Accurate prediction of spatial–temporal traffic flow drives innovation across various pertinent application domains, including traffic management and route planning. Graph Convolutional Neural Network (GCN) consistently assume a central role within forecasting frameworks. The effectiveness of GCN models significantly hinges on a well-constructed graph structure, whether explicitly defined or acquired through the training process. This structure establishes the mechanism through which messages are exchanged among diverse spatial locations. In the context of traffic flow data, both prior knowledge and unknown factors contribute to the graph structure. Considering both the information derived through algorithms (self-learned) and existing knowledge (predefined), which collectively shape the spatial–temporal patterns of traffic flow, we introduce a novel model named parallel self-learned and predefined joint spatial–temporal GCN (PSPJSTGCN) for traffic flow forecasting. Our model employs a gated mechanism to amalgamate predefined and self-learned graphs in parallel, enabling efficient extraction of spatial–temporal dependency information from both sources. Additionally, we leverage multiscale gated convolution to capture dynamic temporal dependencies across a wide range of receptive fields. We meticulously evaluate our proposed approach using four real-world datasets and substantiate its substantial superiority over prevailing state-of-the-art methods.

Accurate traffic prediction is crucial for effective traffic control and risk assessment. Traffic data exhibits a distinct nature, characterized by the interplay of swift, sudden short-term variations and enduring, extended long-term trends within specific regions. This intricate intermingling and interaction give rise to diverse spatial propagation patterns. Successful traffic prediction models necessitate mastering multi-scale temporal and dynamic spatial correlations, as well as their intricate interrelationships. In this study, we present a novel spatial-temporal traffic prediction framework namedInteractiveSpatial-EnhancedGraphConvolutionNetwork (ISGCN). Our key innovation lies in the introduction of a novel dynamic graph convolution module, which not only captures overarching spatial correlations but also unveils the concealed evolution of dynamic spatial correlations over time. By seamlessly integrating the graph convolutional module with temporal sample convolution and interaction blocks, we adeptly bridge multi-scale temporal correlations with the acquired dynamic spatial correlations. Additionally, we harness diverse temporal granularities data to comprehensively capture global temporal correlations. Experiments conducted on four real-world traffic datasets illustrate that ISGCN outperforms diverse types of state-of-the-art baseline models.

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.

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.

Health monitor of bogie-bearing on the train can ensure constant operation of the rail transit system. Since the metro or other rail transit have high safety requirements, it is hard to acquire numerous fault samples. Besides, diagnosing train bogie-bearings under variable working conditions is challenging due to wheel-rail coupling, speed variation, and load fluctuation. An intelligent approach for bogie-bearing fault diagnosis is proposed to deal with the above problems. A third-order tensor model is established to be suitable for variable working conditions. Furthermore, a density-based affinity propagation tensor (DAP-Tensor) clustering algorithm is presented to identify different failures with unlabeled. Train bogie and public data sets were employed to simulate three probable conditions of train operation: high-frequency impact, speed variation, and load change. Compared with existing clustering methods in three cases, the proposed DAP-Tensor performs better in identifying bearing faults under variable working conditions. Moreover, The DAP-tensor has a comparable recognition rate to some deep learning methods, which unsupervised characteristics show it has potential for applications on rail transit trains.