Proceedings of the Twelfth National Conference on Artificial Intelligence (AAAI-94) Workshop on Artificial Intelligence in Business Process Re-Engineering, July 31 - August 4, 1994., Seattle, Washington, USA
This paper argues that automated knowledge acquisition for diagnosis has had limited success in both failure-driven diagnosis and model-based diagnosis. The paper describes fault-based and model-based reasoning for diagnosis and surveys some of the approaches to knowledge acquisition in both areas. The Diagnostic Remodeler (DR) algorithm has been implemented for the automated generation of behavioural component models with function from fault-based knowledge. The use of function in this paper is based on the perspective that function complements behaviour where the derived function is more abstract than the behaviour derived by DR [Kumar 94]. DR uses as its first application example the fault-based knowledge base of the Jet Engine Troubleshooting Assistant (JETA). DR is used to extract the model of the Main Fuel System using the knowledge base and two types of background knowledge as input: device dependent and device independent knowledge. This paper is the first presentation of preliminary results of the implemented DR algorithm.