Due to the limited generality of traditional fault diagnosis expert system and its low accuracy of extracting failure symptoms, a general fault monitoring and diagnosis expert system has been built. For different devices, users can build fault trees in an interactive way and then the fault trees will be saved as expert knowledge. A variety of sensors are fixed to monitor the real-time condition of the device and intelligent algorithms such as wavelet transform and neural network are used to assist the extraction of failure symptoms. On the basis of integration of multi-sensor failure symptoms, the fault diagnosis is realized through forward and backward reasoning. The simulation diagnosis experiments of NC device have shown the effectiveness of the proposed method.
Directed hypergraph observers-based qualitative fault
monitoring tasks
