Multi-objective Route Optimization of Wind-assisted Ships Considering Sail Angle-of-attach Control
-
摘要: 针对风力助航船舶航线优化中存在的风能利用效率量化不足、油耗预测精度受限以及多目标协同优化机制缺失等问题，提出1种融合动态风帆控制与混合驱动预测的多目标航线优化方法。通过建立基于流体力学特性的动态风帆控制策略模型，实现风帆辅助推力的空间矢量解析，该模型突破传统静态攻角设定的局限性，可即时动态调整帆角参数，使风能转化效率处于较高水平。为解决传统物理模型环境适应性差与数据驱动方法物理可解释性弱的双重局限，构建物理约束下的人工神经网络分层融合架构，通过船舶运动学方程构建特征空间基底，采用注意力机制引导的人工神经网络进行残差学习。该方法在保留能耗物理机理的同时，实现数据特征与流体力学方程的双向耦合，经北大西洋航线的验证表明，其油耗预测平均绝对百分比误差（mean absolute percentage error，MAPE）较纯物理模型降低21.9%，较纯数据驱动方法的可解释性也大大提升。在此基础上，建立包含时间成本和燃油消耗的多目标优化模型，设计基于非支配排序遗传算法（non-dominated sorting genetic algorithm，NSGA-Ⅱ）和逼近理想解排序法（technique for order preference by similarity to ideal solution，TOPSIS）的协同优化算法，其非劣解集收敛速度较标准算法得以提升。以“新伊敦”轮为对象的实证研究表明：优化后的航线在北大西洋典型航次中，风帆有效工作效率提升，相较于传统推荐航线，优化航线的单航次航行时间缩短5%左右，油耗成本和固定成本分别降低9.1%和4.95%，总成本降低超过7.2%，有效的提高了风力助航船的经济效益并较少了对环境的污染。Abstract: To address the challenges in the route optimization of wind-assisted ships, namely insufficient quantification of wind energy utilization efficiency, limited accuracy in fuel consumption prediction, and lack of multi-objective coordinated optimization mechanism, this study proposes a multi-objective route optimization method integrating dynamic sail control with hybrid propulsion prediction. A dynamic sail control strategy model based on aerodynamic characteristics is developed to achieve spatial vector analysis of auxiliary thrust from sails. This model overcomes the limitations of conventional static angle-of-attack configurations by enabling real-time dynamic adjustment of sail parameters, thereby maintaining a high level of wind energy conversion efficiency. To resolve the dual constraints of poor environmental adaptability in traditional physical models and weak physical interpretability in data-driven approaches, a physics-constrained hierarchical artificial neural network architecture is constructed. This architecture establishes feature space bases using ship kinematic equations and employs attention-guided neural networks for residual learning. The proposed method preserves the underlying physical principles of energy consumption while enabling bidirectional coupling between data features and fluid dynamics equations. Validation on North Atlantic routes demonstrates that the proposed method reduces the mean absolute percentage error (MAPE) of fuel consumption prediction by 21.9% compared to purely physical models, while offering significantly enhanced inter-pretability over purely data-driven methods. Furthermore, a multi-objective optimization model incorporating both time costs and fuel consumption is established. A coordinated optimization algorithm combining non-dominated sorting genetic algorithm (NSGA-Ⅱ) and technique for order preference by similarity to ideal solution (TOPSIS) is developed, which improves the convergence rates of the non-dominated solution sets compared to standard algorithms. An empirical study conducted on the wind-assisted vessel"NEW ADEN"demonstrates that, during typical voyages in the North Atlantic, the effective operational efficiency of the sail is improved. Compared with the traditional recommended routes, the optimized route reduces voyage time by approximately 5%, fuel consumption costs and fixed costs by 9.1% and 4.95%, respectively, and total operational costs by over 7.2%. This optimization improves the economic benefits of wind-assisted ships while effectively reducing environmental pollution.
