Abstract
 

Recently, deep-learning-based uncertainty-aware fault-diagnosis methods have been developed to enhance the trustworthiness of fault-diagnosis results. However, these methods often fail to identify unseen faults, largely because of their limited ability to extract discriminative features. In addition, existing methods are computationally intensive, as they require multiple iterations of model training or intricate probabilistic computations to calculate uncertainty.To address these challenges, this article proposes a novel uncertainty-aware machine fault diagnosis method named center margin loss-based fault diagnosis (CMLFD). The proposed method extracts highly discriminative features by regulating the distances between class centres and deep features during training. It also calculates the uncertainty of input data using only a single deterministic model training process by comparing the centre distances of deep features and class boundaries.The effectiveness of the proposed method is validated through experimental studies on two rotating machine datasets. The results demonstrate that the proposed method successfully identifies unseen faults while maintaining high diagnostic performance.The proposed CMLFD method provides an effective and computationally efficient framework for uncertainty-aware fault diagnosis of rotating machines, particularly when unseen faults may occur.