Journal of Ocean Engineering and Science最新文献

{"title":"Incremental learning LSTM for short-term roll forecasting in USVs under varying wave encounter conditions","authors":"Zihao Wang ,&nbsp;Tingjun Qu ,&nbsp;Xi Zhou ,&nbsp;Rui Song ,&nbsp;Fei Duan ,&nbsp;Zhenglin Li","doi":"10.1016/j.joes.2025.12.015","DOIUrl":"10.1016/j.joes.2025.12.015","url":null,"abstract":"<div><div>Unmanned surface vehicles (USVs) operating in open-sea environments experience significant roll motion due to wave-induced excitation. The dynamic roll response depends on various factors, including vessel speed, wave encounter angle, and sea state. This paper introduces an online learning method based on a long-short-term memory (LSTM) network that uses incremental learning for online parameter updates, enabling time-series forecasting of USV roll dynamics under varying conditions. The proposed method leverages the temporal modeling capabilities of the LSTM to capture the time dependence induced by the hydrodynamic memory effects of roll motion. Through incremental learning, the model continuously updates its network weights using new data, avoiding full retraining and enhancing computational efficiency. This study compares two online learning modes, incremental updating and retraining, for forecasting short-term roll motion under diverse operating conditions. Validation is conducted using both computational fluid dynamics (CFD) simulation data and sea trial measurements collected from a USV in the South China Sea. The evaluations focus on short-horizon roll prediction across varying sea states, wave encounter angles and encounter frequencies. Unlike offline models trained under fixed conditions, the proposed online learning framework adapts to changes in the statistical distribution. Notably, the incremental learning model achieves comparable accuracy to retraining while offering substantially higher update efficiency, especially in real sea conditions.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 563-576"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755699","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":"Trajectory planning for autonomous surface vehicles based on linear quadratic regulator and control space sampling","authors":"Fan Yang ,&nbsp;Jia-lun Liu ,&nbsp;Zi-Lu Ouyang ,&nbsp;Shi-jie Li","doi":"10.1016/j.joes.2025.12.008","DOIUrl":"10.1016/j.joes.2025.12.008","url":null,"abstract":"<div><div>In response to the limitations of traditional planning methods for Autonomous Surface Vehicles (ASVs), which heavily rely on predefined map representations and neglect kinematic feasibility, this paper proposes a novel kinematic trajectory planning method based on control space sampling for ASVs in complex environments. The proposed planning method integrates control space sampling, kinematic state space equation, and a multi-objective cost function to generate kinematically feasible trajectories while ensuring computational efficiency. By sampling the control input space and deriving state transition trajectories through system kinematics, the dependency on grid-based maps is eliminated and the characteristics of ASV motion are considered. A comprehensive cost function is designed to balance the global path length optimization with local state, control, and predicted cost minimization. Meanwhile, a grid-based redundancy pruning mechanism is proposed to reduce computational complexity. It is demonstrated in the feasibility study that the proposed planning method outperforms conventional methods by generating smoother trajectories with reduced control effort. Finally, a series of experimental tests based on a trial ship are conducted to verify the ability of the proposed method.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 445-457"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755702","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":"A virtual testbed for maritime search and rescue: Customizing YOLO for small object detection in unreal engine","authors":"Spandan Kiran Vaidya ,&nbsp;Sakthivel V ,&nbsp;Rupankar Majumdar ,&nbsp;Parit Gupta ,&nbsp;Jeevan S ,&nbsp;Prakash P ,&nbsp;Thirunavukkarasu Selvamuthukumaran","doi":"10.1016/j.joes.2025.12.018","DOIUrl":"10.1016/j.joes.2025.12.018","url":null,"abstract":"<div><div>Maritime Search and Rescue (SAR) operations face three main issues: they are time-critical, rescue boat access is often difficult, and the vastness of the ocean poses a great challenge to identifying drowning victims. Rescue operations in situations such as a shipwreck or when enthusiasts drown due to rip currents at seashores are largely unsuccessful due to an over-reliance on manual methods. The need for faster, semi-automated methods thus becomes important. This paper aims to introduce drones as agents for rapid detection and rescue in such scenarios.</div><div>This study introduces a virtual simulation testbed, created in Unreal Engine (UE) 4.2 for maritime SAR scenarios. With the integration of the Cesium plug-in, the simulation platform provides a photo-realistic representation of the Earth’s surface, making it valuable for planning search and rescue (SAR) missions. Beyond simulation, the testbed offers the potential to generate large volumes of custom synthetic data, thereby supporting future research toward safer maritime transportation.