Ocean Engineering最新文献_第9页

Marine steel corrosion prediction and zonation using feature extraction and machine learning in the seas around China 利用特征提取和机器学习进行中国周边海域海洋钢腐蚀预测和分区

IF 4.6 2区工程技术 Q1 ENGINEERING, CIVIL

Ocean Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.oceaneng.2024.119649

Jiazhi Yang , Dujian Zou , Ming Zhang , Zichao Que , Tiejun Liu , Ao Zhou , Ye Li

To reduce the losses caused by the marine corrosion of steel, it is important to establish a prediction model to determine the corrosion rate of steel in depth-varying aggressive marine environments. The use of statistical feature extraction methods and machine learning modeling for marine steel corrosion prediction and zoning in the seas around China is investigated. In this study, 856 samples were collected. Mean and standard deviation were selected as environmental characteristics and corrosion loss time-varying relationships were log-transformed. Subsequently, four main supervised machine learning (ML) algorithms including Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), and XGBoost were explored for predicting corrosion loss in different depth-varying marine exposure zones. The GB model showed the best prediction accuracy and generalization ability with MSE, RMSE, MAE, and R2 values of 0.08, 0.43, 0.19, and 0.92, respectively. The spatial and temporal distribution of corrosion loss and zoning map in the seas around China were obtained. According to the corrosion zoning map of the splash zone, the South China Sea has a higher degree of corrosion, particularly in its northwestern region.

为了减少钢材海洋腐蚀造成的损失，建立一个预测模型来确定钢材在深度变化的侵蚀性海洋环境中的腐蚀速率非常重要。本研究考察了统计特征提取方法和机器学习建模在中国周边海域海洋钢腐蚀预测和分区中的应用。本研究共采集了 856 个样本。选取平均值和标准差作为环境特征，并对腐蚀损失时变关系进行对数变换。随后，探讨了四种主要的监督机器学习（ML）算法，包括决策树（DT）、随机森林（RF）、梯度提升（GB）和 XGBoost，用于预测不同深度海洋暴露区的腐蚀损失。GB 模型显示出最佳的预测精度和泛化能力，其 MSE、RMSE、MAE 和 R2 值分别为 0.08、0.43、0.19 和 0.92。得到了中国周边海域腐蚀损失的时空分布和腐蚀区划图。根据飞溅区腐蚀分区图，南海的腐蚀程度较高，尤其是其西北部地区。

{"title":"Marine steel corrosion prediction and zonation using feature extraction and machine learning in the seas around China","authors":"Jiazhi Yang , Dujian Zou , Ming Zhang , Zichao Que , Tiejun Liu , Ao Zhou , Ye Li","doi":"10.1016/j.oceaneng.2024.119649","DOIUrl":"10.1016/j.oceaneng.2024.119649","url":null,"abstract":"<div><div>To reduce the losses caused by the marine corrosion of steel, it is important to establish a prediction model to determine the corrosion rate of steel in depth-varying aggressive marine environments. The use of statistical feature extraction methods and machine learning modeling for marine steel corrosion prediction and zoning in the seas around China is investigated. In this study, 856 samples were collected. Mean and standard deviation were selected as environmental characteristics and corrosion loss time-varying relationships were log-transformed. Subsequently, four main supervised machine learning (ML) algorithms including Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), and XGBoost were explored for predicting corrosion loss in different depth-varying marine exposure zones. The GB model showed the best prediction accuracy and generalization ability with MSE, RMSE, MAE, and R2 values of 0.08, 0.43, 0.19, and 0.92, respectively. The spatial and temporal distribution of corrosion loss and zoning map in the seas around China were obtained. According to the corrosion zoning map of the splash zone, the South China Sea has a higher degree of corrosion, particularly in its northwestern region.</div></div>","PeriodicalId":19403,"journal":{"name":"Ocean Engineering","volume":"314 ","pages":"Article 119649"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Survey of AI-driven routing protocols in underwater acoustic networks for enhanced communication efficiency 水下声学网络中人工智能驱动的路由协议调查，以提高通信效率

IF 4.6 2区工程技术 Q1 ENGINEERING, CIVIL

Ocean Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.oceaneng.2024.119606

Kiran Saleem , Lei Wang , Salil Bharany

The high-speed growth of undersea communication networks requires sophisticated routing protocols to deal with challenging underwater conditions including large latencies, limited bandwidths and varying topologies. In this paper, we examine the use of Artificial Intelligence (AI), Machine Learning (ML), Reinforcement Learning (RL) and fuzzy logic to optimize routing protocols for underwater networks. We provide a comprehensive survey of existing AI-based approaches, emphasizing their novelties and constraints underwater.

To assess the efficiency of these AI-based routing protocols, we carry out extensive simulations across various underwater environments where metrics such as packet delivery ratio, energy consumption, end-to-end delay, and computational efficiency are focused on. The results reveal that AI-aided protocols excel over conventional methods particularly in situations involving complex environmental dynamics as well as resources limitation.

