晨光
暗夜
晨光
极光
Bilingual Paper Reading · 中英对照精读

船舶燃油消耗的估算与优化:综述、挑战与未来方向

准大一 · 轮机工程 × 船舶能效 × 绿色航运 —— 燃油消耗估算与优化综述精读材料
原文:arXiv:2602.21959 2026年2月25日发布 arXiv 预印本(cs.LG) 综述 × 燃油消耗 × 数据融合 × 可解释 AI 附英文摘要朗读音频

一、论文档案

英文标题Estimation and Optimization of Ship Fuel Consumption in Maritime: Review, Challenges and Future Directions
中文标题海事领域船舶燃油消耗的估算与优化:综述、挑战与未来方向
作者杜西察·马里扬, 哈姆扎·哈鲁纳·穆罕默德, 巴赫特·扎曼(机构未在素材中标注;致谢显示获挪威研究理事会 GASS 项目资助)
发布时间2026年2月25日(v1)|分类:cs.LG(机器学习)
一句话概括系统综述船舶燃油消耗(FOC)的估算与优化方法——按物理模型 / 机器学习 / 混合模型三大类梳理,首次把数据融合与可解释 AI(XAI)纳入 FOC 视角,并指出数据标准化、实时优化等关键缺口。
💡 为什么选这篇给你:① 燃油成本占船舶巡航开支约三分之二,是轮机节能与绿色航运的命门;② 综述自带体系(估算 × 优化 × XAI × 数据融合),一篇顶十篇,适合建立领域地图;③ 引言里全是硬数字(75%、40%、2030/2040/2050、two-thirds、25%、1305→115 篇),是练数字听力的好材料。

二、核心术语表(先扫一遍再读正文)

英文术语中文大白话解释
FOC (Fuel Oil Consumption)燃油消耗量船上消耗的全部燃油,包括主机、辅机与锅炉等,是船舶最大的运营成本项。
GHG (greenhouse gas)温室气体航运排放的 CO₂ 等气体,是国际减排法规紧盯的对象。
IMO (International Maritime Organization)国际海事组织联合国负责航运的专门机构,出台船舶能效与排放法规。
MEPC海洋环境保护委员会IMO 下设委员会,2025 年通过了中期减排措施。
slow steaming减速航行主动降低航速省油——因为油耗与航速的三次方成正比,减速是立竿见影的省钱手段。
weather routing气象航线优化结合海况与气象预报选择最省油/最安全的航线。
trim纵倾船舶首尾吃水差,调整纵倾可以减小阻力、降低油耗。
physics-based model基于物理的模型按推进原理、阻力公式等物理规律估算油耗。
machine-learning model机器学习模型从运行数据(AIS、传感器)中学习油耗规律。
hybrid model混合模型物理与数据结合:既有物理结构,又用数据修正,目前研究最少、潜力最大。
data fusion数据融合把 AIS、船载传感器、气象数据等多个来源合并使用,提升估算精度。
XAI (Explainable AI)可解释人工智能让模型「说人话」:解释为什么给出某个预测,增强决策信任。
PI-NN / SHAP / BNN物理信息神经网络 / SHAP / 贝叶斯神经网络三类可解释/物理感知技术:PI-NN 把物理定律嵌入网络,SHAP 解释特征贡献,BNN 给出不确定性。
batch / online algorithm批处理 / 在线算法batch 用整段历史数据离线训练;online 能处理流式数据、实时更新。
AES (all-electric ship)全电力船舶发配电全部电气化的船舶,是绿色航运的代表方向之一。
cube of speed航速的三次方油耗大致随航速的三次方增长——快一点点,油就多烧很多。

三、摘要中英对照(精读核心)