-
图 4 不同风向角和风帆攻角下推力系数
Figure 4. Thrust coefficient under different wind angles and sail attack angles
图 5 不同风向角和风帆攻角下横向力系数
Figure 5. Lateral force coefficient under different wind angles and sail attack angles
图 6 各相对风向角最大推力系数对应的风帆攻角
Figure 6. Sail attack angle corresponding to the maximum thrust coefficient at each relative wind angle
图 7 最大推力系数对应攻角下的横向力系数
Figure 7. Lateral force coefficient under the attack angle corresponding to the maximum thrust coefficient
图 8 基于物理模型和ANN混合驱动的船舶能耗预测架构
Figure 8. Architecture of ship energy consumption prediction based on physical model and ANN hybrid drive
图 12 航线转向点产生示意图
Figure 12. Schematic diagram of the generation of route turning points
图 16 混合驱动模型计算结果同实际数据的对比
Figure 16. Comparison of hybrid drive model calculation results with actual data
图 18 航线优化结果（2023年9月13—24日）
Figure 18. Route optimization results(September 13-24, 2023)
表 1 船舶基本参数
Table 1. Basic parameters of the ship
数据类型 参数名称 参数值 船舶数据 船舶总长/m 332.95 船舶宽度/m 60 船舶水线长度/m 332.6 船舶垂线间长度/m 326.6 船舶主机功率/kw 22 500 船舶辅机功率/kw 1 440 船舶设计航速/（n mile/h） 14.1 风帆数据 帆叶高度/m 35.6 正投影面积/m2 519.94 转速/rad 1/6 风帆的弦长/m 14.6 风帆的厚度/m 2.64 
下载: 导出CSV
表 2 数据预测结果对比
Table 2. Comparison of data prediction results
模型类型 ERMSE EMAE EMAPE/% 物理模型 711.94 638.4 25.837 9 黑盒模型 92.02 58.52 4.26 混合模型 90.45 57.94 3.91
下载: 导出CSV
表 3 航线优化结果对比
Table 3. Comparison of route optimization results
参数名称 推荐航线 优化航线 启发式算法 群智能算法 航行时间/h 301.93 286.98 312.80 300.23 平均速度/(n mile/h) 12.1 12.9 12.1 12.3 航行距离/n mile 3 653.4 3 702.1 3 785.0 3 692.9 油耗成本/USD 297 853.5 270 757.8 308 582.6 284 969.9 固定成本/USD 237 040.7 225 308.6 245 579.2 235 707.5 总成本/USD 534 894.2 496 066.4 554 161.8 520 677.4 算法运行时间/s 126 11 87
下载: 导出CSV
-
[1] TSITSILONIS K M, THEOTOKATOS G. A novel systematic methodology for ship propulsion engines energy management[J]. Journal of Cleaner Production, 2018, 204: 212-236. doi: 10.1016/j.jclepro.2018.08.154 [2] International Maritime Organization. Initial IMO strategy on reduction of GHG emissions from ships[R]. London: International Maritime Organization, 2018. [3] 陈弓, 朱宇, 韩冰. 绿色航运能源技术现状及发展趋势分析[J]. 交通信息与安全. 2023, 41(2): 168-78. doi: 10.3963/j.jssn.1674-4861.2023.02.018CHEN G, ZHU Y, HAN B. A Study on the status quo and trend of green energy technology for shipping industry[J]. Journal of Transport Information and Safety, 2023;41(2): 168-78. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2023.02.018 [4] 陈鲁愚, 陈顺怀, 严新平. 大型远洋风帆助航船舶节能效率分析[J]. 船海工程, 2010, 39(6): 121-123, 128.CHEN L Y, CHEN S H, YAN X P, et al. Analysis of energy-saving efficiency of large ocean-going sailing auxiliary ships[J]. Ship and Ocean Engineering, 2010, 39(6): 121-123, 128. (in Chinese) [5] LI Y, QIAO C. A route optimization method based on simulated annealing algorithm for wind-assisted ships[C]. IOP Conference Series: Earth and Environmental Science, Guangzhou: IOP, China, 2019. [6] CORNO M, FORMENTIN S, SAVARESI S M. Data-driven online speed optimization in autonomous sailboats[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 17 (3): 762-771. http://www.onacademic.com/detail/journal_1000038735623110_153b.html [7] WANG K, XUE Y, XU H, et al. Joint energy consumption optimization method for wing-diesel engine-powered hybrid ships towards a more energy-efficient shipping[J]. Energy, 2022, 245: 123155. doi: 10.1016/j.energy.2022.123155 [8] 陈登, 张文斌, 蒋永旭, 等. 助航风帆对客滚船稳性影响分析[J]. 船海工程, 2024, 53(6): 31-35.CHEN D, ZHANG W B, JIANG Y X, et al. On the influence of booster wind-sails upon stability of the ropax ships[J]. Ship & Ocean Engineering, 2024, 53(6): 31-35. (in Chinese) [9] 黎晓武, 陈纪军, 潘子英, 等. 翼型风帆技术能效评估研究[J]. 科技创新与应用, 2025, 15(3): 124-128.LI X W, CHEN J J, PAN Z Y, et al. Energy efficiency assessment study of wing sail technology[J]. Technology Innovation and Application, 2025, 15(3): 124-128. (in Chinese) [10] 李元奎. 