Study On Multi-Objective Control Strategies Of Automatic Train Operation In Urban Rail Transit

With the acceleration of urbanization, urban traffic is confronted with more serious challenges. The safe, steady and efficient operation of trains in urban rail transit becomes the most effective way to improve the tension of urban traffic. The aggravation of population raises higher requirements for the development of urban rail transit. The study about ATO control strategy has become a hot topic in this field. ATO control needs to achieve multiple performance indexes such as safe operation, energy saving, punctuality, accurate stopping and comfortability. However, there are some shortcomings in present studies about ATO control strategy, some of the studies did not take into consideration of overall indexes, and did not reflect the characteristic of multi-objective in the operational process of the train; some took into consideration of overall indexes, but did not solve the problem of nonunity dimensions for all the performance indexes; some aimed at specific routines or environment and lacked of generality; some merely offline optimized the operation process of the train, which does not meet the requirements of the dynamic characteristic of ATO system.To solve the above problems, this thesis designs a multi-objective control strategy with high efficiency and generality. First of all, the ATO system is examined deeply, and based on the analysis of urban rail transit and its operational environment, multi-objective optimization model for train operation is built by using multi-objective optimization theory combined with penalty function method. The model takes into consideration of all indexes in train operation, and effectively solves the problem of nonunity dimensions for all performance indexes. Secondly, multi-objective optimization model is solved by using genetic algorithm, Pareto optimal solution of the model is obtained, and the optimization speed curve for train operation is created. Then the ATO integrated intelligent controller is designed by combining the fuzzy control algorithm with predictive control algorithm, the controller can control the train to effectively track the multi-objective optimization speed curve, and make fine adjustment dynamically according to the change of environment. Finally, the simulation platform for ATO multi-objective control strategy is established, the result of simulation test on the control strategy indicates that the control strategy successfully achieves accurate control for the train, and satisfies the requirements for multi objectives in train operation.