🎧 音频在文末,可先听一遍原文再读;每个英文句都配了逐句翻译。

摘要 Abstract

EN · 原文
To reduce carbon emissions and minimize shipping costs, improving the fuel efficiency of ships is crucial.
CN · 翻译
为了减少碳排放、降低航运成本,提升船舶燃油效率至关重要。
EN · 原文
Various measures are taken to reduce the total fuel consumption of ships, including optimizing vessel parameters and selecting routes with the lowest fuel consumption.
CN · 翻译
人们采取多种措施降低船舶总油耗,包括优化船舶参数选择油耗最低的航线
EN · 原文
Different estimation methods are proposed for predicting fuel consumption, while various optimization methods are proposed to minimize fuel oil consumption.
CN · 翻译
针对油耗预测有各种估算方法,针对油耗最小化则有各种优化方法
EN · 原文
This paper provides a comprehensive review of methods for estimating and optimizing fuel oil consumption in maritime transport.
CN · 翻译
本文对海事运输中燃油消耗估算与优化方法做了全面综述。
EN · 原文
Our novel contributions include categorizing fuel oil consumption \& estimation methods into physics-based, machine-learning, and hybrid models, exploring their strengths and limitations.
CN · 翻译
我们的新贡献包括:把燃油消耗与估算方法分为基于物理、机器学习、混合模型三大类,并探讨各自的优势与局限。(素材原文 "fuel oil consumption \& estimation" 为导出格式,\& 即 &)
EN · 原文
Furthermore, we highlight the importance of data fusion techniques, which combine AIS, onboard sensors, and meteorological data to enhance accuracy.
CN · 翻译
此外,我们强调数据融合技术的重要性——融合 AIS、船载传感器与气象数据可提升精度。
EN · 原文
We make the first attempt to discuss the emerging role of Explainable AI in enhancing model transparency for decision-making.
CN · 翻译
我们首次尝试讨论可解释人工智能(XAI)在增强决策模型透明度方面的新兴作用。
EN · 原文
Uniquely, key challenges, including data quality, availability, and the need for real-time optimization, are identified, and future research directions are proposed to address these gaps, with a focus on hybrid models, real-time optimization, and the standardization of datasets.
CN · 翻译
本文独到地指出了数据质量、数据可得性、实时优化需求等关键挑战,并针对这些缺口提出未来研究方向——重点是混合模型、实时优化与数据集标准化

核心词(编者提炼):Fuel Oil Consumption 燃油消耗 | Estimation & Optimization 估算与优化 | Data Fusion 数据融合 | Explainable AI 可解释 AI | Green Shipping 绿色航运

四、引言精选(为什么这个问题重要)

① 全球 75% 以上的货物走海路,航运减排是硬任务

EN · 原文
Maritime commercial transport is crucial for global supply chains and international commerce, with over 75% of goods transported by sea routes FERRARI2023100985. However, maritime transport significantly contributes to greenhouse gas (GHG) emissions, leading to pollution and global warming. Therefore, authorities have been making constant efforts to make maritime transport efficient, and strategies are being devised to control greenhouse gas emissions. For example, the International Maritime Organization (IMO) is playing its role by introducing regulations on ship energy efficiency and GHG emissions. According to the 2023 IMO GHG strategy mepc20232023, followed by the adoption of mid-term measures at the MEPC in 2025, carbon emissions per vessel transport work are aimed to be reduced by at least 40% by 2030 compared to 2008. The strategy also aims to reach net-zero GHG emissions by or around 2050, with a mid-term target of at least 70% reduction by 2040.
CN · 翻译
海运对全球供应链与国际商业至关重要,超过 75% 的货物经由海路运输。然而海运也显著贡献温室气体(GHG)排放,造成污染与全球变暖。因此,各方持续努力提升海运效率、制定控排策略。例如,国际海事组织(IMO)通过引入船舶能效与 GHG 排放法规发挥作用。依据 2023 年 IMO GHG 战略(随后 MEPC 于 2025 年通过中期措施),每单位运输功的碳排放到 2030 年须较 2008 年至少降低 40%;战略还提出到 2050 年左右实现 GHG 净零排放,中期目标为到 2040 年至少减排 70%(素材原文 FERRARI2023100985、mepc20232023 等为引用键,原样保留)

② 燃油是最大成本:巡航开支的三分之二

EN · 原文
The primary cost in maritime transport is fuel, with fuel oil consumption (FOC), including all fuel oil consumed on board, accounting for approximately two-thirds of the cruising expenses of a vessel and more than 25% of the total operating expenses of a ship gkerekos2019machine. Thus, reducing FOC would result in reducing GHG emissions and reducing costs. A reduction in FOC can be achieved through multiple methods, including optimizing speed and trim, route optimization, or weather routing. To this end, this Review Article deals with the FOC estimation and FOC optimization techniques.
CN · 翻译
海事运输的首要成本是燃油:燃油消耗量(FOC,含船上全部燃油消耗)约占船舶巡航开支的三分之二、占船舶总运营开支的 25% 以上。因此,降低 FOC 既能减排也能省钱。降耗手段多样,包括优化航速与纵倾、航线优化、气象航线等。为此,本综述聚焦 FOC 估算与 FOC 优化技术。

