The development of virtual coupling technology provides solutions to the challenges faced by urban rail transit systems. Train tracking control is a crucial component in the operation of virtual coupling, which plays a pivotal role in ensuring the safe and efficient movement of trains within the train and along the rail network. In order to ensure the high efficiency and safety of train tracking control in virtual coupling, this paper proposes an optimization algorithm based on Soft Actor-Critic for train tracking control in virtual coupling. Firstly, we construct the train tracking model under the reinforcement learning architecture using the operation states of the train, Proportional Integral Derivative (PID) controller output, and train tracking spacing and speed difference as elements of reinforcement learning. The train tracking control reward function is designed. Then, the Soft Actor-Critic (SAC) algorithm is used to train the virtual coupling train tracking reinforcement learning model. Finally, we took the Deep Deterministic Policy Gradient as the comparison algorithm to verify the superiority of the algorithm proposed in this paper.
With the increasing scale of the urban subway, the total energy consumption of the subway has increased dramatically and poses a great challenge to the comfort of passengers and the punctuality of train operation. In order to ensure on-time train operation and passenger comfort, and at the same time reduce the energy consumption of subway operation, this paper proposes a Proximal Policy Optimization (PPO)-based optimization algorithm for the optimal control of subway train operation. Firstly, a reinforcement learning architecture for optimal control of subway train operation is constructed with the position and speed of train operation as the reinforcement learning state, energy consumption and comfort as the optimization objectives, and train operation time as the constraint. The proposed reinforcement learning model is trained by the PPO algorithm, and the reward scaling is added to the training process to accelerate the training speed and improve the efficiency of the algorithm. The experimental results show that the proposed PPO with reward scaling algorithm can effectively reduce train energy consumption and improve passenger comfort while ensuring on-time train operation.
29 May 2023 in Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability
Preventive maintenance procedures for systems are designed to improve long-term operating performance and reduce maintenance costs. This paper attempts to seek a trade-off between system reliability and maintenance costs and explores the optimal multi-objective maintenance strategy applicable to different field situations. We first provide an overview of the problem and analyze the impacts of varying different maintenance activities on reliability. Then, a mathematical model of reliability losses and maintenance costs is defined and derived, which will be used to construct a multi-objective maintenance strategy. In this research, the PSO-SA stochastic optimization algorithm is proposed to discover the Pareto frontier to find the optimal preventive maintenance threshold and inspection interval that minimizes reliability loss and maintenance costs. Finally, a case study is performed with railway VOBC as an illustration. The analysis results illustrate that the proposed multi-objective maintenance strategy can satisfy the preferences of various decision-makers. It is suitable for different maintenance needs and can support the development of on-site maintenance strategies.
The train control on-board subsystem (TC-OBS) plays an important role in the safety and efficiency of the high-speed train’s operation. Therefore, there is an urgent demand for the analysis of failure characteristics and the reliability of TC-OBS. In this paper, a specific data model is built for the TC-OBS operational and failure data based on data cubes. This model analyzed the failure distribution characteristics of TC-OBS from the combined angles of System Identification, Time and Operation Attribute through the operations of data cubes. Thus, the representative units and systems can be the research objects of the reliability evaluation. With these representative units and systems, this paper uses Bayesian estimation combined with Markov Chain Monte Carlo (MCMC) to estimate the parameters of the time between failures (TBF) distribution model and the reliability is analyzed. Simulation results show that the data model based on data cubes can offer an efficient and convenient method to analyze the failure characteristics and reliability of TC-OBS.