The on-board equipment of Chinese Train Control System-3 (CTCS-3) plays a key role in protecting trains from over-speeding. Conventional over-speed protection methods monitor the speed at discrete time instants. However, the over-speed behavior between discrete time instants cannot be detected, which may cause potential risks. To address this problem, this paper proposes a hybrid safety observation method to monitor train speed throughout the operation. In the proposed method, the train behavior is modeled with a hybrid automata, which takes parameters that affect train movement into consideration. Train behavior in the next control cycles is predicted periodically by computing the reachable set of the model. The safety property set is obtained according to the runtime speed limits. The intersection check between the reachable set and safety property set is performed to decide whether train speed may exceed the speed limit in a short future period. A case study is presented to demonstrate the proposed method in action by using real engineering data from the Chinese railway industry. The results show that the observation method is feasible in verifying the violations of CTCS-3 on-board equipment safety properties.

Trajectory prediction of the train ahead is vital for deciding the minimum safe distance for train separation. An important research challenge, in this regard, is how to effectively and accurately estimate the trajectory of the train ahead using spatiotemporal approaches with train operating data. In this paper, we present a novel hybrid model for predicting train trajectories by integrating Long Short-Term Memory (LSTM) and Kalman Filter (KF). In the proposed hybrid LSTM-KF model, the LSTM model is used to analyze time series data and discover the long-term dependencies of train trajectory data, which can be assumed as observation data for the KF model. The KF model can combine train dynamics mechanism to extract local features of train operation data, so as to smooth the train trajectory predicted by LSTM model. A novel on-the-fly algorithm is devised for efficient realization of the proposed LSTM-KF model. Experiments are carried out using the train data collected from Chengdu Metro Line 8. The results indicate that our hybrid LSTM-KF model has greatly improved the accuracy of long-term train trajectory prediction.

In this article, we combined a search-based technique with model-based mutation testing to overcome the inherent computational cost that comes with the test-case generation of the Chinese Train Control System Level 3 (CTCS-3) train control system by providing a newly designed fitness function to guide the search process of test cases. First, we defined the test-case inputs as timed input traces , which can easily deal with noninput-enabled systems with both input events and input variables. Because the input sequence of the timed input traces can be potentially infinite, they can be more flexible in dealing with different scales of train control systems than can the traditional model-checking techniques. Furthermore, we proposed a way of encoding timed input traces as blocks of inputs for the genetic algorithm, together with crossover and mutation operators, to reduce the search space and improve algorithm efficiency. By using the encoded input blocks as individuals, the test cases generated from the train control system will be more compact and easier to perform. Finally, we applied the mutation operators to the mode-transition function of the CTCS-3 from which all of the known faults have been considered comprehensively. To evaluate the coverage of the test cases generated and compare the performance of different methods, the benchmarking indicators of conformance relation score (CRS), average CRS, and weighted CRS have all been analyzed. In addition, we performed an experiment to determine the extent to which the maximum block width can influence the search performance as a guidance for parameter selection in practice.

The accurate trajectory of the train ahead with more dynamic behaviour, such as train position, speed, acceleration, etc., is the critical issue of virtual coupling for future railways, which can drastically reduce their headways and increase line capacity. This paper presents an integrated convolutional neural network (CNN) and long short-term memory (LSTM) hybrid model for the task of trajectory prediction. A CNN–LSTM hybrid algorithm has been proposed. The model employs CNN and LSTM to extract the spatial dimension feature of the trajectory and the long-term dependencies of train trajectory data, respectively. The proposed CNN–LSTM model has superiority in achieving collaborative data mining on spatiotemporal measurement data to simultaneously learn spatial and temporal features from phasor measurement unit data. Therefore, the high-precision prediction of the train trajectory prediction is achieved based on the sufficient fusion of the above features. We use real automatic train operation (ATO) collected data for experiments and compare the proposed method with recurrent neural networks (RNN), recurrent neural networks (GRU), LSTM, and stateful-LSTM models on the same data sets. Experimental results show that the prediction performance of long-term trajectories is satisfyingly accurate. The root mean square error (RMSE) error can be reduced to less than 0.21 m, and the hit rate achieves 93% when the time horizon increases to 4S, respectively.