③ 文献缺口一:混合模型与实时优化研究不足

EN · 原文
Despite the significant advancements in ship fuel consumption estimation and optimization, several gaps remain in the current literature. Existing review papers primarily focus on individual estimation models or optimization techniques, often neglecting the integration of multiple approaches mylonopoulos2023comprehensive. While previous studies discuss data-driven and physics-based models separately, there is a limited amount of research on hybrid methodologies that effectively combine both paradigms. Moreover, real-time optimization strategies remain underexplored, which are crucial for operational decision-making in dynamic maritime environments yan2021data.
CN · 翻译
尽管船舶油耗估算与优化已取得显著进展,文献仍存在若干缺口:现有综述主要聚焦单一的估算模型或优化技术,往往忽视多种方法的集成;以往研究把数据驱动与基于物理的模型分开讨论,而有效结合两种范式的混合方法研究有限;此外,对动态海事环境中的运营决策至关重要的实时优化策略仍未充分探索

④ 文献缺口二:数据集不标准、XAI 应用不足

EN · 原文
Another critical gap is the lack of standardized datasets for fuel consumption estimation models. The maritime industry relies on diverse data sources, such as Automatic Identification System (AIS) data, onboard sensor readings, and meteorological records li2024dapnet. However, the fusion of these data sources for improved estimation accuracy has not been thoroughly investigated zhu2021modeling. Additionally, while Explainable AI (XAI) techniques are gaining traction in various domains, their application in maritime fuel consumption remains limited, making it difficult for stakeholders to trust AI-driven decision-making processes wang2023innovative ma2023interpretable.
CN · 翻译
另一关键缺口是缺少标准化的油耗估算数据集。海事行业依赖多种数据源,如 AIS 数据、船载传感器读数与气象记录;然而,为提升估算精度而融合这些数据源的研究尚未被深入探讨。此外,可解释 AI(XAI)技术虽在其他领域日渐兴起,在海事油耗中的应用仍然有限,导致利益相关方难以信任 AI 驱动的决策过程。
💡 这是全文最有味道的一句“as fuel consumption rises with the cube of speed, to reduce costs, ship operators often choose slow steaming.”——油耗与航速的三次方成正比:快一点点,油就多烧很多。所以「减速航行」是立竿见影的省钱手段——这是轮机人必须建立的物理直觉。

五、论文贡献(4 个要点)

EN · 原文
1. Data sources and data fusion. Different data sources relevant to the estimation of FOC are reviewed and discussed in detail. Moreover, a unique aspect of the present review is that the fusion of different data sources for FOC is reviewed and discussed. The paper presents a detailed discussion of the data fusion techniques and a table related to data fusion.
CN · 翻译
1. 数据源与数据融合。详细梳理与 FOC 估算相关的各类数据源;本综述的独特之处在于系统评述了多数据源融合,并给出数据融合技术详述与对照表。
EN · 原文
2. Batch/online perspective. The nature of the FOC estimation algorithms (batch/online) in the form of the capability to process streaming data is reviewed.
CN · 翻译
2. 批处理 / 在线视角。按「能否处理流式数据」审视 FOC 估算算法属于批处理还是在线类型——为实时应用画了张能力地图。
EN · 原文
3. Optimization taxonomy. Optimization algorithms for FOC of ships are categorized into several types based on various criteria.
CN · 翻译
3. 优化算法分类。按多种准则把船舶 FOC 优化算法归类为若干类型,方便读者按需选型。
EN · 原文
4. Explainable AI. Explainable AI techniques are reviewed in the context of maritime fuel consumption.
CN · 翻译
4. 可解释 AI。在海事燃油消耗语境下评述 XAI 技术——首次把「模型透明度」纳入 FOC 综述框架。

