Speed Curve Optimization Based On Memetic Algorithm And Predictive Tracking Control For Urban Rail Train

Because of its advantages of large capacity,good comfort and high safety,the urban rail train has become one of the key development objects in the field of rail transit.For now,the urban rail train has been gradually transitioning from the manual driving mode to the automatic driving mode all over the world.Therefore,the Automatic Train Operation(ATO)system has been developed rapidly due to its advantages of the rapidity,punctuality and security.In this paper,the speed curve optimization and tracking control of the ATO system of the urban rail train are studied in depth,and the main contents are as follows.(1)The multi-objective optimization model of the urban rail train is built by taking the energy consumption,comfort,stopping accuracy arid punctuality as optimization indexes,and the linear combination weighting method based on entropy is adopted to solve the weight coefficient of each index.At the same time,the Memetic Algorithm(MA)is used to solve the optimization model of train.For the MA,the Genetic Algorithm(GA)is used for the global search strategy,and the Hill Climbing(HC)algorithm is adopted for the local search strategy.(2)The MA is improved,and the ideas of the directional mutation,gene modification,fusion distance and Opposition-Based Learning(OBL)are introduced,which not only improves the convergence speed and optimization ability of the MA,but also improves the target speed curve to a certain extent in each performance index.(3)The Dynamic Matrix Control(DMC)principle is used to design the ATO speed tracking controller,and a method of the online adjustment of the softness factor based on the fuzzy satisfaction indexes of the control targets is presented,so that the actual speed of the urban rail train can accurately track the speed of the target curve.Finally,according to the actual line data of Dalian metro line 12,the MATLAB/SIMULINK is used to simulate the train ATO system.The simulation results verify the feasibility and effectiveness of the improved MA and the DMC with the online adjustment of the softness factor in the aspects of the train speed curve optimization and speed tracking control.