Multiple faults simultaneous diagnosis based on ellipsoidal unit networks for rotating machine

摘要

To overcome the limitations of the standard feedforward neural network, a novel neural network (i.e., ellipsoidal unit network) is proposed, which is very available for fault diagnosis applications due to its bounded generalization ad extrapolation. In this paper, the theory and the structure of such a network are described, and the training al- gorithm is given based on standard backpropagation algorithm.