数字孪生在轨道车辆轮对预测性维修中的应用
打开文本图片集
Application of Digital Twin in Predictive Maintenance of Wheelsets for Rail Vehicles
JIANGShijun，WANG Zihan，CAO Guibao （CRRC Qingdao Sifang Rolling Stock Research Institute Co.，Ltd.，Qingdao 266031，China）
Abstract：In the field of predictive maintenance of wheelsets for rail vehicles，to solve the application bottleneck of purely data-driven model’ caused by insuficient stock data intheearly stage of operation，the article proposes a predictive maintenance framework based on the digital twin technology. Digital twin is an innovative virtual modeling method which has realized the data interaction and fusion between the entity of wheelsetand its virtual model by buildinga bidirectional interconnection mechanism between physical space and virtual space.This framework is designed with four core functional modules：prediction of key dimensions of wheelset，evaluation of vehicle performance，evaluation of whel-rail contact thresholdandanalysisof wheelset damage. It effectively solves the three major problems of traditional models，including lagging prediction results，restrictive stock data and single external inputs. The predictive maintenance framework integrating the digital twin can improve the accuracy of model predictions under conditions of insufficient data and provide comprehensive evaluations including whel-rail mechanical properties，providing a data support for making maintenance decisions.This method breaks through the technical limitations of the traditional predictive maintenance and provides a new technological path for the inteligent operation and maintenance of key components of urban rail transit vehicles.It has important practical value and promotion significance for promoting the construction of smart urban rail transit.
Key words： smart urban rail； digital twin;application of digital twin；whelset maintenance strategy; dynamical model
近年来随着交通强国、智慧城轨等国家重要战略规划的部署，轨道交通行业不断涌现出以大数据、物联网、人工智能等新兴信息技术为代表的轨道交通智能化系统，持续影响车辆关键部件维修方式的迭代更新，并促进构建形成安全、便捷、高效、绿色、经济的中国式智慧型城市轨道交通[1]。（剩余4797字）
