Search

Optimization on trajectory planning is significant offering the driver or automatic train operation system a guidance to drive the train efficiently. An optimal trajectory is subject to operational, geographic, physical and dynamic constraints. In previous studies, researchers have put much effort into offline optimization. However, operational errors in real situation are rarely taken into consideration. Thus, this paper proposes a dynamic trajectory planning to address the deviation. Specifically, first, we design an online optimization framework to display model predictive control-based train trajectory planning theory. Various constraints are set for optimization problem. Second, taking energy consumption and punctuality into consideration, we propose a moving window method to search the optimal variables, which are applied to evaluate the fitness function. Plus, to improve global search ability and convergence rate, we present a multi-swarm particle swarm optimization by dividing the population into several parts. On the basis of operational time error at reallocation positions, we design a novel weight allocation mechanism for the revaluation of fitness function. At last, taking real data from Beijing-Shanghai high-speed railway as an example, the robustness and effectiveness of the proposed algorithm is proved by comparing multiple parameters with some numerical results of simulations. The results show that the proposed method can adjust operating strategy dynamically so that the train runs in an energy-efficient way. Additionally, in delay scene, the proposed method can also guide the train to catch up with the scheduled time and save energy consumption. [ABSTRACT FROM AUTHOR]

With increasing energy consumption in urban rail transit systems, researchers have paid significant attention to energy-saving train control. In this paper, we propose an effective train trajectory optimization method to reduce the energy consumption based on coasting control, in which coasting control regimes are added to balance running time and energy consumption. For better determining the starting points of coasting control regimes, the whole train running process is divided into several subintervals. Then, aiming to achieve energy efficiency, coasting regimes are added to the subintervals with high energy-saving effects, in which more energy consumption can be reduced with the same running time addition. Based on this, a coasting control method is proposed to generate energy-saving trajectories considering train dynamics, safety, and punctuality. In addition, the proposed method can solve the multisection energy-saving train trajectory optimization problem to obtain optimal running time schemes and related trajectories. Finally, numerical examples based on one of the Beijing metro lines are implemented to verify the effectiveness of the proposed method. The results show that, for the single-section train control problem, the proposed coasting control algorithm can achieve significant energy-saving effects compared to the practical trajectory and calculate energy-saving trajectory in shorter computation times compared to the dynamic programming method. Meanwhile, for the multisection train control problem, energy consumption can be further reduced by optimizing trajectories and running times integratedly. [ABSTRACT FROM AUTHOR]

• A relationship between fuel consumptions and speed guidance of platoon is discussed. • Optimization models based on vehicle platoon guidance strategy are developed. • Average fuel consumption reduced by about 30% with minimal increase in travel time. It is a common traffic phenomenon for vehicles to form a platoon to pass through intersections. This paper presents efforts to investigate the fuel saving potential of an optimization model based on vehicle platoon guidance strategy (VPGS) at signalized intersections. The VPGS-based optimization model includes five steps: (1) dynamic vehicle platoon recognition, (2) formulation of running time for vehicle platoons passing through the intersection, (3) analysis of the leading vehicle trajectory, (4) analysis of the following vehicle trajectories to generate a complete platoon trajectory set, and (5) optimization of the platoon trajectory considering fuel savings. A vehicle specific power (VSP) based approach is applied to estimate fuel consumption. A typical signalized intersection in Beijing is selected to verify the optimization model. The proposed optimization model can quantitatively control the fuel saving effects. The results show that VPGS has significant potential for fuel savings without increasing vehicle travel time, and the average fuel consumption per vehicle decreased by about 30%. [ABSTRACT FROM AUTHOR]

With the rising urge to mitigate the green house effect, reducing the energy consumption of the freight train attracts much attention. Multiple constraints should be taken into account to solve the energy-efficient control problem, which can be reformulated as the multi-objective optimization. This paper proposes a Reinforcement Learning (RL) method for the multi-objective speed trajectory optimization with the goal of the energy-efficiency, punctuality and accurate parking simultaneously. Since the solution space for the optimization problem in this paper is large and discrete, a Gated Recurrent Unit (GRU)-based network is proposed to achieve the fast approximation of the optimal value function instead of the lookup Q-table. Meanwhile, a new architecture, including the embedding matrix, is used to model the control sequence that generates the speed trajectory. Besides, this paper constructs a Deep Q-Network (DQN) framework to train the GRU network without relying on the prior knowledge of the freight train model. Finally, the Intelligent Train Operation (ITO) algorithm is proposed and verified, using the data of Beijing–Guangzhou Railway Line and HXD1B electric locomotive. The case studies indicate that the reward function for the ITO algorithm converges rapidly and the energy consumption monotonically decreases with the trip time, which satisfies the multiple optimization objectives. In terms of saving the energy consumption, the ITO algorithm performs better than Fuzzy Predictive Control (FPC), Genetic Algorithm (GA) and the field test data. The computation time of different speed trajectories demonstrates that the ITO algorithm is applicable to generating the optimal speed trajectory off-line. • A novel multi-objective optimization model based on the reinforcement learning is proposed to search for the optimal control sequence. The embedding matrix is used to formulate the control sequence. • An intelligent train operation algorithm based on the gated recurrent unit network is proposed to compute the optimal speed trajectory without the precise train dynamics or the prior knowledge from the experienced drivers. • The energy consumption is reduced by 3.17%, 0.71% and 6.77% respectively comparing with fuzzy predictive control, genetic algorithm and field test data. [ABSTRACT FROM AUTHOR]

