A New Method of Fault Diagnosis Based on Neural Network
Xiaodong Yang, Pla Navy · Ordnance Industry Automation · 2008
A method of fault diagnosis based on neural network and D-S evidence theory is put forward. Pick up signals from the fault symptom space,then allocate information to sub-neural-network;the sub-neural-network is parallel,and diagnose faults from different aspects;After unitary processing,the output results meet conditions of basic reliability allocating functions. Finally it confuses the information and then gets the diagnosis result. Example of calculation indicates that the method is reliable and effective.