YXYuejuan Xu

Yuejuan Xu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yuejuan Xu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Research on Experimental and Simulated Temperature Control Performance of Power Batteries Based on Composite Phase Change Materials

    by Yanchao Dong, Xiaozhong Ma, Chao Wang, Yuejuan Xu

    The power battery is a key component of electric vehicles and its performance is greatly affected by temperature. Battery thermal management systems based on phase change materials can effectively control the battery temperature and at the same time have the advantages of simple structures, energy savings, and good temperature uniformity, and has broad development prospects. In this paper, expanded graphite–paraffin composite phase change materials were prepared, phase change material cooling experiments were carried out, and a phase change material cooling simulation model was also established using the Fluent software to study the influence of phase change material thermophysical parameters on thermal management performance. The results show that the phase change material thermal management method has excellent cooling performance. The best thermal management performance is achieved at the 3C discharge rate, with a phase change material filling thickness of 4 mm, a melting point of 40 °C above ambient temperature, and a thermal conductivity of 3 W/(m·K). When the phase change latent heat was increased from 150 J/g to 250 J/g, the liquid phase ratio decreased from 0.84 to 0.51, and the subsequent cooling performance was greatly improved, so the phase change latent heat should be increased as much as possible.


  • Open Access

    Evaluation and Optimization Model of Land Use Around Urban Rail Transit Stations Considering TOD Strategy

    by Mingxing Li, Jinbao Zhao, Wenjing Liu, Jiawei Jiang, Yuejuan Xu

    The integration of transportation systems with land use through the Transit-Oriented Development (TOD) model can effectively promote sustainable development in cities. By increasing the intensive use of land within the supply capacity of urban public transportation, this model can comprehensively improve the efficiency of urban transportation and land use, while also addressing problems such as traffic congestion and environmental pollution. To implement this model, a "Node-Place-Function" (NPF) framework is proposed based on the coordination degree between rail transit and land use in Qingdao. A comprehensive evaluation system is constructed to quantitatively assess the TOD level and comprehensive development level of land use around rail transit stations from three dimensions. By applying the NSGA-II genetic algorithm, a land use allocation optimization model is developed to maximize rail transit station accessibility, land economic benefits, and environmental comfort. The research results guide other cities in China to implement TOD in land use planning and promote coordinated development between urban rail transit and land use.


  • Open Access

    Prediction of Urban Taxi Travel Demand by Using Hybrid Dynamic Graph Convolutional Network Model

    by Jinbao Zhao, Weichao Kong, Meng Zhou, Tianwei Zhou, Yuejuan Xu, Mingxing Li

    The efficient and accurate prediction of urban travel demand, which is a hot topic in intelligent transportation research, is challenging due to its complicated spatial-temporal dependencies, dynamic nature, and uneven distribution. Most existing forecasting methods merely considered the static spatial dependencies while ignoring the influence of the diversity of dynamic demand patterns and/or uneven distribution. In this paper, we propose a traffic demand forecasting framework of a hybrid dynamic graph convolutional network (HDGCN) model to deeply capture the characteristics of urban travel demand and improve prediction accuracy. In HDGCN, traffic flow similarity graphs are designed according to the dynamic nature of travel demand, and a dynamic graph sequence is generated according to time sequence. Then, the dynamic graph convolution module and the standard graph convolution module are introduced to extract the spatial features from dynamic graphs and static graphs, respectively. Finally, the spatial features of the two components are fused and combined with the gated recurrent unit (GRU) to learn the temporal features. The efficiency and accuracy of the HDGCN model in predicting urban taxi travel demand are verified by using the taxi data from Manhattan, New York City. The modeling and comparison results demonstrate that the HDGCN model can achieve stable and effective prediction for taxi travel demand compared with the state-of-the-art baseline models. The proposed model could be used for the real-time, accurate, and efficient travel demand prediction of urban taxi and other urban transportation systems.