A study on the development of an automatic fault diagnosis system for testing nuclear power plant digital electronic circuits

This paper describes a study on the development of an automatic fault diagnosis system for testing digital electronic circuits of nuclear power plants. Compared with the other conventional fault diagnosis systems, the system described in this paper uses Artificial Intelligence technique of model based reasoning and corroboration, which makes fault diagnosis much more efficient. Since the system diagnoses the circuit boards based only on input and output signals, it can be further developed for on-line testing. The system was implemented on a microprocessor and was applied for Universal Circuit board testing of the Solid State Protection System in nuclear power plants.