Journal of Ocean Engineering and Science最新文献

{"title":"Enhanced prediction of plane wall jet flow features with hybrid CatBoost modelling","authors":"Mojtaba Mehraein,&nbsp;Amin Mirboluki,&nbsp;Ramtin Golnariyan,&nbsp;Seyed Hossein Mohajeri","doi":"10.1016/j.joes.2025.12.012","DOIUrl":"10.1016/j.joes.2025.12.012","url":null,"abstract":"<div><div>A wall jet is a typical flow field encountered in various engineering fields, including the deviation tunnels, the bottom outlets of dams, and wastewater treatment. Appropriate prediction of wall jet characteristics is helpful in multiple fields, such as fluid mixing optimization, flow control, and structural design. In this study, machine learning algorithms, including standalone CatBoost (CB) and four hybrid CB models including Baysian optimization algorithms (BOA-CB), Gray wolf Optimization algorithm (GWOA-CB), Coati Optimization algorithm (COA-CB), and Whale optimization algorithm (WOA-CB) are employed for the first time to predict the wall jet characteristics such as velocity profile (U), half-width(<em>Y</em>_0.5), maximum velocity (<em>U_max</em>), boundary layer thickness (<em>Y_m</em>) and skin friction (<em>C_f</em>) coefficient were predicted using the ML algorithms. Results showed that the hybrid models performed better than the standalone CB models in predicting wall jet characteristics. Among the hybrid CB models, the best results were obtained when the hyperparameters were optimized using the Coati optimization algorithm (COA-CB). In the cross-validation scenario, the mean absolute percentage (MAPE) of the COA-CB is 20% smaller than the MAPE of the GWOA-CB model. The feature importance analysis using SHAP values showed that the streamwise distance from the nozzle is the most critical parameter affecting the accuracy of the COA-CB model to predict <em>U_max, Y</em>_0.5, <em>Y_m</em>, C_f. The following essential parameters include expansion ratio, tailwater depth ratio, and Reynolds number of the jets. A comparison between the accuracy of this study and previous models showed that the accuracy of the ML models is significantly higher than that of the earlier models. In the cross-validation scenario, the MAPE of the COA-CB model for predicting maximum velocity is approximately 57% better than the top-performing model identified in prior research.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 504-523"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental motion and load comparison of rigidly and hinged connected very large floating platforms","authors":"Abel Arredondo-Galeana ,&nbsp;Yongqiang Chen ,&nbsp;Saishuai Dai ,&nbsp;Xiantao Zhang ,&nbsp;Feargal Brennan","doi":"10.1016/j.joes.2025.11.008","DOIUrl":"10.1016/j.joes.2025.11.008","url":null,"abstract":"<div><div>Very large floating structures (VLFS) could provide a new approach to floating wind foundations due to their capacity to host multiple wind turbines into a single platform. Nonetheless, further evidence of their motion and loading performance is needed. Among the existing options, very large hydroelastic platforms or hinged connected platforms with multiple pontoons can be deployed. However, a comparative experimental assessment of both type of platforms is missing in the literature. To this aim, we test the response of a laboratory scale rigidly and hinged connected VLFS subject to different regular wave conditions. The rigidly connected VLFS emulates a hydroelastic platform, whilst the hinged connected VLFS is built with two hinges. We demonstrate experimentally, an improved load alleviation of the hinged connected VLFS compared to the rigidly connected VLFS. Results are modelled numerically through a Discrete-Module-Beam (DMB) method. Our findings suggest that although both type of platforms can contribute to offshore survivability, hinged connected VLFS could have an edge due to an improved load alleviation. This work aims to contribute to the development of novel floating foundations and provides a benchmark experimental database for hydroelastic and hinged connected VLFS.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 1","pages":"Pages 222-237"},"PeriodicalIF":11.