基于随机森林回归的船舶特涂维修的日能耗预测

doi:10.11959/j.issn.2096-0271.2024018

大数据 ›› 2024, Vol. 10 ›› Issue (1): 170-184.doi: 10.11959/j.issn.2096-0271.2024018

• 专栏：大数据领域应用 • 上一篇

基于随机森林回归的船舶特涂维修的日能耗预测

甘瑞平¹, 任新民², 姜军², 李鹏³, 周小兵¹

¹ 云南大学信息学院，云南昆明 650504
² 友联船厂（蛇口）有限公司，广东深圳 518067
³ 深圳市中科银狐机器人有限公司，广东深圳 518216

出版日期:2024-01-01 发布日期:2024-01-01
作者简介:甘瑞平（1994- ），男，云南大学信息学院硕士生，主要研究方向为工业大数据建模、自然语言处理。
任新民（1966- ），男，友联船厂（蛇口）有限公司高级工程师，主要研究方向为物联网、大数据。
姜军（1976- ），男，友联船厂（蛇口）有限公司高级工程师，主要研究方向为物联网、大数据。
李鹏（1984- ），男，就职于深圳市中科银狐机器人有限公司，主要研究方向为数据采集与分析、智能控制。
周小兵（1975- ），男，博士，云南大学信息学院教授，主要研究方向为自然语言处理、计算机应用。
基金资助:
深圳大学稳定保障计划项目(20200829114939001);深圳信息职业技术学院校级创新科研团队项目(TD2020E001);珠江三角洲水资源配置工程科研项目(CD88-QT01-2022-0068)

Prediction of daily energy consumption for ship special coating maintenance based on stochastic forest regression

Ruiping GAN¹, Xinmin REN², Jun JIANG², Peng LI³, Xiaobing ZHOU¹

¹ School of Information Science ＆Engineering, Yunnan University, Kunming 650504, China
² You Lian Dockyards (Shekou) Co., Ltd., Shenzhen 518067, China
³ Info Robot Co., Ltd., Shenzhen 518216, China

Online:2024-01-01 Published:2024-01-01
Supported by:
Shenzhen University Stability Support Plan(20200829114939001);Project of Shenzhen Institute of Information Technology School-level Innovative, Scientific Research Team(TD2020E001);The Pearl River Delta Water Resources Allocation Engineering Scientific Research Project(CD88-QT01-2022-0068)

摘要/Abstract

摘要：

特殊涂装（简称特涂）维修是修船工作的核心内容，能耗的预测是船舶智能能效优化中的一项重要任务。使用随机森林回归（RFR）模型对船舶特涂维修日能耗进行分析，去除异常值、随机化和标准化数据集，然后使用RFR模型对船舶日能耗历史数据进行训练拟和，利用带交叉验证的网格搜索优化RFR模型，使用优化后的RFR模型对船舶特涂维修日能耗数据进行分析，并与其他模型进行对比实验。结果表明，优化后的RFR模型预测效果优于多种其他模型，R<sup>2</sup>值达93.25%，均方误差明显更低。

关键词: 能耗预测, 随机森林回归, LOF算法, 船舶特涂

Abstract:

Predicting energy consumption is an important task in the intelligent energy efficiency optimization of ship maintenance, with special coating (spec coat) being the core aspect.In this experiment, the random forest regression (RFR) model was employed to analyze the daily energy consumption of ship maintenance for special coating.The dataset was preprocessed by removing outliers, randomizing and standardizing the data.Subsequently, the RFR model was trained and fitted using historical data of daily energy consumption in ship maintenance.The RFR model was optimized using grid search with cross-validation, and analysis of daily energy consumption data for ship special coating maintenance using optimized RFR model.Comparative experiments were conducted with other models.The results revealed that the optimized RFR model outperformed several other models, achieving an R-squared value of 93.25% and significantly lower mean squared error (MSE).

Key words: energy consumption prediction, random forest regression, LOF algorithm, ship special coating

中图分类号:

TP31

甘瑞平, 任新民, 姜军, 李鹏, 周小兵. 基于随机森林回归的船舶特涂维修的日能耗预测[J]. 大数据, 2024, 10(1): 170-184.

Ruiping GAN, Xinmin REN, Jun JIANG, Peng LI, Xiaobing ZHOU. Prediction of daily energy consumption for ship special coating maintenance based on stochastic forest regression[J]. Big Data Research, 2024, 10(1): 170-184.

