OBJECT-BASED AUTOMATED FAULT-DIAGNOSIS

The implementation of a model-based fault diagnosis methodology is presented. An object-based representation is used and shown to allow for easy access to and maintenance of the process model. The diagnostic methodology employed fits easily into this object-based approach. The methodology also offers other advantages including explicit use of simple model equations, non-Boolean reasoning, sensitivity weighting of evidence, and the possibility of multiple fault explanations. Additionally, methods of improving fault discrimination are discussed such as the cautious use of heuristics and the i single fault hypothesis. Testing of the diagnostic system on a process simulation has shown it to be successful at locating various fault conditions. © 1991, Taylor & Francis Group, LLC. All rights reserved.