Fault Diagnosis of an Air-Conditioning System Using LS-SVM

  • Mahendra Kumar
  • I. N. Kar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5909)

Abstract

This paper describes fault diagnosis of an air-conditioning system for improving reliability and guaranteeing the thermal comfort and energy saving. To achieve this goal, we proposed a technique which is model based fault diagnosis technique. Here, a lumped parameter model of an air-conditioning system is considered and then characteristics of twelve faults are investigated in an air-conditioning system provided in passenger coach of an Indian Railway. Based on the variations of the system states under normal and faulty conditions of different degrees, the faults can be detected efficiently by using residual analysis method. The residual code is obtained through simple threshold testing of residuals, which are the output of a general scheme of residual generators. The pattern of residual is classified by using multi-layer LS-SVM classification. The diagnosis results show that LS-SVM classifier is effective with very high accuracy.

Keywords

LS-SVM Residuals generator Air-Conditioning System FDD 

References

  1. 1.
    Kumar, M., Kar, I.N., Ray, A.: State Space based Modelling and Performance Evaluation of air-conditioning system. International Journal of HVAC & R Research 14(5) (September 2008)Google Scholar
  2. 2.
    Liang, J., Du, R.: Model-based fault detection and diagnosis of HVAC systems using Support Vector Machine method. International Journal of refrigeration 30, 1104–1114Google Scholar
  3. 3.
    Pau-Lo-Hsu, Lin, K.-L., Shen, L.-C.: Diagnosis of Multiple Sensor and Actuator Failures in Automotive Engines. IEEE Transactions on Vehicular Technology 44(4) (November 1995)Google Scholar
  4. 4.
    Stoecker, W.F., Jones, J.W.: Refrigeration & Air conditioning. McGraw-Hill Book Company, New York (1982)Google Scholar
  5. 5.
    The Math Works, Inc., MATLAB. The Math Works, Inc., Natick, Massachusetts (2007)Google Scholar
  6. 6.
    Katipamula, S., Brambley, M.R.: Methods for fault detection, diagnostics, and prognostics for building systems-a review, part I. International Journal of HVAC&R Research 11, 3–25 (2005)Google Scholar
  7. 7.
    Du, R.: Monitoring and Diagnosis of Sheet Metal Stamping Processes. In: Gao, R., Wang, L.H. (eds.) Condition-based Monitoring and Control for Intelligent Manufacturing. Springer, New York (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Mahendra Kumar
    • 1
  • I. N. Kar
    • 2
  1. 1.Working as Deputy Chief Electrical Engineer in Northern RailwayDelhi
  2. 2.Department of Electrical EngineeringIndian Institute of TechnologyDelhi

Personalised recommendations