SADEP - A FUZZY DIAGNOSTIC SYSTEM SHELL - AN APPLICATION TO FOSSIL POWER-PLANT OPERATION

Artificial Intelligence applications in large-scale industry, such as fossil fuel power plants, require the ability to manage uncertainty an d time. In these domains, the knowledge about the process comes from e xperts' experience and it is generally expressed in a vague-fuzzy way using ill-defined linguistic terms. In this paper, we present a fuzzy expert system shell to assist an operator of fossil power plants. The fuzzy expert system shell, called SADEP, is based on a new methodology for dealing with uncertainty and time called Fuzzy Temporal Network F N). The FTN generates a formal and systematic structure used to model the temporal evolution of a process under uncertainty. The inference m echanism for a FTN consists in the calculation of the possibility degr ee of the real time occurrence of the events using the fuzzy compositi onal rule Sup_min. A FTN can be used to recognize the significance of events and state variables with respect to current plant conditions an d predict the future propagation of disturbances. SADEP was validated with the diagnosis of two detailed disturbances of a fossil power plan t: a power load increment in the drum level and a water condenser pump failure. The evaluations performed in this work indicate that SADEP c an potentially improve plant availability through early diagnosis of d isturbances that could lead to plant shutdown. (C) 1998 Elsevier Scien ce Ltd. All rights reserved.