Traditional fault diagnosis models often overlook the interconnections between segments of vibration data, resulting in the loss of critical feature information. Therefore, an efficient fault diagnosis model tailored for rolling bearings is proposed in this paper. The 1D vibration signals are first preprocessed using ensemble empirical mode decomposition (EEMD) to generate multiple intrinsic mode functions (IMF) as individual nodes. The percentage distance between each node is calculated using the Wasserstein distance (WD) to capture the relationships between nodes and use it as the edge weights to construct a node graph. An improved multi-head graph attention network (MGAT) model is established to extract features and perform classification on the node graph. This MGAT model effectively utilizes the relationships between nodes and enhances the accuracy of fault diagnosis. The experimental results demonstrate that the proposed method achieves higher accuracy compared to similar models while requiring less processing time.

To reduce the experimental costs associated with tool condition monitoring (TCM) under new cutting conditions, a finite element modeling (FEM)-assisted deep subdomain adaptive network (DSAN) approach is proposed. Initially, an FEM technique is employed to construct a cutting tool model for the new cutting condition (target domain), and the similarity between simulated and experimental data is assessed to obtain valid simulated samples for the target domain. Subsequently, the time–frequency Markov representation method is utilized to extract imaging features from the simulated samples, which serve as input features for the monitoring model. Then, a DSAN model is established to facilitate the transfer from simulation to reality, with the source domain comprising a simulated sample set under new cutting conditions that includes various types of tool conditions obtained through FEM, and the target domain containing only a limited number of normal tool condition samples under new cutting conditions. The application analysis has demonstrated the effectiveness of the proposed method, achieving a classification accuracy of 99%. The proposed approach can significantly reduce experimental costs and obtain high-precision diagnostics of tool conditions with a small sample size.