However, there are practical implementation issues which must be solved before the real-world application of AI-based routing such as hardware constraints, concerns on energy usage , and scalability. This study provides valuable insights into the integration of AI technologies into underwater communication networks, paving the way for more reliable and efficient underwater operations. Our findings contribute to the growing body of knowledge in this field and offer a foundation for future advancements in underwater communication technologies.

海底通信网络的高速发展需要复杂的路由协议来应对具有挑战性的水下条件，包括大延迟、有限的带宽和不同的拓扑结构。在本文中，我们研究了如何利用人工智能（AI）、机器学习（ML）、强化学习（RL）和模糊逻辑来优化水下网络的路由协议。为了评估这些基于人工智能的路由协议的效率，我们在各种水下环境中进行了大量仿真，重点关注数据包交付率、能耗、端到端延迟和计算效率等指标。结果表明，人工智能辅助协议优于传统方法，尤其是在涉及复杂环境动态和资源限制的情况下。然而，在基于人工智能的路由实际应用之前，还必须解决一些实际实施问题，如硬件限制、能源使用问题和可扩展性问题。这项研究为将人工智能技术融入水下通信网络提供了宝贵的见解，为更可靠、更高效的水下作业铺平了道路。我们的研究结果为该领域不断增长的知识体系做出了贡献，并为水下通信技术的未来发展奠定了基础。

{"title":"Survey of AI-driven routing protocols in underwater acoustic networks for enhanced communication efficiency","authors":"Kiran Saleem , Lei Wang , Salil Bharany","doi":"10.1016/j.oceaneng.2024.119606","DOIUrl":"10.1016/j.oceaneng.2024.119606","url":null,"abstract":"<div><div>The high-speed growth of undersea communication networks requires sophisticated routing protocols to deal with challenging underwater conditions including large latencies, limited bandwidths and varying topologies. In this paper, we examine the use of Artificial Intelligence (AI), Machine Learning (ML), Reinforcement Learning (RL) and fuzzy logic to optimize routing protocols for underwater networks. We provide a comprehensive survey of existing AI-based approaches, emphasizing their novelties and constraints underwater.</div><div>To assess the efficiency of these AI-based routing protocols, we carry out extensive simulations across various underwater environments where metrics such as packet delivery ratio, energy consumption, end-to-end delay, and computational efficiency are focused on. The results reveal that AI-aided protocols excel over conventional methods particularly in situations involving complex environmental dynamics as well as resources limitation.</div><div>However, there are practical implementation issues which must be solved before the real-world application of AI-based routing such as hardware constraints, concerns on energy usage , and scalability. This study provides valuable insights into the integration of AI technologies into underwater communication networks, paving the way for more reliable and efficient underwater operations. Our findings contribute to the growing body of knowledge in this field and offer a foundation for future advancements in underwater communication technologies.</div></div>","PeriodicalId":19403,"journal":{"name":"Ocean Engineering","volume":"314 ","pages":"Article 119606"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data-driven model assessment: A comparative study for ship response determination 数据驱动模型评估：船舶响应测定比较研究

IF 4.6 2区工程技术 Q1 ENGINEERING, CIVIL

Ocean Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.oceaneng.2024.119711

Alessandro La Ferlita , Jens Ley , Yan Qi , Thomas E. Schellin , Emanuel Di Nardo , Ould El Moctar , Angelo Ciaramella

Several machine learning approaches to determine ship responses via data-driven models have been applied. Input features and parameters used relied on time-series analyses obtained from computational-fluid-dynamics approach. As inputs into the data-driven model, the heave and pitch motions of a ship advancing in irregular, i.e., natural seaway were considered. By using different models in the framework of machine learning, required computation for the associated ship motions may be avoided, thus reducing the computational effort to forecast ship motions. Comparative predictions with numerical simulations revealed that the deep-neural-network method for training in auto-machine-learning instructions yielded the highest accuracy in heave motion, resulting in a non-normalized mean-absolute-error of 0.74, against the corresponding error of 1.07 from numerical computations, whereas the method trained with the tree-based models (the extreme gradient boosting and the Hist gradient boosting regressor) predicted less accurate motions for the tested ship. The model trained with the random forest regressor exhibited an error of 1.10. Numerical simulation based on a field method proved to be the most suitable choice for pitch motion. Despite the few samples available to train the regressors, results demonstrated that the measured data was sufficient to assess the developed data-driven model for ship response determination.

