Blockchain-based Federated Learning for Bearing Fault Detection in the Industrial Internet of Things

The reliability of Industrial Internet of Things (IIoT) systems requires robust fault detection, which can be achieved with AI. However, the current centralized learning approach is inefficient. Federated Learning (FL) solves this problem by enabling distributed training without exposing individual information. This article proposes a parameter aggregation technique for bearing fault detection in IIoT using a lightweight smart contract with a PoA-based blockchain consensus. The findings indicate that the proposed system provides a secure aggregation process with an accuracy of 94.00% and a processing time of 1.54 s, which is suitable for the IIoT environment.