Fault Diagnosis of Bearings with Small Sample Size Using Improved Capsule Network and Siamese Neural Network

This paper addresses the challenges of low accuracy and long transfer learning time in small-sample bearing fault diagnosis, which are often caused by limited samples, high noise levels, and poor feature extraction. We propose a method that combines an improved capsule network with a Siamese neural network. Multi-view data partitioning is used to enrich data diversity, and Markov transformation converts one-dimensional vibration signals into two-dimensional images, enhancing the visualization of signal features. The dynamic routing mechanism of the capsule network effectively captures and integrates key fault features, improving the model's feature representation and robustness. The Siamese network shares weights to optimize feature matching, while SKNet dynamically adjusts feature fusion to enhance generalization performance. By integrating the Siamese neural network with SKNet, we improve transfer efficiency, reduce the number of parameters, and lighten the model to reduce complexity and shorten transfer time. Experimental results demonstrate that this method can accurately identify faults under conditions of limited samples and high noise, thereby improving diagnostic accuracy and reducing transfer time.