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Time-domain dynamic response analysis of progressive mooring failure for deep-sea semi-submersible platforms","authors":"Zhangxiang Guo ,&nbsp;Nan Hou ,&nbsp;Tianhong Yan ,&nbsp;Guoqiang Zhou","doi":"10.1016/j.joes.2025.11.010","DOIUrl":"10.1016/j.joes.2025.11.010","url":null,"abstract":"<div><div>Deepwater semi-submersible platforms play a pivotal role in the exploration and exploitation of marine resources. The \"Deep Sea No.1″ semi-submersible platform in the South China Sea serves as the reference case for numerical simulations. Progressive mooring failures may significantly increase the risk of subsequent damage to remaining mooring lines, making the platform's self-stabilization capacity after consecutive failures critical for operational safety. Numerical simulations investigate the response of a deepwater semi-submersible platform to progressive mooring failures under 100-year return period extreme sea states. Coupled dynamic analysis of the floater-mooring system was performed in the frequency and time domains in this numerical simulation. The analysis incorporates coupled wind-wave-current interactions to evaluate platform motions, fairlead tensions, and drift characteristics. The study examines 51 scenarios (including 3 intact cases) covering diverse sea conditions and mooring failure configurations, with comparative analysis between intact and failed conditions. Mooring lines are intentionally disconnected at specified time instants to simulate transient/steady-state platform responses and residual mooring tensions. Results demonstrate significant wave direction effects on surge/sway/yaw motions, with maximum fairlead tensions in head seas and strong drift direction-wave heading correlation. Consecutive same-location failures cause irreversible catastrophic drift with 315.5 % yaw angle increase versus single failures, degrading residual mooring capacity while increasing adjacent line tensions. Different failure sequences induce symmetrical transient drift and fairlead tension variations due to mooring system symmetry, with consistent final equilibrium positions despite divergent transient drift directions.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 1","pages":"Pages 257-277"},"PeriodicalIF":11.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data-driven predictive maintenance for two-stroke marine diesel engines using machine learning and MLOps","authors":"Torsten Kirketerp-Møller ,&nbsp;Mathias Wiggers Hyldgaard ,&nbsp;Jie Cai,&nbsp;Aurelian-Ionut Dodis,&nbsp;Niels Gorm Maly Rytter","doi":"10.1016/j.joes.2025.11.011","DOIUrl":"10.1016/j.joes.2025.11.011","url":null,"abstract":"<div><div>Digital ship operation is just around the corners with the rapid development of Artificial Intelligence (AI) and Industrial Internet of Things (IIoT) technologies. Real time condition monitoring and Predictive Maintenance (PdM) of marine diesel engines are crucial to realize the success of ship digital operations. The study investigates the PdM in two-stroke marine diesel engines using Machine Learning (ML) and Machine Learning Operations (MLOps) based on engine operational data. Practical data with labeled engine scuffing incidents are collected from a shipping company. The real scuffing incidents are predicted based on the expected operational behavior modeling method and a customized framework. Three case studies are conducted based on 2 different vessels for the purpose of model validations and further investigation. During the expected behavior modeling procedure, comparisons among different ML models accounting for various parameters (E.g., targets, operational features, moving average types and widths) are conducted and sensitivity studies are performed in order to identify the best solutions for engine PdM in shipping practice. Based on the study, the model effectiveness and efficiency are demonstrated and a limited generalization ability of the expected behavior modeling method with ML has been realized, which can facilitate the alarming and scheduling of maintenance events for vessels. The models and findings from this research work can be easily adapted for possible future use in ship operations.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 1","pages":"Pages 278-296"},"PeriodicalIF":11.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fractional attention entropy and enhanced intrinsic time-scale decomposition for robust underwater target signal detection","authors":"Zhaoxi Li ,&nbsp;Yaan Li ,&nbsp;Kai Zhang ,&nbsp;HaoYang Lan ,&nbsp;Tian Ma","doi":"10.1016/j.joes.2025.10.004","DOIUrl":"10.1016/j.joes.2025.10.004","url":null,"abstract":"<div><div>Underwater target signal detection faces great challenges due to complex ocean noise and time-varying signal characteristics. In this paper, a novel hybrid framework combining fractional attentional entropy (FAE) and enhanced intrinsic time scale decomposition (EITD) is proposed to improve the robustness of feature extraction. FAE quantifies the signal complexity through fractional-order attentional mechanism while EITD adaptively decomposes the non-stationary components. The extracted features are fed into a decision tree (DT) classifier for six types of ship target recognition, which achieves an average accuracy of 98.86 % on a real-world dataset. Comparative experiments show that the proposed method is 19.05 % superior to the traditional intrinsic time scale decomposition (ITD) and dispersion entropy (DispEn). In addition, implementation with probabilistic neural network (PNN) shows that DT achieves excellent generalization with limited training samples (98.86 % vs. 97.05 % accuracy), and this research provides a theoretical basis for underwater weak target detection.