图/表 10

图1

表1

图2

图3

图4

表2

表3

图5

图6

图7

参考文献 20

[1]	WANG K , YAN X P , YUAN Y P ,et al. Real-time optimization of ship energy efficiency based on the prediction technology of working condition[J]. Transportation Research Part D:Transport and Environment, 2016,46: 81-93.
[2]	严新平, 刘佳仑, 范爱龙 ,等. 智能船舶技术发展与趋势简述[J]. 船舶工程, 2020,42(3): 15-20.
	YAN X P , LIU J L , FAN A L ,et al. Brief introduction to the development and trend of intelligent ship technology[J]. Ship Engineering, 2020,42(3): 15-20.
[3]	王凯, 胡唯唯, 黄连忠 ,等. 船舶智能能效优化关键技术研究现状与展望[J]. 中国舰船研究, 2021,16(1): 181-192,199.
	WANG K , HU W W , HUANG L Z ,et al. Research progress and prospects of ship intelligent energy efficiency optimization key technologies[J]. Chinese Journal of Ship Research, 2021,16(1): 181-192,199.
[4]	CHAAL M . Ship operational performance modelling for voyage optimization through fuel consumption minimization[D]. Malmo:World Maritime University, 2018.
[5]	盛同范, 叶峰, 王晨昊 ,等. 船舶行业室内涂装VOCs治理和节能方案的探讨[J]. 船舶物资与市场, 2021,29(6): 53-54.
	SHENG T F , YE F , WANG C H ,et al. Discussion on VOCs treatment and energy saving scheme of indoor painting in shipbuilding industry[J]. Marine Equipment/Materials ＆ Marketing, 2021,29(6): 53-54.
[6]	杨永刚 . 分段涂装车间精益能耗管理应用研究[D]. 上海:上海交通大学, 2016.
	YANG Y G . Study on the lean energy management in the Painting ＆ Blasting workshop[D]. Shanghai:Shanghai Jiao Tong University, 2016.
[7]	陆应康 . 涂装车间能耗预测方法研究与系统实现[D]. 武汉:武汉理工大学, 2020.
	LU Y K . Research on energy consumption prediction method of painting workshop and its system realization[D]. Wuhan:Wuhan University of Technology, 2020.
[8]	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.
[9]	YAN X P , SUN X , YIN Q Z . Multiparameter sensitivity analysis of operational energy efficiency for inland river ships based on backpropagation neural network method[J]. Marine Technology Society Journal, 2015,49(1): 148-153.
[10]	PAGOROPOULOS A , M?LLER A H , MCALOONE T C . Applying multi-class support vector machines for performance assessment of shipping operations:the case of tanker vessels[J]. Ocean Engineering, 2017,140: 1-6.
[11]	BAL BE?IK?I E , ARSLAN O , TURAN O ,et al. An artificial neural network based decision support system for energy efficient ship operations[J]. Computers ＆Operations Research, 2016,66: 393-401.
[12]	WICKRAMANAYAKE S , DILUM BANDARA H M N . Fuel consumption prediction of fleet vehicles using Machine Learning:a comparative study[C]// Proceedings of the 2016 Moratuwa Engineering Research Conference. Piscataway:IEEE Press, 2016: 90-95.
[13]	YANG L Q , CHEN G , RYTTER N G M ,et al. A genetic algorithm-based grey-box model for ship fuel consumption prediction towards sustainable shipping[J]. Annals of Operations Research, 2019.
[14]	孙双林, 杨倩 . 基于最小二乘支持向量机的船舶集中空调系统能耗预测[J]. 舰船科学技术, 2020,42(2): 184-186.
	SUN S L , YANG Q . Energy consumption prediction of ship central air conditioning system based on least square support vector machine[J]. Ship Science and Technology, 2020,42(2): 184-186.
[15]	孙峰, 黄连忠, 刘伊凡 ,等. 一种应用数据挖掘技术评估柴油机性能的方法[J]. 大连海事大学学报, 2017,43(3): 83-88.
	SUN F , HUANG L Z , LIU Y F ,et al. A method of evaluating diesel engine performance by using data mining technology[J]. Journal of Dalian Maritime University, 2017,43(3): 83-88.
[16]	WANG S Z , JI B X , ZHAO J S ,et al. Predicting ship fuel consumption based on LASSO regression[J]. Transportation Research Part D:Transport and Environment, 2018,65: 817-824.
[17]	YUAN J , WEI S M . Comparison of using artificial neural network and Gaussian process in ship energy consumption evaluation[J]. DEStech Transactions on Environment,Energy and Earth Sciences, 2019.
[18]	LEIFSSON L T , S?VARSDóTTIR H , SIGURDSSON S T ,et al. Grey-box modeling of an ocean vessel for operational optimization[J]. Simulation Modelling Practice and Theory, 2008,16(8): 923-932.
[19]	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.
	YE R , XU J S . Vessel fuel consumption model based on neural network[J]. Ship Engineering, 2016,38(3): 85-88.
[20]	丁珍妮, 陈华友, 朱家明 . 三角模糊数组合预测模型及其Shapley值近似解法[J]. 统计与决策, 2019,35(24): 68-72.
	DING Z N , CHEN H Y , ZHU J M . Combined forecasting model of triangular fuzzy number and its approximate solution method of Shapley value[J]. Statistics ＆Decision, 2019,35(24): 68-72.

