| Summary: | 碩士 === 國立成功大學 === 工程科學系專班 === 97 === For equipment engineers’ training, the most important is the problem solving and reasoning ability. Such ability cannot be obtained with just exemplary case trainings in a very short time, but has to accumulate from many experiences in a very long time practice. Even an engineer with a rich experience may use different trouble shooting methods on different problems. But not all methods can find out a cause easily and precisely. Sometimes one has to repeat try-and-error due to unclear relation between components and wastes time and reduces productions. One possible way to get around this is to use maintenance records from others' experiences and the inherent relations of equip components.
This thesis proposes a method and implements a system that uses both the maintenance record databases of an IC assembly factory and the relations of equip components inferred from an ontology for suggesting the most possible problem solving procedures to equipment maintenance engineers. When a junior engineer that does not have much experience has an abnormal machine to repair, he can interact with this question- answering system to get suggestions for maintaining the machine. The maintenance records will accumulate when time goes by, and if a problem that does not occur before, this system will build an ontology relationship among components or states and make suggestions according to that. Using this platform can not only save time for equipment maintenance but also share knowledge in experience among engineers.
|
|---|
