北京交通大学学报2025，Vol.49Issue(6)：1-13,13.DOI:10.11860/j.issn.1673-0291.20250033
基于跨模态特征融合与Transformer-XL递归记忆机制的转辙机故障诊断
Switch machine fault diagnosis based on cross-modal feature fusion and Transformer-XL with recursive memory mechanism
摘要
Abstract
The stable operation of switch machines is a key guarantee for the safety of High-Speed Rail-ways(HSRs).With the increasing demand for intelligent railway systems,higher requirements are im-posed on the precise perception and autonomous diagnosis of switch machine working conditions.To overcome the limitations of traditional methods in terms of diagnostic accuracy,computational real-time performance,and anti-interference capability,this paper constructs an intelligent diagnosis model that integrates cross-modal feature attention mechanism and Transformer-XL recursive memory mechanism.The proposed model enhances fault recognition and environmental adaptability under com-plex operating conditions.By introducing a cross-modal attention mechanism,it enables dynamic inter-action between power curve signals and switch rail vibration signals,mitigating the judgment bias caused by missing single-modal information.The Transformer-XL with recursive memory mechanism dynamically adjusts the model's perception of historical information,allowing it to extract state infor-mation across time windows.Additionally,1D-CNN is incorporated for short-term dynamic feature extraction,optimizing global sequential modeling while improving noise robustness and reducing com-putational complexity.Experimental results demonstrate that the proposed model exhibits significant advantages in cross-modal feature representation,long-term dependency modeling,noise robustness,and computational efficiency.This study provides an intelligent diagnostic solution for HSR mainte-nance,featuring high efficiency,low resource consumption,and strong environmental adaptability.It facilitates the transition from reactive maintenance to predictive maintenance,thereby improving opera-tional safety margins and robustness.关键词
智能运维/转辙机/故障诊断/跨模态注意力/Transformer-XL/递归记忆机制Key words
intelligent maintenance/switch machine/fault diagnosis/cross-modal attention/Transformer-XL/recursive memory mechanism分类
交通工程引用本文复制引用
刘倡,杨世武,刘海威,白英杰,刘尚合..基于跨模态特征融合与Transformer-XL递归记忆机制的转辙机故障诊断[J].北京交通大学学报,2025,49(6):1-13,13.基金项目
国家重点研发计划(2020YFC2200704) （2020YFC2200704）
国家铁路局重点研发计划(KF2024-056) National Key R&D Plan(2020YFC2200704) （KF2024-056）
Key R&D Plan of National Railway Administration(KF2024-056) （KF2024-056）
