|本期目录/Table of Contents|

[1]詹世龙,曾艳,柯冉绚.基于PCA-SVR的集装箱码头设备配置[J].集美大学学报(自然科学版),2026,31(3):308-320.
　ZHAN Shilong,ZENG Yan,KE Ranxuan.Container Terminal Equipment Configuration Based on PCA-SVR[J].Journal of Jimei University,2026,31(3):308-320.
点击复制

基于PCA-SVR的集装箱码头设备配置(PDF)
分享到：

《集美大学学报（自然科学版）》[ISSN:1007-7405/CN:35-1186/N]

卷:
第31卷
期数:
2026年第3期
页码:
308-320
栏目:
船海与交通运输工程
出版日期:
2026-05-28

文章信息/Info

Title:
Container Terminal Equipment Configuration Based on PCA-SVR
作者:
詹世龙; 曾艳; 柯冉绚
（集美大学航海学院，福建 厦门 361021）
Author(s):
ZHAN Shilong; ZENG Yan; KE Ranxuan
(Navigation College of Jimei University,Xiamen 361021，China)
关键词:
支持向量回归; 主成分分析; 集装箱码头; 设备配置优化; 交叉验证; 网格搜索技术
Keywords:
support vector regression; principal component analysis; container terminal; equipment configuration optimization; cross-validation; grid search technique
分类号:
-
DOI:
-
文献标志码:
A
摘要:
提出一种基于支持向量回归（support vector regression,SVR）与主成分分析（principal component analysis，PCA）相结合的优化模型（PCA-SVR），用于优化集装箱码头设备配置，旨在提升码头装卸工作效率。收集多个集装箱码头的设备配置数据，构建并训练SVR模型，同时结合交叉验证和网格搜索技术优化模型参数。训练结果表明，使用径向基核函数的模型在优化后表现最佳。为了克服特征相关性问题，引入PCA进行降维，有效加速了模型训练过程并提高了鲁棒性。模型计算结果表明，PCA-SVR模型在识别设备配置中的冗余或不足方面具有较高的准确性，表现出更优的拟合效果。
Abstract:
This paper proposes an optimized model (PCA-SVR) that combines support vector regression (SVR) and principal component analysis (PCA) to optimize the equipment configuration of container terminals,aiming to improve the efficiency of terminal handling operations.By collecting equipment configuration data from multiple container terminals,the SVR model is constructed and trained,optimizing model parameters through cross-validation and grid search techniques.The data indicate that the model using the radial basis function (RBF) kernel exhibited the best performance after optimization.To address the issue of feature correlation,PCA was introduced for dimensionality reduction,which effectively accelerated model training and enhanced its robustness.Model results show that the PCA-SVR model has high accuracy in identifying redundancies or deficiencies in equipment configuration,demonstrating superior fitting performance.

参考文献/References:

相似文献/References:

[1]郑伟,贾翠华,韩志强.东海和黄海双斑4个地理群体的形态学变异研究[J].集美大学学报(自然科学版),2014,19(2):81.
　ZHENG Wei,JIA Cui-hua,HAN Zhi-qiang.Morphological Variation Among Four Populations of Charybdis bimaculata in the East China Sea and the Yellow Sea[J].Journal of Jimei University,2014,19(3):81.
[2]杨丽君.基于遥感影像的上海市土地覆被变化及驱动力分析[J].集美大学学报(自然科学版),2020,25(2):152.
　YANG Lijun.Analysis of Land Cover Change and Driving Forces in Shanghai Based on Remote Sensing Image[J].Journal of Jimei University,2020,25(3):152.

备注/Memo

备注/Memo:
更新日期/Last Update: 2026-06-25