摘要
三峡升船机是三峡枢纽重要通航设施之一.为确保运行效率,对三峡升船机通航船型及尺度提出了具体要求,并详细记录了升船机的运行数据.文中基于运行数据做了两项研究:①利用相关性分析图对船型要素与通航时间之间的关联关系进行挖掘分析,得出适应升船机的船型;②采用梯度提升决策树(GBDT)方法,预测不同主尺度船舶通过三峡升船机的通航时间,并与神经网络、线性回归等预测方法相比较.结果表明:梯度提升决策树的预测精度最高.
Three Gorges ship lift is one of the important navigation facilities of Three Gorges Project.In order to ensure the operation efficiency,the Three Gorges ship lift put forward specific requirements for navigable ship types and dimensions,and recorded the operation data of the ship lift in detail.Based on the operational data,the following researches were carried out:①Correlation analysis diagram was used to dig and analyze the correlation between ship form elements and navigation time,and get the ship form suitable for ship lift.②Using the gradient lifting decision tree(GBDT)method,the navigation time of ships with different main scales passing through the Three Gorges ship lift was predicted,and compared with the prediction methods such as neural network and linear regression.The results show that the gradient lifting decision tree has the highest prediction accuracy.
作者
耿飞
金雁
GENG Fei;JIN Yan(School of Transportation,Wuhan University of Technology,Wuhan 430063,China)
出处
《武汉理工大学学报(交通科学与工程版)》
2021年第3期454-458,共5页
Journal of Wuhan University of Technology(Transportation Science & Engineering)