检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:叶瑞云 许多 方顺 YE Rui-yun;XU Duo;FANG Shun(Guangdong Provincial Transport Planning and Research Center,Guangzhou 51010l,China)
机构地区:[1]广东省交通运输规划研究中心,广州市510101
出 处:《公路》2023年第1期242-248,共7页Highway
摘 要:目前珠江口跨江通道已处于饱和状态,随着两岸的经济发展及未来通道的规划和建设,交通需求将持续增长,区域交通拥堵问题日益显著,因此对跨江通道的流量分布特征进行深入分析,并构建客货交通流量的预测模型。基于虎门大桥及南沙大桥路段的门架历史数据,分析跨江通道的流量时空分布特征,发现客运流量的高峰期分别为9:00~11:00、16:00~18:00及20:00~22:00,且珠江两岸周六与周日形成了周期性潮汐客流;货运流量的高峰期分别为6:00~8:00、11:00~13:00及15:00~17:00,午高峰的货运量最大,周日货运量显著低于其他时间。基于客货运流量不同的周期性分布特征,结合多种算法分别构建客货运流量预测模型,通过模型对比发现,以30 h作为预测周期的LSTM模型预测精度最高。At present, the cross river channel of the Pearl River estuary is in a saturated state.With the economic development on both sides of the river and the planning and construction of the channel in the future, the traffic demand will continue to grow, and the regional traffic congestion problem will become increasingly prominent.Therefore, the flow distribution characteristics of the cross river channel are analyzed in-depth, and the forecast model of passenger and freight traffic flow is established.Based on the historical data of the gantries of Humen Bridge and Nansha Bridge, the spatial and temporal distribution characteristics of the flow across the river channel are analyzed in the paper.It is found that the peak periods of passenger flow are 9:00~11:00, 16:00~18:00 and 20:00~22:00 respectively, and the tidal flow is formed on Saturdays and Sundays on both sides of the Pearl River, and the peak periods of freight flow are 6:00~8:00, 11:00~13:00 and 15:00~17:00 respectively.The freight volume in the afternoon peak is the largest, and the freight volume on Sunday is significantly lower than that in other times.Based on the different periodic distribution characteristics of passenger and freight traffic flow, the passenger and freight traffic flow prediction models are constructed by combining various algorithms.Through model comparison, it is found that the LSTM model with 30 hours as the prediction period has the highest prediction accuracy.
关 键 词:交通管控 流量预测 珠江口跨江通道 客货流量 LSTM
分 类 号:U491.113[交通运输工程—交通运输规划与管理]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.7