The document proposes a new method called the Brownian correlation metric prototypical network (BCMPN) for fault diagnosis of rotating machinery. The BCMPN uses a multi-scale mask preprocessing mechanism to improve model performance. It extracts multi-scale features using dilation convolution and an effective light channel attention module. For classification, it measures the difference between the joint feature function and product of marginal distributions using Brownian distance, unlike existing methods that use Euclidean or cosine distance. Experiments on gear dataset and laboratory data show the BCMPN performs better than other methods for problems with few training samples and zero samples in the target domain.