通过数据驱动模型确定船舶响应的几种机器学习方法已经得到应用。所使用的输入特征和参数依赖于从计算流体力学方法中获得的时间序列分析。作为数据驱动模型的输入，考虑了船舶在不规则即自然航道中前进时的倾斜和俯仰运动。通过在机器学习框架内使用不同的模型，可以避免相关船舶运动所需的计算，从而减少预测船舶运动的计算量。预测结果与数值模拟结果的比较显示，在自动机器学习指令中进行训练的深度神经网络方法预测海浪运动的准确度最高，非归一化平均绝对误差为 0.74，而数值计算的相应误差为 1.07，而使用树状模型（极梯度提升和直方梯度提升回归器）训练的方法预测受测船舶运动的准确度较低。使用随机森林回归器训练的模型误差为 1.10。基于现场方法的数值模拟被证明是俯仰运动的最合适选择。尽管可用来训练回归器的样本很少，但结果表明，测量数据足以评估所开发的用于确定船舶响应的数据驱动模型。

{"title":"Data-driven model assessment: A comparative study for ship response determination","authors":"Alessandro La Ferlita , Jens Ley , Yan Qi , Thomas E. Schellin , Emanuel Di Nardo , Ould El Moctar , Angelo Ciaramella","doi":"10.1016/j.oceaneng.2024.119711","DOIUrl":"10.1016/j.oceaneng.2024.119711","url":null,"abstract":"<div><div>Several machine learning approaches to determine ship responses via data-driven models have been applied. Input features and parameters used relied on time-series analyses obtained from computational-fluid-dynamics approach. As inputs into the data-driven model, the heave and pitch motions of a ship advancing in irregular, i.e., natural seaway were considered. By using different models in the framework of machine learning, required computation for the associated ship motions may be avoided, thus reducing the computational effort to forecast ship motions. Comparative predictions with numerical simulations revealed that the deep-neural-network method for training in auto-machine-learning instructions yielded the highest accuracy in heave motion, resulting in a non-normalized mean-absolute-error of 0.74, against the corresponding error of 1.07 from numerical computations, whereas the method trained with the tree-based models (the extreme gradient boosting and the Hist gradient boosting regressor) predicted less accurate motions for the tested ship. The model trained with the random forest regressor exhibited an error of 1.10. Numerical simulation based on a field method proved to be the most suitable choice for pitch motion. Despite the few samples available to train the regressors, results demonstrated that the measured data was sufficient to assess the developed data-driven model for ship response determination.</div></div>","PeriodicalId":19403,"journal":{"name":"Ocean Engineering","volume":"314 ","pages":"Article 119711"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fatigue reliability analysis of floating offshore wind turbines under the random environmental conditions based on surrogate model 基于代用模型的随机环境条件下浮式海上风力涡轮机疲劳可靠性分析

IF 4.6 2区工程技术 Q1 ENGINEERING, CIVIL

Ocean Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.oceaneng.2024.119686

Guanhua Zhao, Sheng Dong, Yuliang Zhao

Fatigue reliability analysis is essential for ensuring the safe operation of floating offshore wind turbines (FOWTs) under random wind and wave loads. Traditionally, fatigue assessments are computationally expensive due to the need for numerous numerical simulations. To reduce computational costs, a fatigue reliability analysis method is proposed in the present study by implementing the surrogate model, C-vine copula, and Monte Carlo simulation. The multivariate distribution of environmental conditions is modeled using the C-vine copula and marginal mixed distribution models, while short-term fatigue damages are estimated by the surrogate model. Finally, Monte Carlo simulation is employed to assess the fatigue reliability. The proposed method is applied to evaluate fatigue reliability at three critical locations on a FOWT. Results show that both the back propagation neural network (BPNN) and the Kriging model can accurately predict short-term fatigue damage at various locations. However, the BPNN-based surrogate model is recommended for its lower computationally cost. Furthermore, the proposed method not only assesses the probability of fatigue failure at individual locations but also evaluates system-level fatigue reliability by accounting for correlation between fatigue damage at different locations.

疲劳可靠性分析对于确保浮式海上风力涡轮机（FOWT）在随机风浪载荷下的安全运行至关重要。传统上，由于需要进行大量的数值模拟，疲劳评估的计算成本很高。为了降低计算成本，本研究提出了一种疲劳可靠性分析方法，即采用代用模型、C-藤协约和蒙特卡罗模拟。环境条件的多变量分布采用 C-vine copula 和边际混合分布模型建模，而短期疲劳损伤则采用代用模型估算。最后，采用蒙特卡罗模拟来评估疲劳可靠性。所提出的方法被用于评估 FOWT 三个关键位置的疲劳可靠性。结果表明，反向传播神经网络（BPNN）和克里金模型都能准确预测不同位置的短期疲劳损伤。不过，基于 BPNN 的代用模型计算成本较低，因此值得推荐。此外，所提出的方法不仅能评估单个位置的疲劳失效概率，还能通过考虑不同位置疲劳损伤之间的相关性来评估系统级疲劳可靠性。

