Neural Network Based Diagnosis Method for Looper Height Controller of Hot Strip Mills
ICICIC '06 Proceedings of the First International Conference on Innovative Computing, Information and Control - Volume 3
Editorial: Hybrid learning machines
Neurocomputing
Logic-oriented neural networks for fuzzy neurocomputing
Neurocomputing
Towards Robustness in Neural Network Based Fault Diagnosis
International Journal of Applied Mathematics and Computer Science - Issues in Fault Diagnosis and Fault Tolerant Control
Information Sciences: an International Journal
Editorial: Hybrid intelligent algorithms and applications
Information Sciences: an International Journal
Efficient plant supervision strategy using NN based techniques
HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part I
FDI and accommodation using NN based techniques
HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part I
Hi-index | 0.00 |
Most nonlinear processes suffer from lack of detectability when model based techniques are applied to IFDI (intelligent fault detection and isolation) tasks. Generally, all types of nonlinear processes will also suffer from lack of detectability due to the inherent ambiguity in discerning faults in the process, sensors and/or actuators. This work deals with a strategy to detect and isolate process and/or sensor faults by combining neural networks based on functional approximation procedures associated with recursive rule using techniques for a parity space approach. For this work, a case study dealing with the supervision of a solar volumetric receiver was performed using the proposed intelligent techniques, and produced reliable and acceptable IFDI results.