摘要(Abstract)：
建立内河船舶油耗的多种预测模型,如多元线性回归、岭回归、支持向量回归等算法模型,分析船舶主机功率、扭矩、转速、航速等船舶运行参数与油耗的相关性;以某内河船舶的油耗为实例,对机器学习模型进行训练、验证和测试,通过k-折交叉验证方法对模型的准确性进行分析,采用均方根误差、平均绝对误差、决定系数等误差度量指标评价预测模型的可靠性。结果表明,多元线性回归和岭回归模型具有较好的预测性能,模型的精确度高,预测结果更接近船舶的实际油耗数据。
关键词(KeyWords)： 船舶油耗;机器学习;回归模型;模型验证
基金项目(Foundation): 国家自然科学基金项目(41761012)
作者(Author): 洪耀球
DOI: 10.13349/j.cnki.jdxbn.20210513.005
参考文献(References)：
[1] 魏茂苏，万晓跃，张曦.水上运输企业碳排放量化方法研究[J].中国船检，2016,8(5):98-101.
[2] 楼狄明，包松杰，胡志远，等.基于实船油耗与排放的拖轮航速优化[J].交通运输工程学报，2017,17(1) :93-100.
[3] 马冉祺，黄连忠，魏茂苏，等.基于实船监测数据的定航线船舶智能航速优化[J].大连海事大学学报，2018,44(1):31-35.
[4] LAZAKIS I,GKEREKOS C,THEOTOKATOS G.Investigating an SVM-driven,one-class approach to estimating ship systems condition[J].Ships and Offshore Structures,2019,14(5):432-441.
[5] WONG K I,WONG P K,CHEUNG C S,et al.Modelling of diesel engine performance using advanced machine learning methods under scarce and exponential data set[J].Applied Soft Computing,2013,13(11):4428-4441.
[6] 石新发，刘东风，周志才，等.基于PSO聚类和特征贡献度的油液监测信息特征选择方法[J].润滑与密封，2016,41(1):86-89,114.
[7] 袁智，刘敬贤，刘奕，等.基于实船数据的船舶航速与油耗优化建模[J].中国航海，2020,43(1):134-138.
[8] 叶睿，许劲松.基于人工神经网络的船舶油耗模型[J].船舶工程，2016,38(3):85-88.
[9] FAGERHOLT K,GAUSEL N T,RAKKE J G,et al.Maritime routing and speed optimization with emission control areas[J].Transportation Research:Part C:Emerging Technologies,2015,52:57-73.
[10] BOCCHETTI D,LEPORE A,PALUMBO B,et al.A statistical approach to ship fuel consumption monitoring[J].Journal of Ship Research,2015,59(3):162-171.
[11] KEE K K,LAU SIMON B Y L,YONG RENCO K H.Prediction of ship fuel consumption and speed curve by using statistical method[J].Journal of Computer Science & Computational Mathematics,2018,11(8):19-24.
[12] WANG X G,ZOU Z J,HOU X R,et al.System identification modelling of ship manoeuvering motion based on ε-support vector regression[J].Journal of Hydrodynamics,2015,27(4):502-512.
[13] JEON M,NOH Y,SHIN Y,et al.Prediction of ship fuel consumption by using an artificial neural network[J].Journal of Mechanical Science and Technology,2018,32(12):5785-5796.
[14] HASTIE T,TIBSHIRANI R,FRIEDMAN J.The elements of statistical learning:data mining,inference,and prediction[M].2nd ed.New York:Springer-Verlag,2009.
