ENHANCING OFF-LINE AND ONLINE CONDITION MONITORING AND FAULT-DIAGNOSIS

This paper describes the use of artificial intelligence technology to enhance offline and on-line condition monitoring and fault diagnosis and to integrate these two developments into a closed-loop diagnostic tool for complex systems in modern transportation. Two developments are presented here, which were verified in industrial diagnostic problems; on-line fault diagnosis for trains, and off-line aircraft Engine Condition Monitoring (ECM). Case-based reasoning (CBR) is used to incorporate the knowledge and experience of both train manufacturers and railway companies for on-line train fault diagnosis. The size of the diagnostic problem is such that explicit formulation of fault-trees is almost impossible. CBR facilitates the automatic generation, consistency checking and maintenance of the fault-trees. Additional measures have been taken to meet the real-time requirements for on-line use of a CBR-based diagnostic system. A balanced combination of neural networks and expert-system techniques is used to ensure more consistent off-line ECM. The information, such as trends from in-flight measured aircraft and engine parameters, crew trouble reports, maintenance and findings from accessory repair shops, can be incorporated to assess the engine's state of health, and to deduce appropriate preventative or corrective actions.