Optimization and Design of a Railway Wheel Profile Based on Interval Uncertainty to Reduce Circular Wear

Wheel tread wear is a form of wheel damage that can seriously affect the performance of freight vehicles. A new numerical approach to optimizing wheel profiles can reduce circular wear on the LM wheel in the design cycle. This approach considers the influence of different line conditions and speed fluctuation on wheel wear, along with the performance of the wheel and the rail as the materials wear. In this approach, a nonlinear numerical optimization model for the wheel tread profile is built through a backpropagation (BP) neural network method. The multipoint Kik–Piotrowski (KP) contact mechanics model is applied to calculate the wheel/rail normal force, tangential creep force, the stick-slip area, and the size and shape of the contact patch. The optimal profile is obtained through the genetic algorithm (GA) method. In order to better reflect the random characteristics of wheel/rail matching and interval uncertainty, a random sampling technique is used to generate a random data sample at typical operating speeds.