Search

Due to wheel-rail coupling and other factors, the fault feature of train bogie bearings can be easily masked by noise. The superposition of speed changes under fault shock further causes more difficulty for the direct denoising of signals. Therefore, a denoising framework that can directly process the original vibration signal under speed change has been proposed in this study. The framework includes a variable peak search approach and an adaptive least square (ALS) algorithm. The established variable peak search can capture the transient shock at variable speed. Besides, the proposed ALS algorithm can adaptively search the optimal parameters for the best denoising results. Simulations and actual equipment tests have demonstrated that the proposed framework can effectively reduce noise which has a satisfactory result under speed change conditions. Meanwhile, the performance is superior to other approaches showing its potential for applications on rail transit trains. Especially our study may apply to other typological vehicles under speed change conditions.

Deep Reinforcement Learning (DRL) is the most promising technology for improving high-speed train’s energy efficiency and operation quality. Existing solutions, however, suffer from three significant limitations: 1) They cannot effectively constrain the huge exploration space generated by high-speed trains under high temporal deformability and long-distance trips; 2) The reward function has no adaptability to the different energy-efficiency difficulties of different travel schedules, and the agent will receive incorrect reward signals, requiring manual adjustment; 3) They do not avoid the invalid action sequences of the agent well. To address this challenge, we propose a revolutionary Boundary Constrained and Pre-evaluated Reinforcement Learning (BCPRL) approach to alleviate these issues. This approach combines the Shrink Trajectory Exploration Space (STES) module, the Pre-evaluated Energy-efficiency Scenario Complexity (PESC) module, and the Twin Delayed Deep Deterministic Policy Gradient (TD3) module and uses a hybrid of STES and TD3 to make train operation decision-making to improve the operation quality and learning efficiency of the agent. Numerical experiments validate the effectiveness of the BCPRL approach, which, by drastically reducing the exploration space and getting the agent the correct reward signal, not only maintains excellence in efficiency and punctuality but also far surpasses the other baseline approaches in learning efficiency and robustness.

As one of the important components of train traction motor, the bearing plays a key role in ensuring the safety of train operation. At present, the existing fault diagnosis methods for train traction motor bearings have the disadvantages of poor feature extraction ability, slow diagnosis speed, and low diagnosis accuracy. To solve the above problems, an improved deep residual network (IDRN) is proposed in this paper. Firstly, a new residual convolution block (RCB) is proposed to improve the extraction ability of hidden features. Secondly, the squeeze and excitation block (SE) is embedded in the residual block to increase the sensitivity of the model to features. Lastly, Adan is selected as the optimizer to increase the convergence speed of IDRN. The train traction motor bearing bench built by our research team is selected for the experiment. The results show that the test accuracy of IDRN on the bearing dataset of train traction motor is 98.72%, which is at least 2.27% higher than other comparative models. The IDRN model converges with fewer iterations in the training process, shortening the entire experiment time. At the same time, the CWRU bearing dataset and the bearing dataset with natural defects are selected for comparative verification. The experimental results show that the IDRN model exhibits strong robustness and practicability on different datasets.

Accurate spatial-temporal traffic flow forecasting is essential for helping traffic managers take control measures and drivers to choose the optimal travel routes. Recently, graph convolutional networks (GCNs) have been widely used in traffic flow prediction owing to their powerful ability to capture spatial-temporal dependencies. However, designing the spatial-temporal graph adjacency matrix, which is essential to the success of GCNs remains an open question. This paper proposes a GCN-based traffic flow forecasting method that reconstructs the binary adjacency matrix via tensor decomposition. We first reformulate the spatial-temporal fusion graph adjacency matrix into a three-way adjacency tensor. Then, we use Tucker decomposition to reconstruct the adjacency tensor, encoding more informative and global spatial-temporal dependencies. Finally, we propose multiple Spatial-temporal Tensor Graph Convolution layers that assemble a Spatial-temporal Synchronous Graph Convolutional module for localized spatial-temporal correlations learning and a Dilated Convolution module for global correlations learning in parallel. This enables the comprehensive spatial-temporal dependencies of the road network to be aggregated and learned. Experimental results on four open-access datasets demonstrate that the proposed model outperforms state-of-the-art approaches in terms of prediction performances.

Transformer-oil with low thermal conductivity and large viscosity has poor heat dissipation capability, which leads to the thermal drive failure caused by transient overload. To improve its cooling capability, this paper has proposed first the method which combined the periodically direction-switching electric field and graphene nanofluid to enhance the mixed convective heat transfer properties of transformer-oil, and analyzed the effects of switching periods, nanofluid concentration, electric field strength, heat flux, and Reynolds number on mixed convection heat transfer experimentally. The results show that the heat transfer characteristic of transformer-oil is improved up to 52% by the periodically direction-switching electric field and graphene nanofluid. As the switching period decreases, the thermal performance of the suspension is enhanced more significantly. Moreover, by analyzing the heat transfer mechanism, the periodically direction-switching electric field causes the nanoparticles to move reciprocally, repeatedly impacting and breaking the boundary layer of the heat exchange surface to enhance the perturbation, thus enhancing the heat transfer effect. Meanwhile, the predicted correlation has been proposed on the basis of influence factors, which are in good agreement with the experimental data.

The train operation scheme is the basis of urban rail transport organization. During peak hours, metro operations are characterized by overcrowded and unevenly distributed passenger demand. In this paper, a short-turning strategy is proposed to optimize train operations in combination with passenger flow variations to address the problem of concentrated traffic congestion on long metro lines. Firstly, an optimization model is developed for minimizing the total passenger waiting for time cost and train operating cost, taking into account the actual passing capacity of the line and the current constraints of train operations. Simultaneously, a genetic algorithm is designed to optimize the locations of the turn-back stations and the optimal ratio of different routings during the morning peak hours. Finally, the validity of the model is verified using Nanning Metro Line 1 as a case study, and the sensitivity of positions of turn-back stations is also analyzed. The results showed that the opening of short-turning routing during peak hours is conducive to accelerating train turnover, reducing the number of vehicles employed, and balancing passenger flow. It saved passenger waiting time by 4% and reduced vehicle kilometers traveled by 7% compared with full-length routing. This strategy improves the uneven spatial load of trains during peak passenger flows and provides theoretical support and technical reference for the optimized travel commissioning of urban rail transit line networks.