MARINE DIESEL ENGINE FAULTS DIAGNOSIS BASED ON OBSERVED SYMPTOMS AND EXPERT KNOWLEDGE

摘要

The paper deals with two methods to fault detection and isolation in ship's propulsion diesel engine. The first diagnosis method is based on real-time diagnostic signals i.e. symptoms and their relation to faults in an extended form with tracking times of symptoms occurrence. The effectiveness of this method has been evaluated with concurrently simulating two very similar engine cylinder faults. The second diagnosis method introduced in the paper based on human expert heuristic knowledge showed very good result in diagnosis the same engine fault. In both simulation examples, in a certain way, a form of integration of these two methods is used. The hybrid method based on good monitoring system and heuristic knowledge base could become more attractive in marine applications.