{"title":"Fatigue reliability analysis of floating offshore wind turbines under the random environmental conditions based on surrogate model","authors":"Guanhua Zhao, Sheng Dong, Yuliang Zhao","doi":"10.1016/j.oceaneng.2024.119686","DOIUrl":"10.1016/j.oceaneng.2024.119686","url":null,"abstract":"<div><div>Fatigue reliability analysis is essential for ensuring the safe operation of floating offshore wind turbines (FOWTs) under random wind and wave loads. Traditionally, fatigue assessments are computationally expensive due to the need for numerous numerical simulations. To reduce computational costs, a fatigue reliability analysis method is proposed in the present study by implementing the surrogate model, C-vine copula, and Monte Carlo simulation. The multivariate distribution of environmental conditions is modeled using the C-vine copula and marginal mixed distribution models, while short-term fatigue damages are estimated by the surrogate model. Finally, Monte Carlo simulation is employed to assess the fatigue reliability. The proposed method is applied to evaluate fatigue reliability at three critical locations on a FOWT. Results show that both the back propagation neural network (BPNN) and the Kriging model can accurately predict short-term fatigue damage at various locations. However, the BPNN-based surrogate model is recommended for its lower computationally cost. Furthermore, the proposed method not only assesses the probability of fatigue failure at individual locations but also evaluates system-level fatigue reliability by accounting for correlation between fatigue damage at different locations.</div></div>","PeriodicalId":19403,"journal":{"name":"Ocean Engineering","volume":"314 ","pages":"Article 119686"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Numerical study of the effect of vegetation submerged ratio on turbulence characteristics in sediment-laden flow 植被淹没率对含泥沙水流湍流特性影响的数值研究

IF 4.6 2区工程技术 Q1 ENGINEERING, CIVIL

Ocean Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.oceaneng.2024.119629

Xuan Zhang , Zegao Yin , Yanxu Wang , Fuxiang Zheng , Haibao Feng , Chao Zhang

This study examines the flow and suspended sediment characteristics in sediment-laden flows under various vegetation submergence ratios (SRs), focusing on the evolution trends of turbulence characteristics with different SRs. The analysis of sediment-laden flow is performed by integrating the drift flux model with a vegetation source term, while the turbulence characteristics are simulated using the

k - ω

SST-IDDES turbulence model. The findings indicated that as the vegetation SR increases, the distributions of turbulent kinetic energy (TKE) and turbulent shear stress (TSS) in vertical and horizontal planes become more intense and intricate, exhibiting more pronounced peaks. Matrix cross-correlation analysis of the vertical TKE and TSS fields reveals a strong negative correlation in most of the same region, which ascends as the SR increases. The horizontal TKE and TSS distributions on both sides show a strong negative correlation. Statistical analysis revealed that higher SRs increase vertical TKE above the canopy but suppress vertical TKE within the canopy, while the transverse TKE intensity remains symmetric but non-uniform. The intensity of TSS also escalates as the SR increases. Vertical TSS distribution exhibits extreme values at the flume bottom and near the canopy top, with near-canopy extremes consistently positioned slightly above the canopy top.

本研究考察了不同植被淹没比（SRs）条件下含泥沙水流的流动和悬浮泥沙特征，重点研究了不同 SRs 条件下湍流特征的演变趋势。对含泥沙流的分析是通过将漂移通量模型与植被源项进行整合，而湍流特性则是利用 k-ω SST-IDDES 湍流模型模拟的。研究结果表明，随着植被SR的增加，湍流动能（TKE）和湍流切应力（TSS）在垂直面和水平面上的分布变得更加强烈和复杂，表现出更明显的峰值。对垂直 TKE 和 TSS 场进行的矩阵交叉相关分析表明，在同一区域的大部分地区存在较强的负相关，随着 SR 的增大，负相关也随之增大。两侧的水平 TKE 和 TSS 分布显示出很强的负相关性。统计分析显示，较高的 SR 会增加冠层上方的垂直 TKE，但会抑制冠层内部的垂直 TKE，而横向 TKE 强度保持对称但不均匀。TSS 强度也随着 SR 的增加而增加。垂直 TSS 分布在水槽底部和冠层顶部附近呈现极值，冠层附近的极值始终略高于冠层顶部。

