Copyright © IFAC Fault Detection, Supervision and Safety for Technical Processes, Kingston Upon Hull, UK, 1997 DECISION-MAKING APPROACHES FOR A MODEL-BASED FDI METHOD. Luis Javier de Miguel* Margarita Mediavilla * Jose R. Peran· • fdi@dali.eis.uva .es lnstituto de Tecnologias A vanzadas de la Producci6n , Universidad de Valladolid. Spain Abstract: This paper describes three ways of building a decision system for quantitative model-based fault diagnosis. Some clues are given to apply the method to qualitative model-based FDI. The aim is the management of uncertain and redundant information provided by a residual generator. Although any residual generation method may be considered , the input-output parity equation approach has been used . The key point is the fault sensitivity estimations of the residuals, which lead to define the decision rules. In the case of sensor and actuator faults: sensitivity estimates are easily obtainable from the parity equations. Three ways to solve the decision problem are described: fuzzy logic-based, direct weighting of symptoms and directional properties. The proposed methods have been tested, first on simulation and then on two laboratory control equipments : 3-tanks system and d.c motor system . Copyright© 1998 IFAC Keywords: Fault Detection and Diagnosis, Fuzzy Logic, Sensitivity Analysis, Decision System 1. INTRODUCTION. In the last decades several model-based fault detection methods have been developed: Failure Detection Filters (Patton et al., 1989) , Diag- nostic Dedicated Observers (Patton et al. , 1989 ; Frank , 1990) , Parity Equations from State Space model (Chow and \Villsky, 1984; Willsky, 1976) and Parity Equati ons from Input-Output model (Gertler , 1988; Gertler and Luo. 1989). Most of the recent research lines have focused their interest in robustness issues(Patton. 1993; Patton , 1994; Fang. 199:3: Wagner and Shoureshi. 1992: Fuente. 1994). However. modelling errors are quite difficult t.o avoid in real applications. The constrains of this kind of mode ls have motivated the development of diagnostic knowledge-based approach . (Tzafes t.a.'.i et al ., 198'/: Reiter, 1987; Ulieru, 1994) However. some work has been made 707 on hybrid systems (Isermann, 1994; Isermann , 1993 ; Frank , 1994; Ulieru. 1993; Miguel, 1994) . A complete Fault Detection and Diagnosis System may be represented as it is shown in figure 1 DAS E.X'!"'..R.'lA!. ! N?U'l'S -- -- - - .• LEARNI NG .. - --, MO DULE - - DEC!SrOS __ GE..'iERATOR I M ODt'LE Fig. 1. Modules of a Fault Detection and Isolation System. (DAS: Data Acquisition System).