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 1","pages":"Pages 78-98"},"PeriodicalIF":11.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Undulatory vs. gliding locomotion: Effects on underwater object detection","authors":"Shixian Gong ,&nbsp;Dixia Fan ,&nbsp;Linlin Kang ,&nbsp;Weicheng Cui","doi":"10.1016/j.joes.2025.11.012","DOIUrl":"10.1016/j.joes.2025.11.012","url":null,"abstract":"<div><div>Underwater object detection based on flow sensing is crucial for bio-inspired robotics, due to its reliable performance in turbid environment. Nevertheless, how locomotion patterns affect sensing performance remains poorly understood. We employ numerical simulations to systematically compare flow sensing performance between two fundamental patterns, which are undulatory and gliding motions, through pressure signal analysis on a foil interacting with a stationary cylinder. The effects of different tail-beat frequencies and lateral distances are also considered. Key findings demonstrate that undulatory locomotion remarkably amplifies effective pressure signals, particularly at higher tail-beat frequencies, whereas gliding provides superior suppression of self-generated flow noise. Both locomotion patterns exhibit exponential signal attenuation with increasing lateral distance, though undulatory motion significantly extends the detection range. These findings propose a hybrid strategy: undulatory motion for long-range detection and gliding motion for high-precision perception. Flow analyses identify a characteristic counter-clockwise vortex structure induced by the cylinder, which directly correlates with the effective pressure signal. Spatiotemporal analysis of cylinder-induced flow perturbations demonstrates that undulatory motion substantially enhances the positive vorticity perturbations on the foil posterior, generating a more pronounced and spatially extended region of negative pressure perturbation. The study advances understanding of locomotion-modulated sensing and provides reliable guidance for bio-inspired robotic design on adaptive underwater navigation.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 1","pages":"Pages 297-307"},"PeriodicalIF":11.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance analysis of two-body wave energy converters with a bistable mechanism and a mechanical motion rectifier in irregular waves","authors":"Zihe Chen ,&nbsp;Xiantao Zhang ,&nbsp;Lei Liu","doi":"10.1016/j.joes.2025.10.006","DOIUrl":"10.1016/j.joes.2025.10.006","url":null,"abstract":"<div><div>Various bistable mechanisms have been extensively investigated in wave energy utilization. However, there is little application of their physical realization in two-body wave energy converters (WECs) suitable for offshore regions. Therefore, this work proposes a physical realization of a spring bistable mechanism (SBM). The spring bistable mechanism consists of a pair of pressure springs in series on each side and is integrated into the WEC with a power take-off (PTO) based on a mechanical motion rectifier. The system dynamic model in time domain is developed and validated by the bench test. The dynamic characteristics and performance of the integrated WEC in irregular waves are analyzed and compared for different WEC types, translational PTO damping, spring bistable stiffness and wave conditions. The passive control of the SBM is discussed to uncover the effect of the SBM on performance enhancement. The results suggest that the output power per displacement volume achieves 16.2W/m³ at the significant wave height of 0.1 m for the WaveBob type WEC, which is superior to that for the PowerBuoy type WEC. The output power is improved by a maximum ratio of 16.33 % for the WaveBob type WEC due to the large hydrostatic stiffness of the spar and adjustment of natural frequency of the torus by the SBM in inter-well state.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 1","pages":"Pages 120-140"},"PeriodicalIF":11.