Application of Multi-Objective Particle Swarm Optimization in Optimization of Subway Speed Curve.

In order to solve the problems of energy saving and punctuality of single train operation in urban rail transit, train operation strategy improvement and operation curve optimization are combined. The control strategy of train operation is analyzed in view of the change of additional resistance of train in the actual line. A multi-objective optimization model is established by taking the train running time and energy consumption as the optimization objectives. On the basis of Pareto principle, a multi-objective particle swarm optimization algorithm based on adaptive grid (AGA-MOPSO) is adopted. At the same time, the inertia weight is processed by linear differential decreasing method, and then the train condition transition point is optimized. The Pareto solution set is screened by fuzzy membership function. Simulation results show that AGA-MOPSO has obvious advantages in diversity, stability and optimization effect compared with conventional particle swarm optimization (PSO). In addition, the comparison of three different control strategies shows that better control strategy optimization effect is achieved by adding multiple idle conditions to the actual complete line. [ABSTRACT FROM AUTHOR]