Confidence estimation of the multi-layer perceptron and its application in fault detection systems

Authors:
Marcin Mrugalski;Marcin Witczak;Józef Korbicz
Affiliations:
Institute of Control and Computation Engineering, University of Zielona Góra, ul. Podgórna 50, 65-246 Zielona Góra, Poland;Institute of Control and Computation Engineering, University of Zielona Góra, ul. Podgórna 50, 65-246 Zielona Góra, Poland;Institute of Control and Computation Engineering, University of Zielona Góra, ul. Podgórna 50, 65-246 Zielona Góra, Poland
Venue:
Engineering Applications of Artificial Intelligence
Year:
2008

Citing 7
Cited 3

Robust model-based fault diagnosis for dynamic systems

Robust model-based fault diagnosis for dynamic systems
Fault Diagnosis: Models, Artificial Intelligence, Applications

Fault Diagnosis: Models, Artificial Intelligence, Applications
Artificial intelligence for monitoring and supervisory control of process systems

Engineering Applications of Artificial Intelligence
A hybrid neural network model for rule generation and its application to process fault detection and diagnosis

Engineering Applications of Artificial Intelligence
Modelling and Estimation Strategies for Fault Diagnosis of Non-Linear Systems: From Analytical to Soft Computing Approaches

Modelling and Estimation Strategies for Fault Diagnosis of Non-Linear Systems: From Analytical to Soft Computing Approaches
Issues of Fault Diagnosis for Dynamic Systems

Issues of Fault Diagnosis for Dynamic Systems
Confidence estimation methods for neural networks: a practical comparison

IEEE Transactions on Neural Networks

Early FDI based on residuals design according to the analysis of models of faults: application to DAMADICS

Advances in Artificial Neural Systems
Robust sensor and actuator fault diagnosis with GMDH neural networks

IWANN'13 Proceedings of the 12th international conference on Artificial Neural Networks: advances in computational intelligence - Volume Part I
Passive robust fault detection using RBF neural modeling based on set membership identification

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an identification method based on artificial neural networks, which can be used for the robust fault detection. In particular, a problem of the multi-layer perceptron neural network uncertainty estimation with application of the outer bounding ellipsoid algorithm is considered. The mathematical description of the model uncertainty enables designing robust fault detection system, which effectiveness was verified with the DAMADICS benchmark.