{"title":"Numerical study of the effect of vegetation submerged ratio on turbulence characteristics in sediment-laden flow","authors":"Xuan Zhang , Zegao Yin , Yanxu Wang , Fuxiang Zheng , Haibao Feng , Chao Zhang","doi":"10.1016/j.oceaneng.2024.119629","DOIUrl":"10.1016/j.oceaneng.2024.119629","url":null,"abstract":"<div><div>This study examines the flow and suspended sediment characteristics in sediment-laden flows under various vegetation submergence ratios (SRs), focusing on the evolution trends of turbulence characteristics with different SRs. The analysis of sediment-laden flow is performed by integrating the drift flux model with a vegetation source term, while the turbulence characteristics are simulated using the <span><math><mrow><mi>k</mi><mo>−</mo><mi>ω</mi></mrow></math></span> SST-IDDES turbulence model. The findings indicated that as the vegetation SR increases, the distributions of turbulent kinetic energy (TKE) and turbulent shear stress (TSS) in vertical and horizontal planes become more intense and intricate, exhibiting more pronounced peaks. Matrix cross-correlation analysis of the vertical TKE and TSS fields reveals a strong negative correlation in most of the same region, which ascends as the SR increases. The horizontal TKE and TSS distributions on both sides show a strong negative correlation. Statistical analysis revealed that higher SRs increase vertical TKE above the canopy but suppress vertical TKE within the canopy, while the transverse TKE intensity remains symmetric but non-uniform. The intensity of TSS also escalates as the SR increases. Vertical TSS distribution exhibits extreme values at the flume bottom and near the canopy top, with near-canopy extremes consistently positioned slightly above the canopy top.</div></div>","PeriodicalId":19403,"journal":{"name":"Ocean Engineering","volume":"314 ","pages":"Article 119629"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhanced digital twin framework for real-time prediction of fatigue damage on semi-submersible platforms under long-term multi-sea conditions 增强型数字孪生框架，用于在长期多海条件下实时预测半潜式平台的疲劳损伤

IF 4.6 2区工程技术 Q1 ENGINEERING, CIVIL

Ocean Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.oceaneng.2024.119696

Haiyang Ge , Bo Wu , Xin Li , Qiangqiang Wei , Yunlong Jiang

As the development of offshore oil and gas resources progresses into deeper waters, the impact on marine structures becomes increasingly severe, resulting in significant structural damage. This highlights the importance of health monitoring for marine structures. The emergence of digital twin technology in ocean engineering has greatly advanced the development of marine structure monitoring technologies, improving the intelligence and real-time capabilities of structural health monitoring. This paper proposes an innovative data-driven digital twin framework, applied to the real-time fatigue damage prediction of the semi-submersible platform under long-term multi-sea conditions. Notably, this study introduces a novel stress twinning method along with a high-precision post-processing module that combines field monitoring data with high-fidelity simulation model results. This integration establishes a bidirectional connection between the physical structure and its digital counterpart, enabling real-time mapping of structural hotspot stresses and more accurate fatigue damage predictions. The proposed framework was validated on the semi-submersible platform in the South China Sea, and the results proved its practicality and transformative potential in offshore structure management.

随着近海石油和天然气资源的开发进入更深的水域，对海洋结构的影响变得越来越严重，从而导致重大的结构损坏。这凸显了海洋结构健康监测的重要性。数字孪生技术在海洋工程领域的出现极大地推动了海洋结构监测技术的发展，提高了结构健康监测的智能化和实时性。本文提出了一种创新的数据驱动数字孪生框架，并将其应用于半潜式平台在长期多海条件下的实时疲劳损伤预测。值得注意的是，本研究引入了一种新颖的应力孪生方法和高精度后处理模块，将现场监测数据与高保真仿真模型结果相结合。这种整合在物理结构和数字对应结构之间建立了双向联系，从而能够实时绘制结构热点应力图，并进行更准确的疲劳损伤预测。所提出的框架在中国南海的半潜式平台上进行了验证，结果证明了其在海上结构管理方面的实用性和变革潜力。

{"title":"Enhanced digital twin framework for real-time prediction of fatigue damage on semi-submersible platforms under long-term multi-sea conditions","authors":"Haiyang Ge , Bo Wu , Xin Li , Qiangqiang Wei , Yunlong Jiang","doi":"10.1016/j.oceaneng.2024.119696","DOIUrl":"10.1016/j.oceaneng.2024.119696","url":null,"abstract":"<div><div>As the development of offshore oil and gas resources progresses into deeper waters, the impact on marine structures becomes increasingly severe, resulting in significant structural damage. This highlights the importance of health monitoring for marine structures. The emergence of digital twin technology in ocean engineering has greatly advanced the development of marine structure monitoring technologies, improving the intelligence and real-time capabilities of structural health monitoring. This paper proposes an innovative data-driven digital twin framework, applied to the real-time fatigue damage prediction of the semi-submersible platform under long-term multi-sea conditions. Notably, this study introduces a novel stress twinning method along with a high-precision post-processing module that combines field monitoring data with high-fidelity simulation model results. This integration establishes a bidirectional connection between the physical structure and its digital counterpart, enabling real-time mapping of structural hotspot stresses and more accurate fatigue damage predictions. The proposed framework was validated on the semi-submersible platform in the South China Sea, and the results proved its practicality and transformative potential in offshore structure management.</div></div>","PeriodicalId":19403,"journal":{"name":"Ocean Engineering","volume":"314 ","pages":"Article 119696"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-resolution atlas of extreme wave height and relative risk ratio for US coastal regions 美国沿海地区极端波浪高度和相对风险比高分辨率地图集

