Integrating heuristic and model-based reasonings in fault diagnosis

Abstract

Human expert utilizes various diagnostic knowledges very dynamically in problem solving. Recently a few of integrated reasoning systems are proposed in order to use various types of knowledges in an integrated way. But they have shortcomings in reasoning control and reasoning interactions. To overcome these shortcomings, a diagnostic reasoning system with dynamic interactions that uses diverse types of knowledges with cooperation is proposed.

The diagnostic reasoning system contains the heuristic and the model-based reasoning modes. A type of knowledge in a reasoning mode is shared with another via transformation knowledge. In the integrated diagnostic reasoning system, the heuristic reasoning mode acts a major role in reasoning, and the model-based on fills gap of the heuristic reasoning mode. The model-based reasoning mode helps the heuristic one by supporting primitive level testing, and by generating symptom and hypotheses. In addition, it undertakes remained task if the heuristic reasoning mode fails. The heuristic reasoning mode, also, aids the model-based one by pruning candidate set.

By applying the integrated reasoning system to a printer circuit diagnosis, the system is shown appropriate for the domain that calls cooperative use of heuristic and detailed system description knowledges. By the comparison of the number of tests required to isolate faulty components from the problem system, we have shown that the proposed system is appropriate when insufficient symptoms and incomplete heuristic rules are provided.