An Adaptive Activation Transfer Learning Approach for Fault Diagnosis

For industrial scenarios with changing operating conditions, the vibration data of different operating conditions often have different data distributions. In this article, to make the deep learning framework perform more flexible nonlinear transformations for different input data, a new activation function, i.e., parameter-free adaptively Swish (PASwish), is developed. PASwish formulates different activation schemes for different input data so that vibration data under different operating conditions can carry out adaptive nonlinear transformation, and the generalization ability of the whole network is improved. In addition, this article proposes deep parameter-free cosine networks with PASwish on the basis of PASwish, which can help adjust the network weights of domain-specific features and domain-invariant features by constructing an attention module based on cosine adjustment. Finally, the reconstruction-based domain adaptation method is used to achieve cross-domain fault diagnosis. Experiments are carried out on the bearing fault experimental platform to verify the effectiveness and generalization of the proposed method. We have achieved 95.16% (+/- 1.76\%) average accuracy on 72 transfer tasks, which shows better performance than current studies.

Automated summary

In this article, a new activation function called Parameter-free Adaptively Swish (PASwish) is developed to improve the flexibility and generalization ability of deep learning frameworks in industrial scenarios with changing operating conditions. Additionally, deep parameter-free cosine networks with PASwish are proposed to adjust network weights based on domain-specific and domain-invariant features. The proposed method achieves better performance in cross-domain fault diagnosis compared to current studies, with an average accuracy of 95.16% (+/- 1.76%) on 72 transfer tasks.