Under laboratory conditions for recording a small amount of data, the characteristics of the phenomena distribution become a limitation of machine learning and advanced deep learning concepts for the diagnosis and localization of mechanical wear faults. In this paper, we adopt the combination of the diffusion model and TTT (test-time training), based on the sample distribution of feature data under the laboratory conditions, and we use the pre-trained decoder to decode the data into a continuous potential representation of natural language for sampling, to achieve data regeneration. Subsequently, the TTT algorithm becomes a model with weights in the hidden state itself. The gradient step on the self-supervised loss is selected as the update rule, which is trained synchronously during the testing time, adhering to the concept of migration learning, to construct a high-dimensional mapping relationship between the feature parameters and the failure modes of the mechanical wear. The final validation results show that the diagnosis accuracy reaches more than 95% for six types of typical aero-engine mechanical wear faults.