IF 4.6 2区工程技术 Q1 ENGINEERING, CIVIL

Ocean Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.oceaneng.2024.119684

Seongho Ahn , Vincent S. Neary

Interest in marine energy development has motivated numerous studies on extreme wave conditions to characterize wave loads and project risks. Metrics on extreme wave conditions, including extreme wave height, are limited in nearshore regions by insufficient spatiotemporal coverage and resolution of wave data. This study estimates 1-, 5- and 50-year return period significant wave heights, and relative-risk-ratios computed by non-dimensionalizing these extreme wave heights with their mean values, for US nearshore regions using 32-year regional SWAN wave hindcasts with spatial resolutions of 200–300 m. The model-derived extreme wave height estimates are systematically biased lower than buoy-derived estimates, but are well correlated enabling simple bias correction to buoy-observations. As wave heights at shallow nearshore sites are physically limited by depth-induced wave breaking, model-derived extreme wave height estimates are replaced with estimates using common empirical models based on breaking depth limits. The corrected high-resolution extreme wave height and relative risk ratio atlas generated herein provides important metrics that support resource characterization for the marine energy industry, including resource and site assessment, and the establishment of upper design limits for device type classification and certification to streamline product line development.

对海洋能源开发的兴趣促使人们对极端波浪条件进行了大量研究，以确定波浪载荷和项目风险的特征。在近岸区域，由于波浪数据的时空覆盖面和分辨率不足，包括极端波高在内的极端波浪条件指标受到限制。本研究利用空间分辨率为 200-300 米的 32 年区域 SWAN 波浪后报，估算了美国近岸区域 1 年、5 年和 50 年重现期的显著波高，以及通过将这些极端波高与平均值进行非维度化计算得出的相对风险比。由于近岸浅滩处的波高受到由深度引起的破浪的物理限制，因此用基于破浪深度限制的普通经验模型估算值取代了由模式得出的极端波高估算值。此处生成的校正高分辨率极端波高和相对风险比图集提供了重要的指标，可支持海洋能源行业的资源特征描述，包括资源和地点评估，以及为设备类型分类和认证建立设计上限，以简化产品线开发。

{"title":"High-resolution atlas of extreme wave height and relative risk ratio for US coastal regions","authors":"Seongho Ahn , Vincent S. Neary","doi":"10.1016/j.oceaneng.2024.119684","DOIUrl":"10.1016/j.oceaneng.2024.119684","url":null,"abstract":"<div><div>Interest in marine energy development has motivated numerous studies on extreme wave conditions to characterize wave loads and project risks. Metrics on extreme wave conditions, including extreme wave height, are limited in nearshore regions by insufficient spatiotemporal coverage and resolution of wave data. This study estimates 1-, 5- and 50-year return period significant wave heights, and relative-risk-ratios computed by non-dimensionalizing these extreme wave heights with their mean values, for US nearshore regions using 32-year regional SWAN wave hindcasts with spatial resolutions of 200–300 m. The model-derived extreme wave height estimates are systematically biased lower than buoy-derived estimates, but are well correlated enabling simple bias correction to buoy-observations. As wave heights at shallow nearshore sites are physically limited by depth-induced wave breaking, model-derived extreme wave height estimates are replaced with estimates using common empirical models based on breaking depth limits. The corrected high-resolution extreme wave height and relative risk ratio atlas generated herein provides important metrics that support resource characterization for the marine energy industry, including resource and site assessment, and the establishment of upper design limits for device type classification and certification to streamline product line development.</div></div>","PeriodicalId":19403,"journal":{"name":"Ocean Engineering","volume":"314 ","pages":"Article 119684"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Real-time prediction of full-scale ship maneuvering motions at sea under random rudder actions based on BiLSTM-SAT hybrid method 基于 BiLSTM-SAT 混合方法的随机舵动作下全船海上机动运动的实时预测

IF 4.6 2区工程技术 Q1 ENGINEERING, CIVIL

Ocean Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.oceaneng.2024.119664

Xiao Zhou , Lu Zou , Hong-Wei He , Zi-Xin Wu , Zao-Jian Zou

The prompt identification and prediction of ship maneuvering motions under random rudder actions are crucial for providing valuable navigation decisions in practical navigations. In this study, a hybrid modeling method (BiLSTM-SAT) combining bidirectional long short-term memory (Bi-LSTM) and scaled dot-product attention (SAT) mechanism is developed to adaptively capture the time-series dynamic features of the ship system with multiple degrees of freedom (DOF) and to predict the full-scale ship maneuvering motion at sea in real time. Firstly, the ability of the identified model by BiLSTM-SAT method to predict the 3-DOF nonstandard maneuvering motion of an unmanned surface vessel (USV) in model scale under random rudder actions is validated. On this basis, utilizing the ship motion data from sea trials, the developed BiLSTM-SAT method is applied to predict the time-series 5-DOF maneuvering motions for a full-scale YUKUN ship under the impacts of environmental disturbances and random rudder actions. The results demonstrate that comparing with the traditional LSTM and back propagation (BP) neural network methods, BiLSTM-SAT method can more accurately and stably predict the full-scale ship maneuvering motions in real time characterized by coupled nonlinearity and stochasticity features under variable environmental impacts and random rudder actions with satisfactory confidence level.

