摘要
ＡＭｏｄｉｆｉｅｄＦｅｅｄｆｏｒｗａｒｄＮｅｕｒａｌＮｅｔｗｏｒｋＭｏｄｅｌｆｏｒＦａｕｌｔＤｉａｇｎｏｓｉｓｏｆＲｏｔａｔｉｎｇＭａｃｈｉｎｅｒｙＺａｎｇＣｈａｏｐｉｎｇ（臧朝平）ＧａｏＷｅｉ（高）（ＮＥＲＣＴＶ，ＳｏｕｔｈｅａｓｔＵｎｉｖｅｒｓ...
A new modified feedforward neural network model for fault diagnosis of rotating machinery is presented in this paper based on studying a conventional back propagation diagnostic neural network. This neural network model for fault diagnosis considerably extends the networks capability for representing complex nonlinear relations between the type of faults and the symptoms and promotes the diagnostic accuracy by adding a number of functional units to the input layer. The experimental data show successful and effective results with this method.
