Expert System Development For Nuclear Reactor Failure Diagnosis

The safety aspect is very important in an nuclear installation. Any anomalous process must be detected as soon as possible. In this research, an expert system development for failure diagnosis in a nuclear reactor is treated. This expert system was written in CLIPS language and got its knowledge base from PCTRAN reactor simulator. The experiments has shown that this expert system can determine the component failure location by applying its inference rules from the knowledge base. Although the number of knowledge in the knowledge base is still limited, but its expansion to more complex systems is not difficult. Informations of parameter positions can be added to improve the precision of diagnosis