Abstract: Rail profile optimization is a critical strategy for mitigating wear and extending service life. However, damage at the wheel-rail contact surface goes beyond simple rail wear, as it also involves fatigue phenomena. Focusing solely on wear and not addressing fatigue in profile optimization can lead to the propagation of rail cracks, the peeling of material off the rail, and even rail fractures. Therefore, we propose an optimization approach that balances rail wear and fatigue for heavy-haul railway rails, to mitigate rail fatigue damage. Initially, we performed a field investigation to acquire essential data and understand the characteristics of track damage. Based on theory and measured data, a simulation model for wear and fatigue was then established. Subsequently, the control points of the rail profile according to cubic non-uniform rational B-spline (NURBS) theory were set as the research variables. The rail's wear rate and fatigue crack propagation rate were adopted as the objective functions. A multi-objective, multi-variable, and multi-constraint nonlinear optimization model was then constructed, specifically using a Levenberg Marquardt-back propagation neural network as optimized by the Particle Swarm Optimization algorithm (PSO-LM-BP neural network). Ultimately, optimal solutions from the model were identified using a chaos microvariation adaptive genetic algorithm, and the effectiveness of the optimization was validated using a dynamics model and a rail damage model.