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on the mechanism and distribution characteristics of bubble generation in the bow of a research vessel","authors":"Peng Xu ,&nbsp;Zejun Liang ,&nbsp;Yiwei Fan ,&nbsp;Linfeng Chen ,&nbsp;Jiafeng Wu","doi":"10.1016/j.joes.2025.12.021","DOIUrl":"10.1016/j.joes.2025.12.021","url":null,"abstract":"<div><div>The flow around the ship bow involves complex three-dimensional flow separation, leading to the generation of a large number of bubbles. These bubbles have a significant impact on acoustic instrumentation, and mitigating their effects has become a key focus in the field. Central to this issue is understanding the bubble generation mechanism near the bow. This study investigates the generation of bubbles in the bow region through a combination of physical experiments and numerical simulations. Experiments were conducted in a wind-wave-current circulating flume under controlled laboratory conditions. Qualitative observations of bubble phenomena near the bow were carried out, complemented by numerical simulations to examine the statistical characteristics of bubble distribution. Two distinct types of bubble generation were identified in the experiments: air entrainment due to vortex formation and bubble clouds caused by wave breaking. The former is primarily influenced by hull geometry and the turbulence intensity of the incoming flow, whereas the latter is strongly affected by wave parameters and hull motion. Numerical simulations successfully reproduced bubble generation around the hull, revealing vortex entrainment and wave-breaking-induced bubble clouds. The bubble size–density distribution follows a power-law behavior, with the slope of the bubble density versus diameter distribution found to be -3.3.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 1","pages":"Pages 308-325"},"PeriodicalIF":11.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable machine learning approach for AUV motion prediction based on lake-test data","authors":"Tianqi Pei ,&nbsp;Caoyang Yu ,&nbsp;Jinrong Zheng ,&nbsp;He Zhang ,&nbsp;Junjun Cao ,&nbsp;Xianbo Xiang ,&nbsp;Lian Lian","doi":"10.1016/j.joes.2025.11.002","DOIUrl":"10.1016/j.joes.2025.11.002","url":null,"abstract":"<div><div>Interpretable models are essential for deploying deep-learning techniques in marine activities. However, the layered complexity of state-of-the-art deep-learning architectures hinders mechanistic insight and limits adoption. Here, we introduce a three-degree-of-freedom surrogate model that renders a multivariate long short-term memory network with multiple input and output channels (MIMO-LSTM) for autonomous underwater vehicles (AUVs) transparent and tractable. The surrogate is built on a least-squares support-vector machine selected for its superior approximation and generalization capacity. Benchmark manoeuvres show that the surrogate retains predictive fidelity up to 95.8% while accelerating inference by 98.6% relative to the parent MIMO-LSTM. Interpretable parameter-dependence plots quantify the contribution of individual variables and deliver mechanistically grounded, transparent forecasts of AUV manoeuvring dynamics.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 1","pages":"Pages 180-190"},"PeriodicalIF":11.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bayesian modeling for natural gas pipeline corrosion management","authors":"Nazila Adabavazeh ,&nbsp;Mehrdad Nikbakht ,&nbsp;Atefeh Amindoust ,&nbsp;Sayed Ali Hassanzadeh-Tabrizi","doi":"10.1016/j.joes.2025.10.003","DOIUrl":"10.1016/j.joes.2025.10.003","url":null,"abstract":"<div><div>Pipeline corrosion analysis is considered a challenging topic due to the complexity and uncertainty of the factors involved. The uncontrolled consequences of corrosion impact the \"natural ecosystem, society, and economy.\" Investigating corrosion plays a crucial role in managing incidents. This paper aims to provide an effective management tool for predicting corrosion using Bayesian modeling. This study illustrates how to integrate Bayesian modeling with \"incomplete data, scientific information in various formats, and expert knowledge,\" utilizing it effectively. Employing Netica software, a fault tree representing important elements affecting the natural gas transmission lines corrosion is converted into a cause-and-effect diagram of the Bayesian belief network. Natural gas transmission lines corrosion the model's output response is then analyzed after defining the relationships between these corrosion-affecting variables. The correlation between failures and corrosion is considered through a bivariate normal distribution as the likelihood function in the Bayesian update, and the model was validated using OpenBUGS software. In the next step, sensitivity analysis and scenario analysis were conducted in two industrial zones located in the central regions of the country. The final findings showed that the suggested model can produce accurate results for Corrosion monitoring systems in the Natural Gas Industry, providing an efficient approach to assess safety, quantitative risk analysis, and forming the basis for decisions aimed at averting pipeline episodes.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 1","pages":"Pages 99-119"},"PeriodicalIF":11.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146102816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}