Fault diagnosis for nonlinear systems using a bank of neural estimators

Authors:
A. Alessandri
Affiliations:
ISSIA-CNR Institute of Intelligent Systems for Automation, National Research Council of Italy, Via De Marini 6, 16149 Genova, Italy
Venue:
Computers in Industry - Special issue: Soft computing in industrial applications
Year:
2003

Citing 7
Cited 4

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

Automatica (Journal of IFAC)
Identification of time-varying systems with abrupt parameter changes

Automatica (Journal of IFAC)
Efficient backpropagation learning using optimal learning rate and momentum

Neural Networks
Adaptation and Learning in Automatic Systems

Adaptation and Learning in Automatic Systems
Approximating networks and extended Ritz method for the solution of functional optimization problems

Journal of Optimization Theory and Applications
Bounds on rates of variable-basis and neural-network approximation

IEEE Transactions on Information Theory
Comparison of worst case errors in linear and neural network approximation

IEEE Transactions on Information Theory

Robust fault detection and diagnosis in a class of nonlinear systems using a neural sliding mode observer

International Journal of Systems Science - Advances in Sliding Mode Observation and Estimation (Part Two)
A neural-fuzzy sliding mode observer for robust fault diagnosis

ACC'09 Proceedings of the 2009 conference on American Control Conference
A model-based fault-detection and prediction scheme for nonlinear multivariable discrete-time systems with asymptotic stability guarantees

IEEE Transactions on Neural Networks
Hybrid fault diagnosis of nonlinear systems using neural parameter estimators

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A model-based method to detect faults in nonlinear systems is proposed. Fault diagnosis is accomplished by means of a bank of estimators, which provide estimates of parameters that describe actuator, plant, and sensor faults. These estimators perform according to a receding-horizon strategy and are designed using models of the failures. The problem of designing such estimators for general nonlinear systems is solved by searching for optimal estimation functions. These functions are approximated by feedforward neural networks and the problem is reduced to find the optimal neural weights. The learning can be split into two phases. In the first one, any possible "a priori" knowledge on the statistics of the random variables is used to initialize the neural estimation functions off line. In the second one, the optimization (or training) continues on line. Both off and on line learning rely on stochastic approximation. The performances obtained in the estimation of the fault parameters by the proposed neural estimators and by the extended Kalman filters are compared by means of simulations with an application to underwater robotics.