Application of a Dense Fusion Attention Network in Fault Diagnosis of Centrifugal Fan
This work addresses interpretability and feature extraction in fault diagnosis for centrifugal fans, representing an incremental improvement in domain-specific methods.
The paper tackled the challenge of understanding model structure-function correspondence in deep learning for rotating machinery fault diagnosis by embedding distributed attention modules into dense connections, resulting in a network with stronger diagnostic performance than other advanced models.
Although the deep learning recognition model has been widely used in the condition monitoring of rotating machinery. However, it is still a challenge to understand the correspondence between the structure and function of the model and the diagnosis process. Therefore, this paper discusses embedding distributed attention modules into dense connections instead of traditional dense cascading operations. It not only decouples the influence of space and channel on fault feature adaptive recalibration feature weights, but also forms a fusion attention function. The proposed dense fusion focuses on the visualization of the network diagnosis process, which increases the interpretability of model diagnosis. How to continuously and effectively integrate different functions to enhance the ability to extract fault features and the ability to resist noise is answered. Centrifugal fan fault data is used to verify this network. Experimental results show that the network has stronger diagnostic performance than other advanced fault diagnostic models.