 (2011)CrossRefGoogle Scholar
  16. 16.
    Subbaraj, P., Kannapiran, B.: Artificial Neural Network Approach for Fault Detection in Pneumatic Valve in Cooler Water Spray System. Int. Journal of Comp. Applications 9(7), 975–8887 (2010)Google Scholar
  17. 17.
    Venkatasubramanian, V.: A Review of Process Fault Detection and Diagnosis Part I, II & III. Computers and Chemical Engineering (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • P. Subbaraj
    • 1
  • B. Kannapiran
    • 2
  1. 1.Sri Nandhanam College of Engineering and TechnologyVellore DistrictIndia
  2. 2.Department of Instrumentation & Control EngineeringArulmigu Kalasalingam college of EngineeringVirudunagar DistrictIndia

Personalised recommendations