Unsupervised heterogeneous transfer fault diagnosis based on graph Laplacian common subspace

Abstract

In recent years, transfer learning has been widely used in cross-domain fault diagnosis to solve the problem of insufficient training data. Existing studies focus on the homogeneous transfer fault diagnosis of the same component with different operating conditions. However, when the source and target domain are from two different components, the feature space and category space of the two domains are completely different, which causes the challenging problem of unsupervised heterogeneous transfer fault diagnosis. We propose a graph Laplacian common subspace based unsupervised heterogeneous transfer learning model (GL-HTLM). Firstly, pseudo-labels are designed for the unlabeled samples of target domain using the Gaussian mixture model to learn the distribution characteristics of the original vibration signals. Secondly, a deep convolutional neural network is designed to extract the high-dimensional features of the labeled samples of source domain and the pseudo-labeled samples of target domain. Finally, a common latent attributes space (CLAS) is generated through near-binary feature representation learning to extract the latent attributes of the source and target domain. According to the similarity of any two samples in CLAS, we further define graph Laplacian loss to maximize the inter-category distances while minimizing the intra-category distances. Therefore, the two domains with different category spaces are strongly consistent in the CLAS, so as to classify samples of two domains. In order to validate the proposed method, four heterogeneous transfer fault diagnosis experiments are carried out using bearing dataset and gear dataset. Results demonstrate that our proposed model is superior to existing methods.