Skip to main content
SpringerLink
Log in

Controllers with diagnostic capabilities. A neural network implementation

  • Published:
Journal of Intelligent and Robotic Systems Aims and scope Submit manuscript

Abstract

Designing controllers with diagnostic capabilities is important as in a feedback control system, detection and isolation of failures is generally affected by the particular control law used. Therefore, a common approach to control and failure diagnosis problems has significant merit. Controllers capable of performing failure diagnosis have additional diagnostic outputs to detect and isolate sensor and actuator faults. A linear such controller is usually called a four-parameter controller. Neural networks have proved to be a very powerful tool in the control systems area, where they have been used in the modelling and control of dynamical systems. In this paper, a neural network model of a controller with diagnostic capabilities (CDC) is presented for the first time. This nonlinear neural controller is trained to operate as a traditional controller, while at the same time it provides reproduction of the failure occurring either at the actuator or the sensor. The cases of actuator and sensor failure are studied independently. The validity of the results is verified by extensive simulations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Antsaklis, P. J., (ed.): Special issue on neural networks in control systems,IEEE Control Systems Magazine 10(3) (1990), 3–87.

    Google Scholar 

  2. Antsaklis, P. J., (ed.): Special issue on neural networks in control systems,IEEE Control Systems Magazine 12(2) (1992), 8–57.

    Google Scholar 

  3. Antsaklis, P. J.: Neural networks for the intelligent control of high autonomy systems,Intelligent Syst. Tech. Report 92-9-1, Department of Electrical Engineering, University of Notre Dame, Sept. 1992.

  4. Ferrada, J. J., Gordon, M. D., and Osborne-Lee, I. W.: Application of neural networks for fault diagnosis in plant production,AIChE Annual Meeting, San Francisco, CA, Nov. 1989, Paper 87a.

  5. Hertz, J., Krogh, A., and Palmer, R. G.:Introduction to the Theory of Neural Computation, Lecture Notes Vol. I, Santa Fe Institute Studies in the Sciences of Complexity, Addison-Wesley, Redwood City, CA, 1991.

    Google Scholar 

  6. Hoskins, J. C., and Himmelblau, D. M.: Artificial neural network models of knowledge representation in chemical engineering,Computers Chem. Eng. 12(9/10) (1988), 881–890.

    Google Scholar 

  7. Hou, Z.: Analysis of auto powertrain dynamics and modelling using neural networks, M.Sc. Thesis, Department of Electrical Engineering, University of Notre Dame, Feb. 1992.

  8. Jacobson, C. A., and Nett, C. N.: An integrated approach to controls and diagnostics using the four parameter controller,IEEE Control Systems Magazine 11(6) (1991), 22–29.

    Google Scholar 

  9. Juarez, A. E., Ajbar, A., and Kantor, J. C.: Multivariable control with integrated diagnostics for chemical processes,Proc. Systems Eng. PSE 91, Quebec, 1991.

  10. Konstantopoulos, I. K.: Controller design with failure diagnostic capabilities via neural networks, M.Sc. Thesis, Department of Electrical Engineering, University of Notre Dame, Nov. 1992.

  11. Konstantopoulos, I. K., and Antsaklis, P. J.: The four-parameter controller. A neural network implementation, in:Proc. IEEE Mediterranean Symp. on New Directions in Control Theory and Applications, Chania, Crete, Greece, June 21–23, 1993.

  12. Leonard, J. A., and Kramer, M. A.: Classifying process behavior with neural networks: Strategies for improved training and generalization, in:Proc. 1990 Amer. Control Conf., San Diego, CA, May 1990, pp. 2478–2483.

  13. Naidu, S. R., Zafiriou, E., and McAvoy, T.: Use of neural networks for sensor failure detection in a control system,IEEE Control Systems Magazine 10(3) (1990), 49–55.

    Google Scholar 

  14. Narendra, K. S., and Parthasarathy, K.: Identification and control of dynamical systems using neural networks,IEEE Trans. Neural Networks 1(1) (1990), 4–27.

    Google Scholar 

  15. Nett, C. N.: Algebraic aspects of linear control system stability,IEEE Trans. Automatic Control AC-31(10) (1986), 941–949.

    Google Scholar 

  16. Nett, C. N., Jacobson, C. A., and Miller, A. T.: An integrated approach to controls and diagnostics: The 4-parameter controller, in:Proc. 1988 Amer. Control Conf., Atlanta, GA, June 1988, pp. 824–835.

  17. Rumelhart, D. E., Hinton, G. J., and Williams, R.: Learning internal representations by error propagation, in D. E. Rumelhart and J. L. McClelland (eds),Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1:Foundation, MIT Press, Cambridge, MA, 1986, pp. 318–362.

    Google Scholar 

  18. Sartori, M. A.: Feedforward neural networks and their application in the higher level control of systems, Ph.D. Dissertation, Department of Electrical Engineering, University of Notre Dame, April 1991.

  19. Sartori, M. A., and Antsaklis, P. J.: Failure behavior identification for a space antenna via neural networks, in:Proc. 1992 Amer. Control Conf., Chicago, IL, June 1992, pp. 567–568.

  20. Valavanis, K. P., Jacobson, C. A., and Gold, B.: An application of the 4-parameter controller to the robot payload variation problem, in:Proc. 28th Conf. on Decision and Control, Tampa, FL, December 1989, pp. 2658–2663.

  21. Valavanis, K. P., Jacobson, C. A., and Gold, B.: Integration control and failure detection with application to the robot payload variation problem,J. Intelligent and Robotic Systems 4 (1991), 145–173.

    Google Scholar 

  22. Vidyasagar, M.:Control System Synthesis: A Factorization Approach, MIT Press, Cambridge, MA, 1985.

    Google Scholar 

  23. Warwick, K., Irwin, G. W., and Hunt, K. J. (eds):Neural Networks for Control and Systems, IEE Control Engineering Series, Peter Peregrinus, London, 1992.

    Google Scholar 

  24. Watanabe, K., Matsuura, I., Abe, M., and Kubota, M.: Incipient Fault Diagnosis of chemical processes via artificial neural networks,AIChE J. 35(11) (1989), 1803–1812.

    Google Scholar 

  25. Wu, X., and Cinar, A.: Reliable process control by 4-parameter controllers, in:Proc. 1991 Amer. Control Conf., Boston, MA, June 1991, pp. 1860–1865.

  26. Yao, S. C., and Zafiriou, E.: Control system sensor failure detection via networks of localized receptive fields, in:Proc. 1990 Amer. Control Conf., San Diego, CA, May 1990, pp. 2472–2477.

Download references

Author information

Authors and Affiliations

  1. Department of Electrical Engineering, University of Notre Dame, 46556, Notre Dame, IN, USA

    Ioannis K. Konstantopoulos & Panos J. Antsaklis

Authors
  1. Ioannis K. Konstantopoulos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Panos J. Antsaklis
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Panos J. Antsaklis.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Konstantopoulos, I.K., Antsaklis, P.J. Controllers with diagnostic capabilities. A neural network implementation. J Intell Robot Syst 12, 197–228 (1995). https://doi.org/10.1007/BF01262961

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01262961

Key words

Search

Navigation