The energy-efficient driving of automatic train operation (ATO) system in high-speed railway systems has attracted more and more attention. Different from the energy-efficient automatic train control problem for metro trains, the traction/braking forces given by high-speed ATO systems are currently not continuous but discrete values corresponding to traction/braking notches due to the limited communication interface between ATO systems and rolling stocks. In addition, since high-speed trains are powered by single-phase alternating current, there is no power supply for train traction in neutral sections, which is introduced to separate two catenaries powered by currents with different phases. In this paper, we propose a discrete-space based mathematical formulation for the energy-efficient automatic train control problem for high-speed trains, where binary variables are introduced to indicate the traction/braking notch selections and to indicate whether a discrete space interval is a neutral section or not. The mathematical formulation is then transformed into a mixed integer linear programming (MILP) model, which can be solved by existing solvers. However, due to the discretization of the space the discrete traction/braking notches, the resulting MILP problem could be infeasible and the optimal driving strategy cannot be obtained. Hence, we present a novel relaxation method, i.e., the final braking notch relaxation method, to relax a few constraints in the final braking phase and to generate a feasible speed profile. Comprehensive experiments are investigated based on Beijing–Harbin high-speed railway line, where the energy consumption of the speed profiles with discrete (i.e., notch-based) traction/braking forces is slightly higher than that with continuous traction/braking forces. Moreover, the impacts of the neutral section locations and the effects of different numbers of traction/braking notches are deeply analyzed. • Energy-efficient automatic train operation for high speed railway lines. • A new optimal train control model with discrete notches and neutral sections. • Practically inspired final braking notch relaxation method to eliminate infeasibility. • The relaxation of discrete notches enhances computational efficiency. • Our model and method were tested based on data of Chinese high-speed railways. [ABSTRACT FROM AUTHOR]

The trajectory of the urban heat island (UHI) centroid in three dimensions indicates the overall variation of the intensity and distribution of the UHI. This study applied the Gaussian volume model on the daily MODIS/LST products from 2000 to 2012 to derive the UHI centroid in Beijing on a multi-temporal scale. The trajectories indicated that (1) on a diurnal scale during July–September, the daytime and nighttime centroids of the UHI were primarily located in the Xicheng district near the city center, and the mean intensity was from 2.12 to 2.97°C. The daytime centroid was in the south of the nighttime centroid and demonstrated a higher intensity and a larger core area, where Aqua obtains a higher intensity than Terra. The movement of the UHI centroid was also more significant in the north–south direction than in the east–west direction; (2) on a monthly scale, the daytime centroid moved from the northeast to the southwest by (1.85, 2.91) km from July to September, and the intensity varied from 2.16°C (September) to 3.09°C (August), while the nighttime centroid generally moved anticlockwise from January to December, and the intensity varied from 1.98°C (July) to 3.07°C (January); and (3) on an annual scale, the daytime UHI centroid in August and the nighttime UHI centroid moved toward the northeast by (2.15, 1.31) km and (0.43, 0.89) km, respectively. There was a dramatic change in the UHI prior to 2008, which was most likely caused by the numerous preparation projects for the 2008 Beijing Olympic Games. Correlation analysis demonstrated that the hot and medium-hot landscapes exhibited positive contributions to the variation of the horizontal location of UHI centroid, and NDVI and albedo showed positive contributions to the variations of daytime (less than 10%) and nighttime (close to 50%) UHI centroids, respectively. Also, we discussed the relationship between Z-dimension of UHI centroid and other UHI indicators, and the impact of missing data. This study presents scientific insights for urban planning and management in Beijing and motivates the investigation of comprehensive changes in UHI of other metropolises worldwide. [ABSTRACT FROM AUTHOR]