Open Access

ARTICLE

Graph Representation Consistency Enhancement via Graph Transformer for Fault Diagnosis of Complex Industrial Systems

Fang Hao¹, Puyuan Hu², Yumo Jiang², Ruonan Liu^2,*

1 The 704th Research Institute of China State Shipbuilding Corporation, Shanghai, China
2 School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China

* Corresponding Author: Ruonan Liu. Email:

(This article belongs to the Special Issue: Advancements in Mobile Computing for the Internet of Things: Architectures, Applications, and Challenges)

Computers, Materials & Continua 2026, 87(2), 63 https://doi.org/10.32604/cmc.2026.075655

Received 05 November 2025; Accepted 19 December 2025; Issue published 12 March 2026

Abstract

Industrial fault diagnosis is a critical challenge in complex systems, where sensor data is often noisy and interdependencies between components are difficult to capture. Traditional methods struggle to effectively model these complexities. This paper presents a novel approach by transforming fault diagnosis into a graph recognition task, using sensor data represented as graph-structured data with the k-nearest neighbors (KNN) algorithm. A Graph Transformer is applied to extract node and graph features, with a combined loss function of cross-entropy and weighted consistency loss to stabilize graph representations. Experiments on the TFF dataset show that Graph Transformer combined with consistency loss outperforms conventional methods in fault diagnosis accuracy, offering a promising solution for enhancing fault detection in industrial systems.

---

Keywords

---