基于泊松-威布尔过程的钢轨修理周期预测研究
Research on prediction for rail maintenance period based on Poisson-Weibull process

在将线路上连续的钢轨离散划分成多个钢轨单元的基础上，提出基于泊松-威布尔过程的钢轨修理周期预测模型。模型以单个钢轨单元为研究对象，在充分考虑不同空间位置钢轨单元劣化过程异质性的前提下，根据钢轨单元伤损的历史检测数据，对每个钢轨单元的维修周期和大修周期进行了预测，利用北京地铁2号线钢轨的伤损检测数据对模型的有效性进行验证。研究结果表明：本文提出的钢轨修理周期预测模型能够为管理者合理安排钢轨的修理计划提供足够的决策支持，辅助管理者实现钢轨的“预防修”。
In this paper, continuous rails on a line of track are divided into rail segments discretely and a prediction model based on the Poisson-Weibull process is proposed. In the proposed model, each single rail segment is regarded as a unit whose maintenance and renewal period are analyzed individually relying upon the history records of its rail defect detection, considering the heterogeneities in deterioration processes of rail segments in separate locations. Finally, the model is validated through a case study of the Beijing Metro, using inspection records of rail defects of Line 2. The model is found to show good agreement with the rail inspection and maintenance records of the Beijing Metro, indicating its appropriateness for use by railroad management in scheduling future rail maintenance plans and realizing the ‘preventive maintenance’ of the rails