Search Results (2)

The train dynamics modeling problem is a challenging task due to the complex dynamic characteristics and complicated operating environment. The flexible formations, the heavy carriage load, and the nonlinear feature of air braking further increase the difficulty of modeling the dynamics of heavy haul trains. In this study, a novel data-driven train dynamics modeling method is designed by combining the attention mechanism (AM) with the gated recursive unit (GRU) neural network. The proposed learning network consists of the coding, decoding, attention, and context layers to capture the relationship between the train states with the control command, the line condition, and other influencing factors. To solve the data insufficiency problem for new types of heavy haul trains to be deployed, the model agnostic meta-learning (MAML) framework is adopted to achieve knowledge transferring from tasks supported by large amounts of field data to data-insufficient tasks. Effective knowledge transfer can enhance the efficiency of data resource utilization, reduce data requirements, and lower computational costs, demonstrating considerable potential in the application of sustainable development. The simulation results validate the effectiveness of the proposed MAML-based method in enhancing accuracy. Full article

The intercity railway is subject to variation and fluctuation in demand both in time and space over a day to a large extent. In that case, more advanced line planning techniques are practically needed to match the non-equilibrium passenger demand. We propose an integer linear programming model for adapting to the fluctuating demand and improving rail line profit, in which the multi-period planning approach and flexible train composition mode are taken into consideration. In particular, we also consider the limitations of the carriage and the dynamic transfer of resources during a finite period to ensure the better implementation of the line planning and subsequent operation plans. Our purpose is to improve on previous line planning models by integrating the multi-period strategic-level line planning decision with resource constraints. Since the problem is computationally intractable for realistic size instances, an improved round heuristic algorithm that is based on linear relaxation is proposed and we compare the round heuristic performance with the commercial solver Gurobi on artificial instances. The numerical experiments that are based on an intercity railway in China certify the effectiveness and applicability of the proposed model and algorithm. We evaluate the impact of different optimization parameters and reserved carriages and the computation results show that in comparison to the fixed composition mode, the proposed approach can improve the utilization efficiency of carriage resources and increase the line profit by 1.9% under the same carriage resource conditions. Full article