Multiscale domain adaption models and their application in fault transfer diagnosis of planetary gearboxes

In recent years, various deep domain adaption (DDA) models, such as deep domain confusion (DDC) and deep adaption network (DAN), are proposed. These models can adapt a trained model in the source domain to new classification tasks in the target domain. However, these classical DDA models suffer from some inherent drawbacks. For example, traditional DDA models can output only one transfer feature (TF) with high dimension and fixed scales, thus possibly losing important information while performing domain confusion operation. Multiscale domain adaption (MSDA) is proposed in this paper to remold and improve the classical DDA models to solve the aforementioned problems. MSDA is a universally applicable strategy that can be embedded into most existing classical DDA models. An MSDA block is designed and constructed on the basis of multiscale convolution networks to replace the last convolutional layer of the original DDA model. The MSDA block has four parallel pipelines consisting of multiscale convolutional and global average pooling operations. Therefore, MSDA can extract more domain-invariant features than the original feature extractor, meanwhile the four low-dimension TFs can simplify the calculation of domain confusion losses. The four TFs are concatenated into a feature vector, and then it is input into the top classifier for fault identification. MSDA can be effectively applied to five classical DDA models and enhance their abilities of domain adaption. The effectiveness and advantage of the proposed MSDA are verified through 18 fault transfer diagnosis tasks of planetary gearboxes.

Automated summary

This paper proposes a Multiscale Domain Adaption (MSDA) method to improve classical Deep Domain Adaption (DDA) models by addressing their inherent drawbacks. MSDA, with its MSDA block constructed based on multiscale convolution networks, can extract more domain-invariant features and simplify the calculation of domain confusion losses, thereby enhancing the domain adaption abilities of DDA models.