风力助航船舶航线优化模型及智能算法研究[D]. 大连: 大连海事大学, 2014.LI Y K. Study on route optimization model and intelligent algorithm for wind-assisted navigation ships[D]. Dalian: Dalian Maritime University, 2014. (in Chinese) [11] 常志东. 基于智能算法的风力助航船舶航线优化[J]. 舰船科学技术, 2022, 44(9): 83-86.CHANG Z D. Route optimization of wind-assisted navigation ships based on intelligent algorithms[J]. Ship Science and Technology, 2022, 44(9): 83-86. (in Chinese) [12] WANG K, GUO X, ZHAO J, et al. An integrated collaborative decision-making method for optimizing energy consumption of sail-assisted ships towards low-carbon shipping[J]. Ocean Engineering, 2022, 266: 112810. doi: 10.1016/j.oceaneng.2022.112810 [13] 王端伟. 考虑实况气象的风力助航船舶航线优化[J]. 珠江水运, 2023(1): 70-72.WANG D W. Optimization of wind-assisted ship routes considering real weather conditions[J]. Pearl River Water Transport, 2023(1): 70-72. (in Chinese) [14] MA R, WANG Z, WANG K, et al. Evaluation method for energy saving of sail-assisted ship based on wind resource analysis of typical route[J]. Journal of Marine Science and Engineering, 2023, 11(4): 789. http://www.mdpi.com/2233414 [15] 马琳, 杨平. 基于反向传播神经网络的分航段船舶油耗预测模型[J]. 中国航海, 2024, 47(4): 168-174.MA L, YANG P. Segmental prediction model of ship fuel consumption based on backpropagation neural networks[J]. Navigation of China, 2024, 47(4): 168-174. (in Chinese) [16] 索基源, 李元奎, 崔金龙, 等. 基于XGBoost算法的船舶油耗预测模型[J]. 中国航海, 2024, 47(2): 153-159.SUO J Y, LI Y K, CUI J L, et al. Ship fuel consumption prediction model based on XGBoost algorithm[J]. Navigation of China, 2024, 47(2): 153-159. (in Chinese) [17] 乔磊, 尹奇志, 姚昌宏, 等. 基于BSO-BP的船舶油耗预测模型[J]. 上海海事大学学报, 2024, 45(2): 29-34.QIAO L, YIN Q Z, YAO C H, et al. Prediction model of ship fuel consumption based on BSO-BP[J]. Journal of Shanghai Maritime University, 2024, 45(2): 29-34. (in Chinese) [18] MA Y, BI H, HU M, et al. Hard sail optimization and energy efficiency enhancement for sail-assisted vessel[J]. Ocean Engineering, 2019, 173: 687-699. http://www.onacademic.com/detail/journal_1000041592510099_4c3c.html [19] 曹雪玲, 陈爱国, 林鸿杰, 等. 风力助航船舶翼型帆的动力特性分析[J]. 广东造船, 2021, 40(2): 16-19.CAO X L, CHEN A G, LIN H J, et al. Analysis of the aerodynamic characteristics of the wing sail of wind-assisted ships[J]. Guangdong Shipbuilding, 2021, 40(2): 16-19. (in Chinese) [20] 池华方, 周健, 朱鹏莅. 风帆助航船舶能效控制系统研究[J]. 交通节能与环保, 2018, 14(5): 29-33.CHI H F, ZHOU J, ZHU P L. Study on energy efficiency control system of wind-assisted navigation ships[J]. Traffic Energy Conservation and Environmental Protection, 2018, 14 (5): 29-33. (in Chinese) [21] 马伟皓. 排放控制区约束下集装箱班轮多层次运输优化策略研究[D]. 杭州: 浙江大学, 2023.MA W H. Research on multi-level transportation optimization strategy of container liner under the constraint of emission control area[D]. Hangzhou: Zhejiang University, 2023. (in Chinese) [22] 董思邑. 风翼助航船舶的航速航线联合优化方法研究[D]. 大连: 大连海事大学, 2022.DONG S Y. Research on the joint optimization method of speed and route for wind-wing assisted navigation ships[D]. Dalian: Dalian Maritime University, 2022. (in Chinese) [23] 李明峰, 王胜正, 谢宗轩. 恶劣气象海况下船舶航线的多变量多目标优化建模[J]. 中国航海, 2020, 43(2): 14-19, 30.LI M F, WANG S Z, XIE Z X. Multivariable and multi-objective optimization modeling of ship routes under adverse meteorological sea conditions[J]. Navigation of China, 2020, 43(2): 14-19, 30. (in Chinese) [24] DEB K, PRATAP A, AGARWAL S, et al. A fast and elitist multi-objective genetic algorithm: NSGA-Ⅱ[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197. http://www.researchgate.net/profile/Pouria_Ahmadi/post/Where_can_I_get_multiobjective_optimization_test_problems_equations_used_in_NSGA-III_paper/attachment/5ae31604b53d2f63c3c872ca/AS%3A620003443372033%401524831748096/download/DEB.pdf -
点击查看大图
计量
- 文章访问数: 21
- HTML全文浏览量: 7
- PDF下载量: 1
- 被引次数: 0