六、结论中英对照

EN · 原文
We have reviewed the FOC estimation and optimization models available in the literature. We have also discussed the challenges of FOC estimation and optimization. Moreover, the common limitations of the available works on FOC estimation and optimization are also discussed in detail. Additionally, future directions for research on fuel oil consumption estimation and optimization are outlined. There has also been a shift from conventional shipping to alternative technologies, such as green shipping. The goal is to develop green technologies for shipping that reduce emissions and lower costs. For example, multi-energy hybrid propulsion systems are emerging as a vital innovation for the future of maritime transport as discussed in guo2024energy. In an all-electric ship (AES), considering uncertainties in the navigation environment and load demand, a joint optimization for power generation and voyage scheduling is formulated and solved, to minimize operating and battery loss costs, using reinforcement learning in shang2024dynamic.
CN · 翻译
我们综述了文献中可用的 FOC 估算与优化模型,讨论了其中的挑战与常见局限,并勾勒了未来研究方向。行业正从传统航运转向绿色航运等替代技术,目标是开发既能减排又能降本的绿色技术:例如多能源混合推进系统正成为未来海事运输的关键创新;在全电力船舶(AES)中,考虑航行环境与负荷需求的不确定性,研究者用强化学习对发电与航次调度做联合优化,以最小化运行与电池损耗成本。
EN · 原文
Furthermore, there are economic aspects related to fuel consumption, such as high bunker prices or crises in the maritime market, e.g., demand drop or fleet oversupply. In these cases, as fuel consumption rises with the cube of speed, to reduce costs, ship operators often choose slow steaming. i.e., voluntary speed reduction by ships as an effective measure to reduce fuel consumption and operational costs.
CN · 翻译
此外还有与油耗相关的经济因素,如高油价或航运市场危机(需求下降、运力过剩)。在这些情况下,由于油耗随航速的三次方上升,船东常选择减速航行(slow steaming)——即船舶主动降速,作为降低油耗与运营成本的有效措施。
EN · 原文
Future Directions: An important research direction in the FOC estimation is the fusion of different data sources. Although some approaches to data fusion are available, there is still a need to expand the list of state-of-the-art techniques for data fusion. Hybrid models for FOC estimation have not been well explored in the literature. For example, modifying the loss function to incorporate information about the ship's underlying features could be investigated. Online algorithms for estimating the FOC of ships may also be explored further. For instance, the FOC estimation algorithm can detect the mode of the ship and apply the corresponding model in real time according to the ship's activity. Future research should explore hybrid XAI approaches on how PI-NN, SHAP, and BNN can be combined to improve both interpretability and accuracy in FOC estimation.
CN · 翻译
未来方向:FOC 估算的重要方向是多数据源融合(还需扩充最先进融合技术);混合模型尚未被充分探索(例如可研究修改损失函数以融入船舶底层特征信息);在线算法值得深入(如让估算算法识别船舶运行模式、按活动实时切换对应模型);还应探索混合 XAI 方法——把 PI-NN、SHAP 与 BNN 结合起来,同时提升 FOC 估算的可解释性与精度。

七、编者解读:这篇论文到底讲了什么(大白话版)

  1. 问题:航运是减排重点(全球 75% 以上货物走海路),燃油又是船上最大开销(巡航开支约三分之二)——省油 = 省钱 = 减排,一举两得,但方法五花八门、没人系统梳理过。
  2. 现状梳理:估算油耗的方法分三类——物理模型(按推进原理算)、机器学习(从数据学)、混合模型(两者结合,目前研究最少);优化手段有航速优化、纵倾优化、航线优化、气象航线等。
  3. 这篇的增量:首次把「数据融合(AIS + 船载传感器 + 气象)」和「可解释 AI」放进 FOC 综述框架;还画了一张对比表(Table 1),把自己和 5 篇既有综述逐项 PK。
  4. 痛点:数据不标准、没有公开基准数据集、实时优化研究少、混合模型未充分探索——导致不同论文结果没法公平对比,模型换个船型就失灵。
  5. 最值钱的提醒:油耗与航速的三次方成正比——减速航行(slow steaming)是立竿见影的措施;未来方向指向混合模型、实时优化、数据集标准化、XAI 实时监控。
🎯 对保研的启示:综述论文的价值在于「分类框架 + 缺口清单」。学会像作者那样用一张表把自己的贡献和已有工作逐项对比(✓/×),这是文献综述类工作的核心方法论——开题报告和复试 PPT 都用得上。

八、给准大一的阅读路线图 & 延伸方向

📖 怎么读这篇论文(三遍法)

  1. 第一遍(10 分钟):只读摘要和术语表,回答三个问题——综述覆盖了什么?分类框架是什么?指出了哪些缺口?
  2. 第二遍(20 分钟):读引言 + 结论,重点体会「为什么混合模型、实时优化、数据标准化是未来」以及 IMO 减排时间表(2030/2040/2050)。
  3. 第三遍(30 分钟):读 1.1 节贡献清单和结论的未来方向列表,跳过所有公式与文献编号,只抓「三类估算模型、几类优化方法、数据融合怎么做、XAI 解决什么」。

🚀 这个方向你能延伸做什么

九、英文摘要朗读(练听力用)

先盲听一遍→再看对照稿→再听一遍。目标是听出每个数字(75%、40%、2030、2040、2050、two-thirds、25%)和术语(FOC、GHG、AIS、physics-based、machine-learning、hybrid、Explainable AI、data fusion)。