The paper discusses an AN-24 aircraft engine fault diagnosis system which has been realized by inputting the experiences of repair mechanics or engine experts. The system is composed of four sections: a phenomena model, inference model, learning model, and an interpretation model. Therefore, the system is a model-based diagnosis system. These four models are relatively independent which makes parallel operation, easy debugging, and the addition of new knowledge possible. The experience of the engine experts has been stored initially in the outer knowledge base. Intermediate knowledge which arises during the process of inference is treated in the inner knowledge base. The inner knowledge base adopts a blackboard structure
An artificial intelligence system of trouble diagnosis for aircraft engines
Ein System der künstlichen Intelligenz zur Fehlerdiagnose für Flugzeuge
1996
5 Seiten, 3 Quellen
Conference paper
English