首页|城市互通式立体交叉设计及优化研究——以厦门市为例

城市互通式立体交叉设计及优化研究——以厦门市为例

扫码查看
城市互通立交的建立有助于减少交通拥堵,节约行车时间,保障人、车安全,它的合理、规划建立对城市交通具有重要意义.以厦门市滨海东大道为例,对城市互通式立体交叉的设计和优化进行综合研究.通过对厦门市滨海东大道的调研和分析,针对主线交通量、匝道交通量、辅路交通量以及行人和非机动车对交通的干扰和影响,提出构建对称双环变异苜蓿叶形互通立交设计和优化方案,并对该方案的交通组织优化、城市交通流组成及影响因素进行分析,最后针对交通量预测问题,提出基于长短期记忆网络(long short-term memory,LSTM)的未来年交通量预测模型,研究方案对 2030 年、2040 年和 2050 年的交通量进行预测.研究结果表明,本文所提方案能有效提高交通效率、增加交通安全、缓解拥堵,所提出的预测交通流量的方法精度较高,误差较小,相比于K 最近邻算法(K-nearest neighbor,KNN)、差分自回归移动平均算法(auto regression integreate moving average,ARIMA)、随机森林算法(random forest,RF)的精度分别提高了 15.5%、32.2%、46.3%.由此,该方法有助于对规划年互通立交交通量进行准确预测,可为城市交通规划和设计提供参考.
Design and Optimization of Urban Interchanges:A Case Study of Xiamen City
The implementation of urban interchanges plays a crucial role in reducing traffic congestion,saving travel time,and ensuring the safety of both people and vehicles.The strategic and well-planned establishment of these interchanges holds immense significance for urban transportation.Focusing on Binhai East Avenue in Xiamen and a comprehensive study on the design and optimization of urban interchanges was conducted.By examining and analyzing the avenue,a design and optimization plan was proposed to construct a symmetrical double loop variant alfalfa leaf shaped interchange.In order to address the issues caused by mainline traffic volume,ramp traffic volume,auxiliary road traffic volume,pedestrians,and non-motorized vehicles,the optimization of traffic organization,urban traffic flow composition,and influencing factors were analized,while also traffic volume prediction was addressed.A future annual traffic volume prediction model based on Long Short-Term Memory(LSTM)was proposed to forecast the traffic volume for the research plan in 2030,2040,and 2050.The research findings demonstrate that the proposed scheme effectively enhances traffic efficiency,improves safety,and alleviates congestion.Furthermore,the traffic flow prediction method exhibits high accuracy and minimal error,surpassing K-Nearest Neighbor(KNN),Auto Regression Integreate Moving Average(ARIMA),and Random Forest(RF)with accuracy improvements of 15.5%,32.2%,and 46.3%respectively.This method proves valuable for accurately predicting interchange traffic volume during the planning year,serving as a valuable reference for urban transportation planning and design.

urban transportation planninginterchange designmain line traffic volumetraffic volume predictionLSTM model

张瑞

展开 >

中交公路规划设计院有限公司市政部,北京 100010

城市交通规划 互通式立体交叉设 主线交通量 交通量预测 LSTM模型

2024

科技和产业
中国技术经济学会

科技和产业

影响因子:0.361
ISSN:1671-1807
年,卷(期):2024.24(4)
  • 20