Open-Set Fault Diagnosis in Multimode Processes via Fine-Grained Deep Feature Representation
This work addresses fault diagnosis for industrial processes, offering an incremental improvement by enhancing feature representation to handle multimode distributions.
The paper tackled the problem of open-set fault diagnosis in multimode processes, where known health states have multiple cluster distributions, by proposing a novel model (FGCRN) that achieved superior performance in accurately classifying known faults and identifying unknown ones.
A reliable fault diagnosis system should not only accurately classify known health states but also effectively identify unknown faults. In multimode processes, samples belonging to the same health state often show multiple cluster distributions, making it difficult to construct compact and accurate decision boundaries for that state. To address this challenge, a novel open-set fault diagnosis model named fine-grained clustering and rejection network (FGCRN) is proposed. It combines multiscale depthwise convolution, bidirectional gated recurrent unit and temporal attention mechanism to capture discriminative features. A distance-based loss function is designed to enhance the intra-class compactness. Fine-grained feature representations are constructed through unsupervised learning to uncover the intrinsic structures of each health state. Extreme value theory is employed to model the distance between sample features and their corresponding fine-grained representations, enabling effective identification of unknown faults. Extensive experiments demonstrate the superior performance of the proposed method.