On-line fault diagnosis system support for reactive scheduling in multipurpose batch chemical plants

In this work, a simple strategy for the development and implementation of a fault diagnosis system (FDS) that interacts with a schedule optimiser in b atch chemical plants is presented. The proposed FDS consists of an artifici al neural network (ANN) structure supplemented with a knowledge-based exper t system (KBES) in a block-oriented configuration. The system combines the adaptive learning diagnostic procedure of the ANN and the transparent deep knowledge representation of the KBES. The information needed to implement t he FDS includes a historical database of past batches, a Hazard and Operabi lity (HAZOP) analysis and a model of the plant. Two motivating case studies are presented to show the results of the proposed methodology. The first c orresponds to a fed-batch reactor. In this example, the FDS performance is demonstrated through the simulation of different process faults. The second case study corresponds to a multipurpose batch plant. In this case, the re sults of reactive scheduling are shown by simulating different abnormal sit uations. A performance comparison is made against the traditional schedulin g approach without the support of the proposed FDS. (C) 2001 Elsevier Scien ce Ltd. All rights reserved.