Narrow Results

With the application of the dynamic control system, Cellular Automata model has become a valued tool for the simulation of human behavior and traffic flow. As an integrated kind of railway signal-control pattern, the four-aspect color light automatic block signaling has accounted for 50% in the signal-control system in China. Thus, it is extremely important to calculate correctly its carrying capacity under the automatic block signaling. Based on this fact the paper proposes a new kind of "cellular automata model" for the four-aspect color light automatic block signaling under different speed states. It also presents rational rules for the express trains with higher speed overtaking trains with lower speed in a same or adjacent section and the departing rules in some intermediate stations. In it, the state of mixed-speed trains running in the section composed of many stations is simulated with CA model, and the train-running diagram is acquired accordingly. After analyzing the relevant simulation results, the needed data are achieved herewith for the variation of section carrying capacity, the average train delay, the train speed with the change of mixed proportion, as well as the distance between the adjacent stations.

Train delay is a serious issue that can spread rapidly in the railway network leading to further delay of other trains and detention of passengers in stations. However, the current practice in the event of the trail delay usually depends on train dispatcher’s experience, which cannot manage train operation effectively and may have safety risks. The application of intelligent railway monitor and control system can improve train operation management while increasing railway safety. This paper presents a methodology in which train timetabling, platforming and routing models are combined by studying the real-time adjustment and optimization of high-speed railway in the case of the train delay in order to produce a cooperative adjustment algorithm so that the train operation adjustment plan can be obtained. MATLAB computer programs have been developed based on the proposed methodology and adjustment criteria have been established from knowledge data bases in order to calculate optimized solutions. A case study is used to demonstrate the proposed methodology. The results show that the proposed method can quickly adjust the train operation plan in the case of the train delay, restore the normal train operation order, and reduce the impact of train delay on railway network effectively and efficiently.

Accurate prediction of train delay recovery is critical for railway incident management and providing passengers with accurate journey time. In this paper, a two-stage prediction model is proposed to predict the recovery time of train primary-delay based on the real records from High-Speed Railway (HSR). In Stage 1, two models are built to study the influence of feature space and model framework on the prediction accuracy of buffer time in each section or station. It is found that explicitly inputting the attribute features of stations and sections to the model, instead of implicit simulation, will improve the prediction accuracy effectively. For validation purpose, the proposed model has been compared with several alternative models, namely, Logistic Regression (LR), Artificial Neutral Network (ANN), Support Vector Machine (SVM) and Gradient Boosting Tree (GBT). The results show that its remarkable performance is better than other schemes. Specifically, when the error is extended to 3min, the proposed model can achieve up to the accuracy of 94.63%. It proves that our method has high value in practical engineering application. Considering the delay propagation of trains is a complex process, our future study will focus on building delay propagation knowledge base and dispatcher experience knowledge base.