Research And Implementation On Space Camera Fault Diagnosis Expert System

In order to improve the efficiency of fault diagnosis of space cameras, shorten the time for fault diagnosis, fault diagnosis to reduce the human and material resources, the design experts to more than a collection of best practices to achieve human-machine joint diagnosis of fault diagnosis expert system for space camera. Fault diagnosis technology described research status at home and abroad to introduce expert system, fault tree analysis and neural network fault diagnosis technology features and basic methods. Advantages and disadvantages for them to take reasonable combination of the three fault diagnosis method for fault diagnosis. In the comparative analysis, based on the establishment of the fault tree as a means of knowledge acquisition, using rules-based framework and knowledge base construction plan. Use of self-learning ability of neural networks, using BP neural network model and the Bayes network model established system of learning machine. Since the main source of failure data FMEA table, according to the characteristics of knowledge acquisition to build the fault tree space camera. Failure mainly to production rules said. Then introduced the fault diagnosis inference mechanism. Hybrid reasoning with forward and backward reasoning. Object-oriented java and SQL Server as a development tool. Create a knowledge base, inference machine and the interpreter, and other experts to use java to implement parts of the system, knowledge of storage using SQL Server database to complete. Fault simulation of space camera, the use of the expert system for fault diagnosis, the results show that the phenomenon of expert system for rapid fault analysis, diagnosis results are consistent with reality.