Journal Home > Volume 20 , Issue 2
Tsinghua Science and Technology 2015, 20(2): 200-204 https://doi.org/10.1109/TST.2015.7085633
Open Access | Issue | Published: 23 April 2015

Design of Fault Detection Observer Based on Hyper Basis Function

Show Author's Information Xin Wen( ),  Xingwang Zhang,  Yaping Zhu
Faculty of Aerospace Engineering, Shenyang Aerospace University, Shenyang 110136, China
College Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Keywords:
neural networks, observer, fault detection, hyper basis function
Cite this article:
Wen X, Zhang X, Zhu Y. Design of Fault Detection Observer Based on Hyper Basis Function. Tsinghua Science and Technology, 2015, 20(2): 200-204. https://doi.org/10.1109/TST.2015.7085633
Download citation
EndNote(RIS)
BibTeX

414

Views

20

Downloads

Citations

7

Crossref

N/A

WoS

10

Scopus

3

CSCD

Abstract Full text About this article

In this paper, we propose the Hyper Basis Function (HBF) neural network on the basis of Radial Basis Function (RBF) neural network. Compared with RBF, HBF neural networks have a more generalized ability with different activation functions. A decision tree algorithm is used to determine the network center. Subsequently, we design an adaptive observer based on HBF neural networks and propose a fault detection and diagnosis method based on the observer for the nonlinear modeling ability of the neural network. Finally, we apply this method to nonlinear systems. The sensitivity and stability of the observer for the failure of the nonlinear systems are proved by simulation, which is beneficial for real-time online fault detection and diagnosis.


menu
Abstract
Full text
Outline
About this article

Design of Fault Detection Observer Based on Hyper Basis Function

Show Author's information Xin Wen( ), Xingwang Zhang, Yaping Zhu
Faculty of Aerospace Engineering, Shenyang Aerospace University, Shenyang 110136, China
College Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

Abstract

In this paper, we propose the Hyper Basis Function (HBF) neural network on the basis of Radial Basis Function (RBF) neural network. Compared with RBF, HBF neural networks have a more generalized ability with different activation functions. A decision tree algorithm is used to determine the network center. Subsequently, we design an adaptive observer based on HBF neural networks and propose a fault detection and diagnosis method based on the observer for the nonlinear modeling ability of the neural network. Finally, we apply this method to nonlinear systems. The sensitivity and stability of the observer for the failure of the nonlinear systems are proved by simulation, which is beneficial for real-time online fault detection and diagnosis.

Keywords: neural networks, observer, fault detection, hyper basis function

References(18)

[1]
Song, H. Zhang, H. Y. and Wang, X. R. Fault detection approach based on fuzzy observer for uncertain nonlinear systems, (in Chinese), Aerospace Control, vol. 23, no. 3, pp. 74-78, 2005.
Google Scholar
[2]
Zhu, X. H. Li, Y. H. Li, N. and Han, J. D. Novel observer-based robust fault detection method for nonlinear uncertain systems, (in Chinese), Control Theory & Applications, vol. 30, no. 5, pp. 644-648, 2013.
Google Scholar
[3]
Gao, L. E. Liu, W. D. and Lu, Y. Failure diagnose observer design and simulation for X-type rudder plane of underwater vehicle, (in Chinese), Journal of Projectiles, Rockets, Missiles and Guidance, vol. 28, no. 4, pp. 222-224, 2008.
Google Scholar
[4]
Zarei J. and Shokri, E. Robust sensor fault detection based on nonlinear unknown input observer, Measurement, vol. 48, no. 2, pp. 355-367, 2014.
DOI Google Scholar
[5]
Wang, Z. H. Zhang, M. and Shen, Y. Actuator fault detection and isolation for the attitude control system of satellite, (in Chinese), Journal of Harbin Institute of Technology, vol. 45, no. 2, pp. 72-76, 2013.
Google Scholar
[6]
Song, Y. Q. Zhang, W. G. and Liu, X. X. Fault diagnosis based on RBF neural network observer in flight control system, (in Chinese), Computer Simulation, vol. 27, no. 3, pp. 85-88, 2010.
Google Scholar
[7]
Du, Z. M. Fan, B. Chi, J. L. and Jin, X. Q. Sensor fault detection and its efficiency analysis in air handling unit using the combined neural networks, Energy and Buildings, no. 72, pp. 157-166, 2014.
DOI Google Scholar
[8]
Vanini, Z. N. S. Khorasani, K. and Meskin, N. Fault detection and isolation of a dual spool gas turbine engine using dynamic neural networks and multiple model approach, Information Sciences, no. 259, pp. 234-251, 2014.
DOI Google Scholar
[9]
Schwenker, F. Kestler, H. A. and Palm, G. Three learning phases for radial-basis-function networks, Neural Networks, vol. 14, nos. 4&5, pp. 439-458, 2001.
DOI Google Scholar
[10]
Adhyaru, D. M. State observer design for nonlinear systems using neural network, Applied Soft Computing, vol. 12, no. 8, pp. 2530-2537, 2012.
DOI Google Scholar
[11]
Wu, H. W. Dai, Q. H. Wang, P. and Li, Y. D. Neural-network-based observers for nonlinear systems, (in Chinese), Journal of Tsinghua University (Science and Technology), vol. 40, no. 3, pp. 44-47, 2000.
Google Scholar
[12]
Valls, J. M. Aler, R. and Fernandez, O. Using a Mahalanobis-like distance to train radial basis neural networks, Computational Intelligence and Bioinspired Systems, vol. 12, no. 8, pp. 2530-2537, 2012.
Google Scholar
[13]
Vorobyov S. A. and Cichocki, A. Hyper radial basis function neural networks for interference cancellation with nonlinear processing of reference signal, Digital Signal Processing, vol. 11, no. 3, pp. 204-221, 2001.
DOI Google Scholar
[14]
Vukovic N. and Miljkovic, Z. A growing and pruning sequential learning algorithm of hyper basis function neural network for function approximation, Neural Networks, vol. 46, no. 10, pp. 220-226, 2013.
DOI Google Scholar
[15]
Li, A. J. Luo, S. W. Huang, H. and Liu, Y. H. Decision tree based neural network design, (in Chinese), Journal of Computer Research and Development, vol. 2, no. 8, pp. 1312-1317, 2005.
DOI Google Scholar
[16]
Xu, Z. C. Zhou, Y. G. and Yu, F. M. Design of observers for nonlinear systems based on improved neural-network, (in Chinese), Microcomputer & Its Applications, vol. 30, no. 8, pp. 76-78, 2011.
Google Scholar
[17]
Shaik, F. A. Purwar, S. and Pratap, B. Real-time implementation of Chebyshev neural network observer for twin rotor control system, Expert Systems with Applications, vol. 38, no. 10, pp. 13 043-13 049, 2011.
DOI Google Scholar
[18]
Wen, X. Wang, Q. Qian, F. and Zhang, H. Y. Method of state observer design and fault detection, (in Chinese), Journal of Beijing University of Aeronautics and Astronautics, vol. 24, no. 6, pp. 676-679, 1998.
Google Scholar
Publication history
Copyright
Rights and permissions

Publication history

Received: 30 September 2014
Revised: 17 November 2014
Accepted: 05 January 2015
Published: 23 April 2015
Issue date: April 2015

Copyright

© The author(s) 2015

Rights and permissions

Return