Fault diagnosis based on rough set and neural network
Feng Chen · Journal of Harbin University of Commerce · 2007
On the basis of neural network fault diagnosis model,this paper introducs rough sets theory and disctete method of continous attribute value.And rough sets theory is used to eliminate unnessary attributes from the decision table.The result of emluator indicats that this method can reduce the needed training samples and simply the neural network structure and shortened the training time of the network.It is estimated that the optimized strategy may be further applied in fault diagnoses.