A heuristic fault tolerant control for nonlinear MIMO systems using neural networks

Authors:
Jose Noriega
Affiliations:
Departamento de Investigacion en Fisica, Universidad de Sonora, Hermosillo, Sonora, Mexico
Venue:
ICECS'03 Proceedings of the 2nd WSEAS International Conference on Electronics, Control and Signal Processing
Year:
2003

Citing 3
Cited 0

Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy—a survey and some new results

Automatica (Journal of IFAC)
Original Contribution: Adaptive control of dynamic systems by back propagation networks

Neural Networks
Metamodelling: for bond graphs and dynamic systems

Metamodelling: for bond graphs and dynamic systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a fault tolerant control algarithm based on a simple integrater and a neural network model for a multiple-input multiple-output (MIMO) nonlinear system. Two situations are considered. First, the system is working under normal operation parameters and the control vector is computed only by the minimisation of the performance index using the gradient descent rule. Second, assuming that a fault in any actuator gain will degrade the controller performance, a threshold is expected to detect the fault and initiate a fault compensation procedure.