Research On Optimization Of ATO Energy Saving Operation Control Strategy For Urban Rail Train

China’s urban rail transit has been developing rapidly in recent years,and the total operating mileage and passenger volume are growing rapidly,which brings huge energy consumption and operating costs while alleviating urban traffic congestion.The energy consumption of urban rail transit is dominated by electrical energy consumption,and among these energy consumptions,the energy consumption of train traction accounts for almost half of all energy consumptions.Therefore,to lower the cost of operating the urban rail transit system and to fulfill the objectives of energy conservation and emission reduction,we can start by reducing the traction energy consumption of trains.An important instance of automation and intelligence in urban rail transit is Automatic Train Operation(ATO)system.The ATO system on the train calculates the target speed curve in the optimization layer according to the operation command and the range of the Movement Authority(MA)combined with the line parameters,the control layer tracks the target speed profile and outputs traction and braking commands to realize automatic train travel between stations.Traditional train energy-saving research uses algorithms to optimize the intended speed profile under restrictions,but does not fully take into account the speed tracking control of ATO systems,the train tracks deviations in the target speed profile,which affects the energy consumption of the train operation.In this paper,a genetic particle swarm algorithm is proposed to optimize the target velocity profile,while the real-time tracking of the energy-saving velocity profile is achieved by Artificial Bee Colony PID.The main research content is as follows:First of all,to clarify the research background and significance of the topic,the theory related to the ATO system,including its principle,main functions,double-layer structure,was studied,the relationship between the ATO system and other subsystems of automatic train control is clarified.Clarify the train ATO control strategy and optimization principles,the train traction,braking force and resistance during operation are analyzed to derive the combined forces on the train under different operating conditions,and a train dynamics model is established.Deriving the relationship between the combined force and the speed and acceleration of the train and the distance travelled,for the train running process,the mathematical model for energy saving optimization of trains is established under the constraints of operating speed,on-time precise stopping,and comfort index.Secondly,propose the Genetic Particle Swarm Optimization Algorithm(GAPSO),the standard Particle Swarm Optimization(PSO)algorithm’s inertia weights and learning factors are improved by the proposed method,the cross-variance operator of Genetic Algorithm(GA)is added,demonstrating the GAPSO algorithm’s superiority in function exploration.The algorithm is used to iteratively search for the optimal value and derive the target speed curve of energy saving in the optimization layer of the ATO system with the minimum value of traction energy consumption as the objective function.Thirdly,there are issues with the typical PID control used for automatic train driving,such as the inability to timely modify parameters,the susceptibility of the tracking control to oscillation,and the low level of stability,the Artificial Bee Colony(ABC)method is used in the design for real-time PID parameter self-tuning.ATO tracking control layer uses an ABCPID speed controller to precisely track the speed profile of energy-saving goals,lower the amplitude of the difference between the actual train speed curve and the target speed curve to effectively reduce the deviation from the target traction energy consumption.Finally,by integrating the line parameters during train operation,the simulation experiment of the train operation process is then completed,to confirm the viability of the suggested target speed profile energy-saving optimization method,the energy consumption indices before and after optimization are compared.In addition,following operation optimization,the ABC-PID speed controller is utilized to track the speed profile of the energysaving target curve.The tracking performance is compared to that of the PID speed controller.Determine whether ABC-PID speed control can meet the ATO system control performance requirements by analyzing the tracking control effect under various operating situations,the train’s adaptability is increased,and automatic train operation that is both safe and energyefficient is made viable by the ability to precisely track the energy-saving target speed curve.