影响因素	舱室数量/个	施工面积/m²	工序/道	设备总数/台	总能耗/（kW·h）
萨法	22	27 600	10	40	1 200 162.8
托玛琳	18	24 801	10	52	753 397.85
坦桑石	8	11 091	10	25	255 251.77
丹娜	22	27 454	10	53	828 235.33
古姆达	15	10 753	10	37	492 620.4
西姆斯	22	27 454	10	54	1 081 057.03
黎明之光	14	10 753	10	43	648 553.79
海洋石油116	16	177 573	8	96	1 861 483.63
新道恩	14	8 851	10	30	265 683.9406
雷姆	22	27 454	10	39	908 837.6865

RFR		XGBR		SVR
参数名	参数值	参数名	参数值	参数名	参数值
n_estimators	200	n_estimators	191	C	500
max_depth	14	max_depth	9	kernel	linear
max_features	5	max_features	5	cache_size	500
random_state	50	random_state	100
		eta	0.3

模型	MSE	R²	EV	MAE
LR	0.137	85.95%	86.05%	0.283
PR	0.136	86.45%	86.98%	0.238
RFR	0.067	93.25%	93.29%	0.181
SVR	0.151	84.62%	84.71%	0.267
XGBR	0.080	91.94%	92.11%	0.192

基于随机森林回归的船舶特涂维修的日能耗预测

Prediction of daily energy consumption for ship special coating maintenance based on stochastic forest regression

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 20

相关文章 15

Metrics

推荐阅读 0

[1]	郭亮, 杨裔, 秦炳峰, 曹建文, 李敏, 袁威, 李彩虹, 王军涛. 基于大数据技术的甘肃智慧旅游系统[J]. 大数据, 2024, 10(1): 157-169.
[2]	杨彪, 熊贇, 傅玲, 徐蔚峰, 李婧. 工业数字化转型：故障诊断方法研究进展[J]. 大数据, 2024, 10(1): 110-126.
[3]	郑纬民. 构建支持大模型训练的计算机系统需要考虑的4个问题[J]. 大数据, 2024, 10(1): 1-8.
[4]	程伟, 马成, 凌捷. 大数据技术在数据安全治理中的应用[J]. 大数据, 2023, 9(6): 3-14.
[5]	叶剑, 李文. 支持互联互通的隐私计算网关设计与实现[J]. 大数据, 2023, 9(6): 28-38.
[6]	吴信东, 应泽宇, 盛绍静, 蒋婷婷, 卜晨阳, 张赞. 数据中台框架与实践[J]. 大数据, 2023, 9(6): 137-159.
[7]	曹娟, 朱勇椿, 亓鹏, 黄子尧, 杨天韵, 王政嘉, 卜语嫣. 数字内容生成、检测与取证技术综述[J]. 大数据, 2023, 9(5): 150-173.
[8]	李伟明, 李彤, 张大方, 戴隆超, 柴云鹏. 跨空间域数据管理分布式共识算法：现状、挑战和展望[J]. 大数据, 2023, 9(4): 3-15.
[9]	庄琪钰, 李彤, 卢卫, 杜小勇. Harp：面向跨空间域的分布式事务优化算法[J]. 大数据, 2023, 9(4): 16-31.
[10]	彭泰, 孙晶, 陈旭涧, 周纤, 叶宇铭, 白晓颖. 基于数据对象的跨域情报可信共享[J]. 大数据, 2023, 9(4): 44-58.
[11]	刘一达, 丁小欧, 王宏志, 杨东华. 人工参与的迭代式数据清洗方法研究[J]. 大数据, 2023, 9(4): 59-68.
[12]	安洋, 孙健玮, 李倩, 宫永顺. 基于多源异构时空数据融合的交通流量预测模型[J]. 大数据, 2023, 9(4): 69-82.
[13]	朱天晨, 赵军, 李博, 李建欣. Argus：基于多源数据驱动的工控安全态势感知系统[J]. 大数据, 2023, 9(4): 98-115.
[14]	任洪润, 朱扬勇. 基于数据市场类型的数据定价模型研究[J]. 大数据, 2023, 9(4): 116-138.
[15]	任洪润, 朱扬勇. 数据管道模型：场外流式数据市场形态探索[J]. 大数据, 2023, 9(3): 15-28.