在实际航行中，及时识别和预测随机舵动作下的船舶操纵运动对于提供有价值的导航决策至关重要。本研究开发了一种结合双向长短时记忆（Bi-LSTM）和缩放点积注意（SAT）机制的混合建模方法（BiLSTM-SAT），以自适应地捕捉多自由度（DOF）船舶系统的时序动态特征，并实时预测全尺寸船舶在海上的机动运动。首先，验证了 BiLSTM-SAT 方法识别的模型在随机舵动作下预测模型尺度下无人水面舰艇（USV）三维多自由度非标准机动运动的能力。在此基础上，利用海试中的船舶运动数据，应用所开发的 BiLSTM-SAT 方法预测了全尺寸 YUKUN 船在环境干扰和随机舵作用影响下的 5-DOF 时间序列操纵运动。结果表明，与传统的 LSTM 和反向传播 (BP) 神经网络方法相比，BiLSTM-SAT 方法能更准确、更稳定地实时预测全尺寸舰船在多变环境影响和随机舵动作下具有非线性和随机性耦合特征的操纵运动，且置信度令人满意。

{"title":"Real-time prediction of full-scale ship maneuvering motions at sea under random rudder actions based on BiLSTM-SAT hybrid method","authors":"Xiao Zhou , Lu Zou , Hong-Wei He , Zi-Xin Wu , Zao-Jian Zou","doi":"10.1016/j.oceaneng.2024.119664","DOIUrl":"10.1016/j.oceaneng.2024.119664","url":null,"abstract":"<div><div>The prompt identification and prediction of ship maneuvering motions under random rudder actions are crucial for providing valuable navigation decisions in practical navigations. In this study, a hybrid modeling method (BiLSTM-SAT) combining bidirectional long short-term memory (Bi-LSTM) and scaled dot-product attention (SAT) mechanism is developed to adaptively capture the time-series dynamic features of the ship system with multiple degrees of freedom (DOF) and to predict the full-scale ship maneuvering motion at sea in real time. Firstly, the ability of the identified model by BiLSTM-SAT method to predict the 3-DOF nonstandard maneuvering motion of an unmanned surface vessel (USV) in model scale under random rudder actions is validated. On this basis, utilizing the ship motion data from sea trials, the developed BiLSTM-SAT method is applied to predict the time-series 5-DOF maneuvering motions for a full-scale YUKUN ship under the impacts of environmental disturbances and random rudder actions. The results demonstrate that comparing with the traditional LSTM and back propagation (BP) neural network methods, BiLSTM-SAT method can more accurately and stably predict the full-scale ship maneuvering motions in real time characterized by coupled nonlinearity and stochasticity features under variable environmental impacts and random rudder actions with satisfactory confidence level.</div></div>","PeriodicalId":19403,"journal":{"name":"Ocean Engineering","volume":"314 ","pages":"Article 119664"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Statistical analysis of extreme sea levels in the Red Sea 红海极端海平面统计分析

IF 4.6 2区工程技术 Q1 ENGINEERING, CIVIL

Ocean Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.oceaneng.2024.119689

Charls Antony , Sabique Langodan , Ibrahim Hoteit

Coastal areas frequently experience high-sea-level events that can cause property damage and loss of life. From a coastal engineering perspective, accurately estimating the probability of extreme sea levels is crucial for designing robust coastal structures. While these estimates are typically based on long-term tide-gauge observations, sea-level hindcasts are also used when available data are limited. This study obtained estimates of extreme sea-level probabilities for the Red Sea, utilizing a 30-year dataset (1993–2022) containing hourly sea level records reconstructed using a surge model (MOG2D), a global tide model (FES2014), and sea-level anomaly data from satellite altimeters. The reconstructed sea-level data were validated against measurements from six tide gauges along the eastern Red Sea and demonstrated good agreement. Spatial maps of extreme sea levels indicated values ranging from approximately 0.4 to 1.8 m. The highest estimates for the 100-year return level were found in the northern Gulf of Suez, with elevated values also observed in the northern and southern Red Sea. Furthermore, we assessed the impact of sea-level rise on extreme sea-level probabilities. Our results revealed that even small increments in the mean sea level could lead to considerable changes in extreme sea-level probabilities across most of the Red Sea. Overall, our findings are valuable for various coastal development projects along the Red Sea coast and for improving coastal vulnerability assessments.

