Research on Multi-objective Optimal Control of Heavy Haul Train Based on Improved Genetic Algorithm

Abstract

The study of heavy haul train (HHT) automatic and stable driving strategy has become the focus of many scholars due to the large load capacity, long body length, concentrated power, and complex line conditions. HHT is difficult to control, drivers are fatigued in manual driving, traction and braking force increase during operation, and the transmission time of braking waves is lengthened, resulting in serious longitudinal impulse, which leads to a series of serious accidents. In this paper, aiming at the safe and stable driving of HHT, the dynamic model of multi-particle model was established and designs the multi-objective curve optimization strategy of fuzzy adaptive genetic algorithm (FAGA). A fuzzy reasoner is mainly used for the adaptive selection of crossover and mutation probability. In terms of safety, energy-saving and punctuality designed train operation target curve combines the actual railway routes (speed limit, ramp, curve, etc.), and compares the optimization effect with standard genetic algorithm. Finally, an improved high-order model-free adaptive iterative learning control algorithm is adopted to track the optimized target curve with high precision, and compared the results of the standard iterative learning control algorithm. The simulation results show that the control method used in this paper can better track the ideal speed target curve and realize the optimal control of the HHT driving curve.