Designing neural-network-based fault detection systems with D-optimum experimental conditions

  • Marcin Witczak University of Zielona Góra
  • Przemysław Prętki University of Zielona Góra

Abstract

The paper deals with an application of the theory of optimum experimental design to the problem of selecting the data set for developing neural models. Another objective is to show how to design a robust fault detection scheme with neural networks and how to increase its fault sensitivity by decreasing model uncertainty. It is also shown that the optimum design is independent of the parameters that enter linearly into the neural network. The final part of this paper shows a comprehensive simulation study regarding modelling and fault detection with the proposed approach. In particular, the DAMADICS benchmark problem is utilized to verify the performance and reliability of the proposed technique.

Keywords

References

[1] A.C. Atkinson and A.N. Donev. Optimum Experimental Designs. Oxford University Press. New York 1992.
[2] J. Chen and R. J. Patton. Robust Model-based Fault Diagnosis for Dynamic Systems. Kluwer Academic Publishers.
London 1999.
[3] M.H. ChoueikiTraining data development with D-optimality criterion. IEEE Trans. Neural Networks, 10 (1):
56- 63, 1999.
[4] G. Chryssolouris, M. Lee and A. Ramsey. Confidence interval prediction for neural network models. IEEE Trans.
Neural Networks, 7 (1): 229-232, 1996.
[5] DAMADICS (2004): Website of the Research Training Network DAMADICS: Development and Application of
Methods for Actuator Diagnosis in Industrial Control Systems. http://diag.mchtr.pw.edu.pl/damadics/.
Published
Nov 30, 2022
How to Cite
WITCZAK, Marcin; PRĘTKI, Przemysław. Designing neural-network-based fault detection systems with D-optimum experimental conditions. Computer Assisted Methods in Engineering and Science, [S.l.], v. 12, n. 2-3, p. 279-291, nov. 2022. ISSN 2956-5839. Available at: <https://cames.ippt.pan.pl/index.php/cames/article/view/996>. Date accessed: 03 july 2024.
Section
Articles