Adaptive Privacy-Preserving Federated Learning for Fault Diagnosis in Internet of Ships

Abstract

The recent appearance of Internet of Things (IoT) technologies applied in the maritime industry has introduced the Internet of Ships (IoS) paradigm. By leveraging IoS and deep learning (DL), various DL-based fault diagnosis methods have been proposed to improve shipping companies’ maintenance performance and reduce operational costs. However, the traditional centralized learning approach (CL), which centralizes the data resources of different shipping companies to a cloud server for model training, is restricted in real industrial scenarios due to privacy concerns and business competitions. In this article, we propose a novel adaptive privacy-preserving federated learning approach, named AdaPFL, for fault diagnosis in IoS, which can organize different shipping agents to collaboratively develop a model by sharing model parameters with no risk of data leakage. First, we use two common tasks as examples to demonstrate that a small part of the model parameters might reveal the shipping agents’ raw information. Based on this, the Paillier-based communication scheme is designed to preserve the raw information of the shipping agents. Furthermore, to deal with the harsh marine environment, a control algorithm is proposed to adaptively change the model aggregation interval during the training process for reducing cryptography computation and communication costs. Theoretical analysis and experiments prove the high effectiveness of the AdaPFL on a real nonindependent and identically distributed (non-i.i.d) fault data set.