A Novel Periodic Cyclic Sparse Network With Entire Domain Adaptation for Deep Transfer Fault Diagnosis of Rolling Bearing
Xing Zhan, Cai Yi, Jianhui Lin, Qiuyang Zhou
Abstract
In recent years, the rolling bearing fault diagnosis technique based on deep learning (DL) provides a more intelligent and reliable way for the safe operation of mechanical systems. However, this technique still exists problems of high model complexity and poor generalization ability in the application. To solve the above problem, a novel periodic cyclic sparse network with entire domain adaptation (PcsNet-EDA) for deep transfer fault diagnosis of rolling bearing is proposed in this article. The proposed periodic cyclic sparse design pattern makes the weight matrices of the convolutional layer and the fully connected layer contain a large number of zero-weight parameters with the regular arrangement, which effectively reduces the complexity of the model. The proposed EDA simultaneously considers the alignment of both global and local discrepancy, which further enhances the generalization ability of the model. In experimental validation, this article first analyzes the basic diagnostic performance of PcsNet. Then, the transfer diagnostic performance of PcsNet within single-source domain scenarios based on EDA is explored, including the influence of different predefined sparse structures on the transfer diagnostic accuracy. The validation shows that the proposed PcsNet and the corresponding transfer model PcsNet-EDA can achieve satisfactory results on different bearing fault datasets for fault diagnosis.