沿海地区经常发生高海平面事件，可能造成财产损失和人员伤亡。从海岸工程的角度来看，准确估算极端海平面发生的概率对设计坚固的海岸结构至关重要。虽然这些估算通常基于长期的验潮观测数据，但在可用数据有限的情况下，也会使用海平面后报。本研究利用一个 30 年数据集（1993-2022 年）对红海的极端海平面概率进行了估算，该数据集包含利用浪涌模型（MOG2D）、全球潮汐模型（FES2014）和卫星高度计海平面异常数据重建的每小时海平面记录。重建的海平面数据与红海东部沿岸六个验潮仪的测量数据进行了验证，结果显示两者吻合良好。极端海平面的空间分布图显示了约 0.4 至 1.8 米不等的海平面值。苏伊士湾北部的百年重现海平面估计值最高，红海北部和南部也观测到了较高的海平面值。此外，我们还评估了海平面上升对极端海平面概率的影响。我们的结果表明，即使平均海平面略有上升，也会导致红海大部分地区的极端海平面概率发生相当大的变化。总之，我们的研究结果对红海沿岸的各种沿海开发项目和改进沿海脆弱性评估都很有价值。

{"title":"Statistical analysis of extreme sea levels in the Red Sea","authors":"Charls Antony , Sabique Langodan , Ibrahim Hoteit","doi":"10.1016/j.oceaneng.2024.119689","DOIUrl":"10.1016/j.oceaneng.2024.119689","url":null,"abstract":"<div><div>Coastal areas frequently experience high-sea-level events that can cause property damage and loss of life. From a coastal engineering perspective, accurately estimating the probability of extreme sea levels is crucial for designing robust coastal structures. While these estimates are typically based on long-term tide-gauge observations, sea-level hindcasts are also used when available data are limited. This study obtained estimates of extreme sea-level probabilities for the Red Sea, utilizing a 30-year dataset (1993–2022) containing hourly sea level records reconstructed using a surge model (MOG2D), a global tide model (FES2014), and sea-level anomaly data from satellite altimeters. The reconstructed sea-level data were validated against measurements from six tide gauges along the eastern Red Sea and demonstrated good agreement. Spatial maps of extreme sea levels indicated values ranging from approximately 0.4 to 1.8 m. The highest estimates for the 100-year return level were found in the northern Gulf of Suez, with elevated values also observed in the northern and southern Red Sea. Furthermore, we assessed the impact of sea-level rise on extreme sea-level probabilities. Our results revealed that even small increments in the mean sea level could lead to considerable changes in extreme sea-level probabilities across most of the Red Sea. Overall, our findings are valuable for various coastal development projects along the Red Sea coast and for improving coastal vulnerability assessments.</div></div>","PeriodicalId":19403,"journal":{"name":"Ocean Engineering","volume":"314 ","pages":"Article 119689"},"PeriodicalIF":4.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unified line-of-sight: A guidance algorithm with integral wind-up mitigation and turning assist for USVs 统一视线：为 USV 提供具有整体风力减缓和转弯辅助功能的制导算法

IF 4.6 2区工程技术 Q1 ENGINEERING, CIVIL

Ocean Engineering

Pub Date : 2024-11-05 DOI: 10.1016/j.oceaneng.2024.119615

Kantapon Tanakitkorn, Surasak Phoemsapthawee, Nonthipat Thaweewat, Sirirat Jungrungruengtaworn

Guidance algorithm is a key part in waypoint navigation for USVs. In this paper, a novel guidance algorithm named the unified line-of-sight (ULOS) is introduced. The ULOS algorithm is developed based on the concept of the integral-based LOS algorithm. However, a special technique is employed in the ULOS algorithm to address the integral wind-up issue commonly found in other integral-based LOS algorithms in the literature. In addition, a heading compensation term based on sway velocity is incorporated into the algorithm. This sway compensation term enhances the vehicle’s ability to execute sharp turns effectively. The ULOS algorithm was benchmarked against four existing guidance algorithms in various tasks through numerical simulations. The comprehensive results have revealed the superior performance of the ULOS algorithm over the other algorithms.

制导算法是 USV 航点导航的关键部分。本文介绍了一种名为统一视线（ULOS）的新型制导算法。ULOS 算法是在基于积分的 LOS 算法概念基础上开发的。不过，ULOS 算法采用了一种特殊技术，以解决文献中其他基于积分的 LOS 算法中常见的积分卷绕问题。此外，算法中还加入了基于摇摆速度的航向补偿项。该摇摆补偿项增强了车辆有效执行急转弯的能力。通过数值模拟，ULOS 算法与现有的四种制导算法在各种任务中进行了比较。综合结果显示，ULOS 算法的性能优于其他算法。

引用次数: 0