Research On ATO Multi-objective Optimization Control Strategy For High-speed Train

With the rapid development of high-speed railways,the traditional transport mechanism combining manual driving and automatic train protection system has been unable to ensure the safety of trains while taking the efficiency of transport into account.Based on this,ATO(Automatic Train Operation,ATO)was applied and has become a hot research topic at present.The ATO system can not only effectively improve transportation efficiency and ensure transportation safety,but also improve comfort,energy consumption,punctuality and other indicators.Therefore,it is of great social significance and economic value to develop the research of train automatic driving technology.In terms of control strategies for train ATO system,most of the existing work focuses on reducing energy consumption,which is a relatively single goal.Moreover,the existence of neutral zones and their impact on train operations are ignored,which is inconsistent with the actual situation.In this dissertation,objective functions such as energy consumption,comfort and punctuality are established,and a multi-objective optimization model is established by incorporating the neutral zone of train idleness into constraint conditions.On this basis,a differential evolution algorithm based on biogeography-based optimization algorithm is used to perform multi-objective optimization and generate the optimized target speed curve.In terms of train control algorithms for train ATO systems,this dissertation introduces cloud model intelligent control.Cloud model inference can achieve control of complex nonlinear systems without relying on accurate mathematical models,retain uncertainties in the controlled object and environment,and have strong adaptability and robustness to system state parameter changes.The work of this dissertation is mainly carried out from the following aspects:Firstly,the working principle and structure of the ATO system are deeply analyzed.According to the control principle of the ATO system,the optimization of the high-speed train running process is divided into two parts: the optimization of the target speed curve and the tracking of the target speed curve.To facilitate the optimization of the target speed curve,the corresponding evaluation index of ATO system performance was established,and the train operating condition transition and control strategy were analyzed.Secondly,the force analysis and modeling of the train are carried out,and the rigid multiparticle model is introduced.According to the multi-objective optimization model,which was established based on the evaluation index and constraint conditions such as neutral zones.Combined with the actual route data and train parameters,the improved biogeography algorithm is used to solve the problem.The simulation results show that under the hybrid control strategy,compared with the single time-node control strategy,the optimized target curve can take full advantage of the utilization time margin and use idle line to replace the required braking distance as far as possible,so as to further reduce the energy consumption required for operation.The comfort level is increased by 39.24%,and the energy consumption is reduced by 3.5653%.Finally,the PID speed controller based on a two-dimensional composite cloud model is designed to track the target speed curve,and the PID controller and fuzzy PID controller are set up for comparison.The simulation results show that the PID controller with the twodimensional composite cloud model has better tracking and control effects for the target velocity curve.