A new method for sensor fault detection, isolation and accommodation
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 488-492
- https://doi.org/10.1109/imtc.1999.776799
Abstract
In this paper a framework for an intelligent sensor with real-time diagnosis and rectification is proposed. It is based on the combination of recurrent neural networks and the information fusion technique. The architecture is constructed to perform sensor detection, isolation and accommodation, along with description of recurrent neural networks and multisensory information fusion. Simulation results show good performance on the application to some type airplane Author(s) Yong Liu Dept. of Control. Sci., Harbin Inst. of Technol., China Yi Shen ; Hengzhang HuKeywords
This publication has 3 references indexed in Scilit:
- Sensor value validation based on systematic exploration of the sensor redundancy for fault diagnosis KBSIEEE Transactions on Systems, Man, and Cybernetics, 1994
- Training recurrent neural networks: why and how? An illustration in dynamical process modelingIEEE Transactions on Neural Networks, 1994
- Real Time Fault Monitoring of Industrial ProcessesPublished by Springer Science and Business Media LLC ,1994