Modelling for fault detection and isolation versus modelling for control
Mathematics and Computers in Simulation - Special issue on 3rd IMACS Symposium on Mathematical Modelling — 3rd MATHMOD Vienna
Use of Autoassociative Neural Networks for Signal Validation
Journal of Intelligent and Robotic Systems
Fuzzy systems design: direct and indirect approaches
Soft Computing - A Fusion of Foundations, Methodologies and Applications
Research on the Application of Neural Network in Diaphragm Icing Sensor Fault Diagnosis
ISNN '09 Proceedings of the 6th International Symposium on Neural Networks on Advances in Neural Networks
An approach to online identification of Takagi-Sugeno fuzzy models
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Information Sciences: an International Journal
Quantifying the reliability of fault classifiers
Information Sciences: an International Journal
Hi-index | 0.07 |
Sensors are indispensable components of modern plants and processes and their reliability is vital to ensure reliable and safe operation of complex systems. In this paper, the problem of design and development of a data-driven Multiple Sensor Fault Detection and Isolation (MSFDI) algorithm for nonlinear processes is investigated. The proposed scheme is based on an evolving multi-Takagi Sugeno framework in which each sensor output is estimated using a model derived from the available input/output measurement data. Our proposed MSFDI algorithm is applied to Continuous-Flow Stirred-Tank Reactor (CFSTR). Simulation results demonstrate and validate the performance capabilities of our proposed MSFDI algorithm.