Abstract
This paper shows an approach to use a Neural Network trained by the classic backpropagation algorithm for solving the problem of fault detection and isolation (FDI) of simple mechanisms subject to failures in actuators. The approach taken was to reserve the term of the projection of the tuning algorithm used for keeping bounded the weight, and use it at the time of the fault. Works like Vemuri et.al. [12], where faults are focused in the inertia matrix and the isolation technique does not show clearly the results it aims, were the inspiration for this research. Here the fault is modelled as a torque suddenly bounded at first actuator and a neural network of two layers is used with an adaptive law whose projection operation is a reserved degree of freedom for keeping the system under control.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anzurez-Marin, J., Cuevas-Silva, O., Pitalúa-Díaz, N.: The fault diagnosis problem: residual generators design using neural networks in a two-tanks interconnected system. In: Electronics, Robotics and Automotive Mechanics Conference (2009)
De Persis, C., Isidori, A.: A geometric approach to nonlinear fault detection and isolation. IEEE Trans. Autom. Control 46(6), 853–865 (2001)
Beard, R.V.: Failure accomodation in linear systems through self-reorganization. Ph.D. dissertation, Massachusetts Institute Technology, Cambridge (1971)
Czajkowski, A., Patan, K.: Design of predective fault tolerant control by the means of state space neural networks. In: 24th Mediterranean Conference on Control and Automation, Athens, Greece, June 2016
Czajkowski, A., Luzar, M., Witczak, M.: Robust multi-model fault detection and isolation with a state-space neural network. In: 24th Mediterranean Conference on Control and Automation, Athens, Greece, June 2016
Gertler, J.: All linear methods are equal and extendible to (some) nonlinearities. Int. J. Robust Nonlinear Control 12, 629–648 (2002)
Hwang, I., Kim, S., Kim, Y., Seah, C.E.: A survey of fault detection, isolation, and reconfiguration methods. IEEE Trans. Control Syst. Technol. 18(3), 636–653 (2010)
Ioannou, P.A., Sun, J.: Stable and Robust Adaptive Control. Prentice-Hall, Englewood Cliffs (1995)
Jones, H.L.: Failure detection in linear systems. Ph.D. dissertation, Massachusetts Institute Technology, Cambridge (1973)
Lewis, F.L., Jagannathan, S., Yeşildirek, A.: Neural Network Control of Robot Manipulators and Nonlinear Systems. Taylor & Francis, London (1999)
Massoumnia, M.A.: A geometric approach to the synthesis of failure detection filters. IEEE Trans. Autom. Control 31, 839–846 (1986)
Vemuri, A.T., Polycarpou, M.M., Diakourtis, S.A.: Neural network based fault detection in robotic manipulators. IEEE Trans. Robot. Autom. 14(2), 342–348 (1998)
Talebi, H.A., Khorasani, K.: A neural network-based multiplicative actuator fault detection and isolation of nonlinear systems. IEEE Trans. Control Syst. Technol. 21(3), 842–851 (2013)
White, D.A., Sofge, D.A.: Handbook of Intelligent Control: Neural, Fuzzy and Adaptive Approaches. Van Nostrand Reinhold, New York (1993)
Yen, G.G.: Reconfigurable learning control in large space structures. IEEE Trans. Control Syst. Technol. 2, 362–370 (1994)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Esquivel, J.A., Díaz, J.A., Carrera, I., Moreno, H. (2017). Neural Networks for FDI on the First Actuator of a Two-Link Planar Manipulator. In: Chang, I., Baca, J., Moreno, H., Carrera, I., Cardona, M. (eds) Advances in Automation and Robotics Research in Latin America. Lecture Notes in Networks and Systems, vol 13. Springer, Cham. https://doi.org/10.1007/978-3-319-54377-2_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-54377-2_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-54376-5
Online ISBN: 978-3-319-54377-2
eBook Packages: EngineeringEngineering (R0)