YLYu Liu

Yu Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yu Liu has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Anomaly discrimination via spatiotemporal correlation analysis of time-varying sensor systems under sparse traffic loads

    by Lianzhen Zhang, Yu Liu, Yanliang Du, Jiyu Xin, Jianting Zhou, Kaizhong Deng, Hong Zhang

  • TPS-GNN: Predictive model for bridge health monitoring data based on temporal periodicity and global spatial distribution characteristics

    by Yu Liu, Lianzhen Zhang, Jiyu Xin, Sijie Peng

    In recent years, the investigation of spatiotemporal dynamics in bridge health monitoring data has gained substantial prominence, with spatiotemporal models becoming a focal point of research in this domain. Traditional multilayer graph neural networks (GNNs) struggle to effectively distinguish the influence of sensor data from various cross-sectional positions on target nodes due to the oversmoothing issue when capturing spatial dependencies. Similarly, recurrent neural networks exhibit limitations in managing long-term dependencies and capturing periodic patterns, reducing their efficacy in applications like bridge monitoring, where an in-depth analysis of long-term trends is essential. To address these challenges, we introduce the concept of temporal periodicity and global spatial (TPS) and propose a predictive model named TPS-GNN. This model is specifically designed to leverage the temporal periodicity of data and the global spatial distribution characteristics. For spatial features, TPS-GNN directly employs representations from different hop neighborhoods, allowing it to accurately capture the spatial dependencies of sensor data across varying hop distances. This approach effectively retains node feature information and capitalizes on both local and global information, enhancing the model’s capacity to represent complex spatial relationships. Regarding temporal features, we introduce a position-encoding scheme that integrates daily, weekly, and seasonal periodic information into the flow data. The current and historical models process continuous and periodic time series data separately, thus better capturing temporal dependencies. Experimental results on two real-world bridge health monitoring datasets demonstrate that TPS-GNN significantly outperforms existing state-of-the-art predictive models, achieving up to a 78% improvement in prediction performance. This highlights the model’s ability to accurately predict bridge health monitoring data, enhancing the precision of data forecasts and providing reliable support for bridge maintenance and management.


  • Study on Dynamic Characteristics of Sliding Bearings at Different Rotations

    by Junwei Zhang, Qijiang Yang, Liu Yu, Ming Cheng, Ling Tian, Qinyao Xu, Mengsheng Xia

    In this paper, the dynamic characteristics of the sliding bearings were studied. A 3D model of the sliding bearings was established by Solidworks software. The sliding bearings were tested using the bearing analysis module of the rotor dynamics dyfound software. In order to study the dynamic characteristics of the sliding bearing, the influence of the maximum oil film pressure, the minimum oil film pressure, the stiffness and damping of the sliding bearing under different loads and different speeds under the same load and different speeds on the sliding bearing is studied.


  • Stress–Strain Assessments for Buried Oil Pipelines Under Freeze-Thaw Cyclic Conditions

    by Zhen-Chao Teng, Xiao-Yan Liu, Yu Liu, Yu-Xiang Zhao, Kai-Qi Liu, Yun-Chao Teng

    In this study, outdoor freeze-thaw cyclic tests on the Q345 steel pipeline portion were conducted to analyze the buried oil pipeline stress evolution in a seasonally frozen soil area, namely, the Mohe–Daqing portion of China–Russia crude oil pipeline. The results obtained show that under the freeze-thaw cycle, the variation trend of soil temperature around the pipeline exhibited a hysteresis pattern, which was similar to that of atmospheric temperatures. The soil frost heaving force was shown to drop with depth, and its value at the pipe top was higher than that at the pipe bottom. With the number of freeze-thaw cycles, the frost heaving force of the soil first increased and finally stabilized, while the principal stress of the pipeline increased gradually, and its extreme value tended to be stable after 7–8 cycles, which was consistent with the “ratchet effect” theory. The above findings made it possible to elaborate on a more efficient freeze-thaw cyclic test setup for clarifying the mechanism of frozen soil/pipeline interactions.


  • Open Access

    Analysis of the Seismic Performance of a Two‐Span Specially Shaped Column Frame

    by Zhen-Chao Teng, Tian-Jia Zhao, Yu Liu

    In traditional building construction, the structural columns restrict the design of the buildings and the layout of furniture, so the use of specially shaped columns came into being. The finite element model of a reinforced concrete framework using specially shaped columns was established by using the ABAQUS software. The effects of concrete strength, reinforcement ratio, and axial compression ratio on the seismic performance of the building incorporating such columns were studied. The numerical analysis was performed for a ten‐frame structure with specially shaped columns under low reversed cyclic loading. The load‐displacement curve, peak load, ductility coefficient, energy dissipation capacity, and stiffness degradation curve of the specially shaped column frame were obtained using the ABAQUS finite element software. The following three results were obtained from the investigation: First, when the strength of concrete in the specially shaped column frame structure was increased, the peak load increased, while the ductility and energy dissipation capacity weakened, which accelerated the stiffness degradation of the structure. Second, when the reinforcement ratio was increased in the specially shaped column frame structure, the peak load increased and the ductility and energy dissipation capacity also increased, which increased the stiffness of the structure. Third, when the axial compression ratio was increased in the structure, the peak load increased, while ductility and energy dissipation capacity reduced, which accelerated the degradation of structural stiffness.