Zhang, Tianze (Beijing Jiaotong University), Zhao, Bobo (Beijing Jiaotong University), Li, Jiapeng (Beijing Jiaotong University)

Advancing Data Augmentation: Generative Methods for Switch Machine Fault Summarization

Scheduled for presentation during the Video Session "On-Demand Video Presentations" (VP-VP), Saturday, November 22, 2025, 08:00−18:00, On-Demand Platform

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on April 2, 2026

Abstract

The switch machine is a key execution device in railway signaling systems. Leveraging fault data effectively is critical for enhancing the operational reliability of switch machines. Summarization for the switch machine textual data facilitates the extraction of critical information, including fault phenomena, cause analysis, and solutions. Currently, textual data is often sparse and imbalanced in switch machine fault analysis, and traditional augmentation techniques generate samples that lack semantic consistency or violate domain rules, compromising summarization quality and diagnostic reliability. This paper presents a GAN-based data augmentation method incorporating domain rules to address these challenges. The experiment trains the summarization model on datasets augmented by diverse augmentation techniques to validate the proposed method. Experimental results show that our method generates high-quality, diverse data, significantly enhancing summarization performance and outperforming multiple baselines.