Current data-driven fault diagnosis methods are prone to overfitting and a decrease in accuracy when working with only a limited number of labeled samples. Additionally, existing graph neural network-based fault diagnosis methods often fail to comprehensively utilize both global and local features. To address these challenges, we propose a rolling bearing fault diagnosis method based on Multi-Scale Weighted Visibility Graph(MSWVG) and a Multi-Channel Graph Convolutional Network(MCGCN). Our approach converts vibration signals into multiple weighted graphs from the perspective of geometric meaning and extracts local node feature information and global topology information of graphs using MCGCN. Experimental results demonstrate that our method achieves excellent performance under both sufficient and limited data conditions, providing a promising approach for real-world industrial bearing fault diagnosis.

In order to improve the generality and real-time of image matching procedure, Visual Studio 2010 and MATLAB R2009a have been used as the platform to research mixed programming and improved SIFT algorithm. In this method, the advantages of C # and Matlab have been combined to reduce the difficulty of programming and to improve programming efficiency. The results show that, improved SIFT algorithm can greatly improve real-time of matching program while guaranteeing good matching rate, its suitable in real-time applications.