Deep Decoupling Convolutional Neural Network for Intelligent Compound Fault Diagnosis

Abstract

Intelligent compound fault diagnosis of rotating machinery plays a crucial role for the security, high-efficiency, and reliability of modern manufacture machines, but identifying and decoupling the compound fault are still a great challenge. The traditional compound fault diagnosis methods focus on either bearing or gear fault diagnosis, where the compound fault is always regarded as an independent fault pattern in the process of fault diagnosis, and the relationship between the single fault and compound fault is not considered completely. To solve such a problem, a novel method called deep decoupling convolutional neural network is proposed for intelligent compound fault diagnosis. First, one-dimensional deep convolutional neural network is employed as the feature learning model, which can effectively learn the discriminative features from raw vibration signals. Second, multi-stack capsules are designed as the decoupling classifier to accurately identify and decouple the compound fault. Finally, the routing by agreement algorithm and the margin loss cost function are utilized to train and optimize the proposed model. The proposed method is validated by gearbox fault tests, and the experimental results demonstrate that the proposed method can effectively identify and decouple the compound fault.