A GMDH Neural Network Based Approach to Passive Robust Fault Detection using a Constraints Satisfaction Backward Test
| Authors: | Puig Vicenç, Universitat Politècnica de Catalunya, Spain
Mrugalski Marcin, University of Zielona Góra, Poland
Ingimundarson Ari, Universitat Politècnica de Catalunya, Spain
Quevedo Joseba, Universitat Politècnica de Catalunya, Spain
Witczak Marcin, University of Zielona Góra, Poland
Korbicz Jozef, University of Zielona Góra, Poland |
|---|
| Topic: | 6.4 Safeprocess |
|---|
| Session: | Fusion of Analytical and Soft Computing Methods in Fault Diagnosis |
|---|
| Keywords: | Fault Detection, Fault Diagnosis, Robustness, Adaptive Threshold, Neural Network. |
|---|
Abstract
This paper focus on the problem of passive robust fault detection using non-linear models that include parameter uncertainty. The non-linear model considered here is described by a Group Method of Data Handling (GMDH) neural network. The problem of passive robust fault detection using models including parameter uncertainty has been mainly addressed checking if the measured behaviour is inside the region of possible behaviours following what will be called in the following a forward test. In this paper, a backward test based on checking if there exist a parameter in the uncertain parameter set that is consistent with the measured behaviour is introduced. This test is implemented using interval constraint satisfaction algorithms. Finally, this approach is tested on the servoactuator proposed as a FDI benchmark in the European Project DAMADICS.
