摘要
铁路货车需要长期运输外行,对货车车厢关键部件进行健康评估和预测性维护有助于提升货车外出作业的效率。然而,铁路运输环境较为恶劣且各部件间的运行机制复杂,现阶段货车车厢的预测性维护仍存在一些问题。定期不连续的状态异常监测、局部不精确的健康评估和事后低效的维修策略都阻碍了铁路货车车厢的预测性维护研究发展。针对上述问题,本文在调研铁路货车的实际运行情况后,构建了针对铁路货车车厢的预测性维护体系,并与齐车合作对该体系进行实际搭建和案例验证。结果表明,该体系架构实现了对铁路货车车厢实时的健康评估和基于数据的精准预测,并输出智能维护决策,为铁路货车健康管理的智能化发展提供了新的研究思路。
Due to long-term transportation and operation of railway freight cars, health assessment and predictive maintenance of key components of freight car carriages are helpful to improve the efficiency of freight cars. However, the railway transport environment is relatively poor and the operation mechanism between the components is complex. At present, there are still some problems in the predictive maintenance of freight car carriages. Regular discontinuous state anomaly monitoring, partial inaccurate health assessment and inefficient posterior maintenance strategy hinder the development of predictive maintenance research on railway freight car carriages. In response to the above problems, after investigating the actual operation of railway freight cars, this paper constructs a predictive maintenance system for railway freight car carriages, and carries out the practical construction and case verification of the system in cooperation with CRRC Qiqihar Rolling Stock Co., Ltd.. The results show that the system architecture realizes real-time health assessment of railway freight car carriages and accurate prediction based on data, and outputs intelligent maintenance decisions, which provides a new research concept for the intelligent development of railway freight car health management.
作者
付勇
郑文杰
赵奔
常雪梅
王睿瑞
明新国
FU Yong;ZHENG Wenjie;ZHAO Ben;CHANG Xuemei;WANG Ruirui;MING Xinguo(Dalian R&D Center of CRRC Qiqihar Rolling Stock Co.,Ltd.,Dalian 116052,China;School of Mechanical and Power Engineering,Shanghai Jiaotong University,Shanghai 200241,China;Shanghai CRRC Ribold Intelligent System Co.,Ltd.,Shanghai 201821,China)
出处
《智慧轨道交通》
2022年第5期32-37,共6页
SMART RAIL TRANSIT
关键词
预测性维护
铁路货车
健康评估
故障预测
维修决策
predictive maintenance
railway freight cars
health assessment
fault prediction
maintenance decision