Making transformer hear better: Adaptive feature enhancement based multi-level supervised acoustic signal fault diagnosis

Shuchen Wang, Qizhi Xu, Shunpeng Zhu, Biao Wang

Abstract: Highlights•A multi-level supervised learning paradigm for efficient fault diagnosis.•A TF fusion-based method for balanced fidelity and resolution in feature extraction.•Designed FBAM to enhance focus on weak fault characteristics in neural networks.