An optimised grinding target profile considering long-term service performance: A case study of no. 18 high-speed turnout

Abstract

The design of rail grinding profiles for turnout has always been a significant subject of research. This paper proposes a rail grinding target profile design method that can improve the serviceability of turnout. Firstly, the high-speed turnout rail profile was parameterised by non-uniform rational B-spline (NURBS), with the amount of key section control point grinding used as a design variable. Secondly, considering the evolution mechanism of turnout dynamics performance and rail wear, a turnout long-term service performance prediction model is established based on deep feedforward network (DFN), with relevant evaluation indexes as the objective function. Non-dominated sorting genetic algorithm-Ⅱ (NSGA-Ⅱ) is used to solve this multi-objective optimisation problem. Finally, a comparative analysis of the performance of the turnout profile before and after optimisation is conducted. The computed outcomes demonstrate that after the turnout is ground, all the dynamic performance indicators have substantially improved in the short term. Additionally, the maximum wear on the straight switch rail has been reduced by 31.2 % and the position of the occurrence has shifted backward, which has improved the stressing of the weak rail elements to some extent. In long-term service conditions, the optimised turnout profile sustains a higher level of riding quality compared to the measured profile. Optimisation of the profile can effectively decelerate the rail wear rate and aid in prolonging the service life of the turnout.