Open Access

ARTICLE

Robust and Efficient Federated Learning for Machinery Fault Diagnosis in Internet of Things

Zhen Wu^1,2, Hao Liu³, Linlin Zhang⁴, Zehui Zhang^5,*, Jie Wu¹, Haibin He¹, Bin Zhou⁶

1 Ningbo C.S.I. Power & Machinery Group. Co., Ltd., Ningbo, 315020, China
2 Zhejiang Institute of Communications, Hangzhou, 311112, China
3 School of Software, Nankai University, Tianjin, 300350, China
4 China Automotive Technology and Research Center Co., Ltd., Tianjin, 300300, China
5 China-Austria Belt and Road Joint Laboratory on Artificial Intelligence and Advanced Manufacturing, Hangzhou Dianzi University, Hangzhou, 310018, China
6 Jiangxi Tsinghua Tellhow Sanbo Electric Machinery Co., Ltd., Nanchang, 330096, China

* Corresponding Author: Zehui Zhang. Email:

(This article belongs to the Special Issue: Integrating Split Learning with Tiny Models for Advanced Edge Computing Applications in the Internet of Vehicles)

Computers, Materials & Continua 2026, 87(1), 42 https://doi.org/10.32604/cmc.2025.075156

Received 26 October 2025; Accepted 21 November 2025; Issue published 10 February 2026

Abstract

Recently, Internet of Things (IoT) has been increasingly integrated into the automotive sector, enabling the development of diverse applications such as the Internet of Vehicles (IoV) and intelligent connected vehicles. Leveraging IoV technologies, operational data from core vehicle components can be collected and analyzed to construct fault diagnosis models, thereby enhancing vehicle safety. However, automakers often struggle to acquire sufficient fault data to support effective model training. To address this challenge, a robust and efficient federated learning method (REFL) is constructed for machinery fault diagnosis in collaborative IoV, which can organize multiple companies to collaboratively develop a comprehensive fault diagnosis model while keeping their data locally. In the REFL, the gradient-based adversary algorithm is first introduced to the fault diagnosis field to enhance the deep learning model robustness. Moreover, the adaptive gradient processing process is designed to improve the model training speed and ensure the model accuracy under unbalance data scenarios. The proposed REFL is evaluated on non-independent and identically distributed (non-IID) real-world machinery fault dataset. Experiment results demonstrate that the REFL can achieve better performance than traditional learning methods and are promising for real industrial fault diagnosis.

---

Keywords

---