A Novel Physics-Informed Federated Learning Framework for Robust Bearing Fault Diagnosis

Rolling bearing failures are a primary cause of catastrophic machinery breakdowns, posing significant economic and safety risks. Effective fault diagnosis is frequently hindered by challenges inherent to modern industrial settings, including data privacy constraints, statistical heterogeneity across Non-Independent and Identically Distributed (Non-IID) datasets, and the prevalence of few-shot learning scenarios. To address these challenges, this paper introduces CARR-MgNet, a novel physics-informed federated learning framework. The framework utilizes a M ulti- g ranularity fusion Net work (MgNet) backbone, which enhances feature robustness by embedding physical fault characteristics directly into its convolutional kernels. To ensure stable federated training across heterogeneous clients, we then introduce a C lass- A verage R epresentation R egularization (CARR) mechanism to effectively mitigate client drift. Extensive experiments on four public industrial datasets validate the state-of-the-art performance of our proposed framework. Under challenging non-IID conditions, CARR-MgNet surpasses established baselines, including FedProx and MOON, by up to 8.2% in accuracy. Furthermore, it reduces the number of communication rounds required to reach 95% accuracy by 40% compared to FedAvg and reduces total communication overhead by 35%. These results demonstrate that our physics-informed federated approach provides a robust, communication-efficient, and privacy-preserving solution for real-world industrial fault diagnosis.