Spatial Graph Convolutional Neural Network via Structured Subdomain Adaptation and Domain Adversarial Learning for Bearing Fault Diagnosis
This is an incremental improvement for industrial fault diagnosis systems, addressing specific limitations in unsupervised domain adaptation methods.
The paper tackles bearing fault diagnosis under changing working conditions by proposing DSAGCN, a method that combines graph convolutional networks with subdomain adaptation techniques, achieving superior performance on CWRU and Paderborn datasets compared to existing models.
Unsupervised domain adaptation (UDA) has shown remarkable results in bearing fault diagnosis under changing working conditions in recent years. However, most UDA methods do not consider the geometric structure of the data. Furthermore, the global domain adaptation technique is commonly applied, which ignores the relation between subdomains. This paper addresses mentioned challenges by presenting the novel deep subdomain adaptation graph convolution neural network (DSAGCN), which has two key characteristics: First, graph convolution neural network (GCNN) is employed to model the structure of data. Second, adversarial domain adaptation and local maximum mean discrepancy (LMMD) methods are applied concurrently to align the subdomain's distribution and reduce structure discrepancy between relevant subdomains and global domains. CWRU and Paderborn bearing datasets are used to validate the DSAGCN method's efficiency and superiority between comparison models. The experimental results demonstrate the significance of aligning structured subdomains along with domain adaptation methods to obtain an accurate data-driven model in unsupervised fault diagnosis.