A Fault Diagnosis Method Based on Capsule Convolutional Network

In order to improve the accuracy of equipment fault diagnosis, a method for equipment fault diagnosis is proposed based on convolutional capsule network. Compared with the convolution neural network, the capsule convolutional network can effectively extract the related information such as the spatial position between the data, and further mine the hidden information of the data. Since the fault data of complex equipment is interrelated, convolutional capsule network can more effectively extract the hidden features of fault data, which helps to improve the accuracy of fault diagnosis and equipment maintainability.