BP neural network is prone to local minima during training and thus cannot obtain the optimal solution. It may also cause misjudgment during fault diagnosis. To address this problem, this paper proposes the H-BP, a simplified neural network fault diagnosis method. This network combines the global optimal computing power of the Hopfield neural network and the advantages of the BP neural network in solving nonlinear classification problems, thus avoiding the network training from falling into the local minimum. It is applied to the fault diagnosis of centrifugal fans, which shows that the H-BP network fault diagnosis method can well realize fault state recognition and improve the accuracy of fault diagnosis.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore