Deep hybrid convolutional neural network for fault diagnosis of wind turbine gearboxes

Abstract

One embodiment provides a system for facilitating fault diagnosis. During operation, the system collects current signals associated with a physical object which comprises a rotating machine. The system demodulates the collected signals to obtain current envelope signals, which eliminates fundamental frequencies and retains fault-related frequencies. The system resamples the current envelope signals, which converts the fault-related frequencies to constant frequency components. The system enlarges, by a fault-amplifying convolution layer, the resampled envelope signals to obtain fault information. The system provides the fault information as input to a deep convolutional neural network (CNN). The system generates, by the deep CNN, an output which comprises the fault diagnosis for the physical object.