DECDAF: Dual-Level Entropy-Aware Consensus Domain Adversarial Framework for Open-Set Fault Diagnosis

In recent years, domain adaptation methods have been widely applied in fault diagnosis. However, these methods are typically based on the assumption that the source and target domains have identical fault modes. In real-world industrial scenarios, unknown fault modes may occur in mechanical equipment, resulting in limitations in existing diagnostic methods. To address these issues, a dual-level entropy-aware consensus domain adversarial framework (DECDAF) is proposed for open set fault diagnosis. First, a dual-level entropy-aware module is constructed that employs unified entropy metrics at the sample-level and domain-level, which dynamically weights samples and adjusts decision boundaries. Then, for supervised learning, an auxiliary classifier module is employed to enhance the alignment of known classes; for unsupervised learning, a self-supervised clustering module is introduced to explore the intrinsic structure of the target domain and disambiguate marginal samples. Finally, a consensus domain adversarial module is designed that integrates the outputs of multiple modules to ensure consistent recognition of known classes and enhance domain alignment through adversarial learning. Comprehensive experimental results on two datasets demonstrate the effectiveness of this approach in solving the open set fault diagnosis and demonstrate its usability through real-world condition applications.