This paper presents an expert system fault diagnosis and seamless self-healing scheme based on artificial intelligence,which is used for the astronomical telescope drive system. For the faults that have already occurred, the expert system inference mechanism can be used to realize quick localization of failure, and we can use the expert solution in the knowledge base to run the self-healing decision until the failure is resolved. For the failure the knowledge base doesn’t have, we can use human-machine interface to achieve real-time update of the knowledge base. For the faults that didn’t occurred, the trained adaptive BP neural network is used to fit the parameters of the telescope running status, to monitor the running status of the telescope in real time and to realize the fault warning of the telescope operation.

Fault diagnosis and seamless self-healing technology is one of the key technologies to realize intelligent, its research is of great significance.