Optimization of cyclic air braking strategy for heavy haul trains: an ADP approach

The cyclic air braking strategy on the long steep downward slopes is one of the main challenges to the heavy haul train control in China. To overcome this dilemma, this paper proposes an optimization method of cyclic air braking strategy based on the approximate dynamic programming (ADP) algorithm which can achieve low maintenance costs and high running efficiency on the premise of safe operation. The optimization problem is described considering the characteristics of the heavy haul railways in China. Then the cyclic air braking strategy on the long steep downward slopes is formalized as a Markov decision process (MDP) and the critical elements in the ADP methodology are introduced according to the constraints and optimization objectives. Further, the value-iteration based ADP approach is proposed to solve the optimization problem of cyclic air braking strategy. The simulation experiments are carried out with the real-world data of the Shuohuang Line to illustrate the effectiveness of the proposed approach.