Search

Abstract Automatic train protection (ATP) system is essential for ensuring the safe operation of high‐speed trains. However, the existing extensive and fixed maintenance mode of the ATP system results in a waste of resources. To achieve a state of operation and maintenance that ensures both protection capability and economic efficiency, a lean method in a dynamic maintenance mode for the full life cycle of the ATP system is proposed. Firstly, reliability tests are carried out based on historical failure data. The parameter values of the possible life distribution are estimated by maximum likelihood method, and the optimal life distribution of different devices is obtained through the Kolmogorov–Smirnov hypothesis test. Secondly, a dynamic failure rate function is introduced to describe the impact of maintenance on device performance. A refined maintenance model is then established within the life cycle, and the dynamically changing preventive maintenance intervals and frequencies are obtained using a genetic algorithm. Finally, to mitigate the impact of the intermittent operation of ATP system on maintenance, the multidimensional relationships among the maintenance strategy, service time and operation mileage are revealed. The effectiveness of the proposed method is verified through an example test on a type of driver machine interface device.

There is limited research on the loss and reconstruction of car-following features. To delve into car-following's characteristics, we propose a car-following model based on LSTM-Transformer. By fully leveraging the advantages of long short-term memory (LSTM) and transformer models, this study focuses on reconstructing the input car-following features. Training and testing were conducted using 700 car-following segments extracted from a natural driving dataset and the Next Generation Simulation (NGSIM) dataset, and the proposed model was compared with an LSTM model and an intelligent driver model. The results demonstrate that the model performs exceptionally well in feature reconstruction. Moreover, compared to the other two models, it effectively captures the car-following features and accurately predicts the position and speed of the following car when features are lost. Additionally, the LSTM-Transformer model accurately reproduces traffic phenomena, such as asymmetric driving behavior, traffic oscillations and lag, by reconstructing the lost features. Therefore, the LSTM-Transformer car-following model proposed in this study exhibits advantages in feature reconstruction and reproducing traffic phenomena compared to other models.

Despite the significant impact of network hyperparameters on deep learning car-following models, there has been relatively little research on network hyperparameters of deep learning car-following models. Therefore, this study proposes a car-following model that combines particle swarm optimization (PSO) and gated recurrent unit (GRU) networks. The PSO-GRU car-following model is trained and tested using data from the natural driving database. The results demonstrate that compared to the intelligent driver model (IDM) and the GRU car-following model, the PSO-GRU car-following model reduces the mean squared error (MSE) for the speed simulation of following vehicles by 88.36% and 72.92%, respectively, and reduces the mean absolute percentage error (MAPE) by 64.81% and 50.14%, respectively, indicating a higher prediction accuracy. Dataset 3 from the drone video trajectory database of Southeast University and NGSIM’s I-80 dataset are used to study the car-following model’s cross-dataset adaptability, that is, to verify its transferability. Compared to the GRU car-following model, the PSO-GRU car-following model reduces the standard deviation of the test results by 60.64% and 32.89%, highlighting its more robust prediction stability and better transferability. Verifying the ability of the car-following model to produce the stop-and-go phenomenon can evaluate its transferability more comprehensively. The PSO-GRU car-following model outperforms the GRU car-following model in creating stop-and-go sensations through platoon simulation tests, demonstrating its superior transferability. Therefore, the proposed PSO-GRU car-following model has higher prediction accuracy and cross-dataset adaptability compared to other car-following models.

An automatic train protection (ATP) system is the core to ensure operation safety of high-speed railway. At present, failure rate change rules of the system are not well understood and the maintenance strategy is not refined. In order to improve the protection capability and maintenance level of high-speed trains, this paper proposes a decision tree machine learning model for failure feature extraction of ATP systems. First, system type, mean operation mileage, mean service time, etc. are selected as ATP failure feature parameters, and cumulative failure rate is selected as a model output label. Second, support vector machine, AdaBoost, artificial neural networks and decision tree model are adopted to train and test practical failure data. Performance analysis shows that decision tree learning model has better generalization ability. The accuracy of 0.9761 is significantly greater than the other machine learning models. Therefore, it is most suitable for failure features analysis. Third, interpretability analysis reveals the quantitative relationship between system failure and features. Finally, an intelligent maintenance system for ATP systems is built, which realize the refined maintenance throughout life cycle.

Copyright of Maintenance & Reliability / Eksploatacja i Niezawodność is the property of Polish Scientific & Technical Society Consumables, Polish Maintenance Society and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)