Fault detection and identification using FIRFMS

Abstract

This paper deals with two of the main tasks of fault monitoring systems (FMS): fault detection and fault identification. During fault detection, the FMS should recognize that the plant behavior is abnormal, and therefore, that the plant is not working properly. During fault identification, the FMS should conclude which type of failure has occurred. The main goal of this work is to present, in the context of the Fuzzy Inductive Reasoning Fault Monitoring System (FIRFMS), a new fault detection technique called enveloping and an enhancement of the fault identification method based on the model acceptability measure. Both contributions allow a more robust and reliable FIRFMS fault detection and identification processes. The enveloping technique and the model acceptability measure are applied to three applications of quite different areas. The first one corresponds to an electric circuit model previously used for such purpose in the literature. The second one is a biomedical system, the human central nervous system (CNS) control. It is the first attempt to apply the FIRFMS to support medical decisions. The third and last one corresponds to a water demand distribution system. The electric circuit is used to show that the enhanced FIRFMS outperforms the previous FIRFMS. The biomedical and water demand distribution systems are presented to show the good performance of the new FIRFMS.

Keywords:

• Fuzzy systems
• Inductive reasoning
• Fault monitoring systems
• Biomedicine
• Water demand

Notes

^§ Tel.: [email protected]

^∥ Tel.: [email protected]

^#The research presented in this paper was supported by the DPI2002-03225 CICYT project.

Additional information

Notes on contributors

Àngela Nebot

§ § Tel.: [email protected]

François E. Cellier

∥ ∥ Tel.: [email protected]