</div><div>This study introduces an object detection framework tailored for maritime SAR scenarios, employing selected models from the YOLOv11 and YOLOv12 series trained on domain-relevant classes. A systematic training approach was followed, combining dataset balancing strategies with targeted architecture modifications. These efforts led to a 38.7% improvement in the mAP₅₀ metric compared to the baseline YOLOv12s model, with the enhanced YOLOv12s achieving 94.6% mAP₅₀. Further evaluation on three edge devices demonstrated the Jetson Nano NX as the most suitable platform for deployment. Among the tested models, the enhanced YOLOv12n emerged as the optimal choice for drone-based applications, delivering 92.3% mAP₅₀ at 31.2 FPS on the Jetson Nano NX, thereby achieving an effective balance between accuracy and real-time performance.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 597-613"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755707","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":"Coupling between an SPH-based fluid solver and mooring dynamics for floating offshore devices: DualSPHysics and MoorDynPlus","authors":"I. Martínez-Estévez ,&nbsp;B. Tagliafierro ,&nbsp;J.M. Domínguez ,&nbsp;A. Marzeddu ,&nbsp;M. deCastro ,&nbsp;A.J.C. Crespo","doi":"10.1016/j.joes.2025.12.001","DOIUrl":"10.1016/j.joes.2025.12.001","url":null,"abstract":"<div><div>This paper presents a two-way coupling methodology between the robust Smoothed Particle Hydrodynamics (SPH)-based fluid solver DualSPHysics and the lumped-mass mooring dynamics solver MoorDynPlus. Such integration enables accurate and efficient simulation of the complex hydrodynamic interactions between floating structures and their mooring systems, and is well suited to address wave–structure interaction, including extreme wave conditions. Details of the mooring solver and the coupling framework formed by DualSPHysics-MoorDynPlus are presented, highlighting the proposed methodology implementation for efficient data exchange between the two solvers. The coupled model is rigorously validated against a comprehensive experimental dataset obtained from a dedicated research campaign conducted as part of the SURVIWEC project, which tested two 1:15 scale model devices – one equipped with taut moorings and the other with catenary moorings – subjected to a variety of wave conditions, including regular and focused wave trains. The presented results demonstrate that the DualSPHysics-MoorDynPlus model can accurately predict the dynamic response of the floating structures, including their motions and the associated mooring line tensions. It effectively captures non-linear hydrodynamic effects, which are crucial for assessing the survivability of offshore structures under extreme wave conditions. This work provides a valuable tool for the design and analysis of offshore renewable energy devices, as well as other marine structures operating in challenging ocean environments.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 381-405"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755743","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":"A numerical investigation on interaction effects between two underwater vehicles in close proximity","authors":"Zi-Qiang Zheng ,&nbsp;Lu Zou ,&nbsp;Xuan Wang ,&nbsp;Zao-Jian Zou","doi":"10.1016/j.joes.2025.04.002","DOIUrl":"10.1016/j.joes.2025.04.002","url":null,"abstract":"<div><div>Underwater vehicles operating in close proximity suffer from significant hydrodynamic interactions, especially when there is a prominent vehicle size disparity. To gain profound insights into the physical mechanisms of interaction effects, this paper investigates the hydrodynamic interactions between a submarine model (SUBOFF) and a much smaller Unmanned Underwater Vehicle (UUV) model using the Reynolds Averaged Navier–Stokes (RANS) method. Firstly, the resistance of SUBOFF is predicted for Verification and Validation (V&amp;V) purpose, from which satisfactory numerical accuracies are achieved. Subsequently, hydrodynamic forces and moments on the two vehicles are predicted, considering 60 layouts with different relative vehicle positions. The simulated flow fields indicate that remarkable impacts on the UUV longitudinal force are due to the distinct flow disturbances and shelter effects caused by the submarine sail. In general, the presence of submarine causes considerable flow variations, resulting in notable vertical forces and pitch moments on UUV. The results further suggest that placing the UUV above the SUBOFF middle-body in a limited region is more favorable. Finally, it is found that keeping the UUV pitch angle below 2° is helpful to avoid apparent increases in vertical force and pitch moment on UUV.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 345-361"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755741","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":"Load and response analysis of the IEA 22 MW monopile wind turbine considering marine atmospheric turbulence characteristics","authors":"Feng Guo ,&nbsp;Zhen Gao","doi":"10.1016/j.joes.2026.01.002","DOIUrl":"10.1016/j.joes.2026.01.002","url":null,"abstract":"<div><div>Since 2020, offshore wind turbine prototypes have experienced a substantial increase in size. At the same time, wind turbine design standards have not specified requirements for marine atmospheric turbulence. The impact of marine atmospheric turbulence characteristics on the load and response (LaR) of large wind turbines has not been fully studied. This paper compares and evaluates the LaR of the IEA 22 MW bottom-fixed turbine under three turbulence conditions: the marine atmospheric turbulence model by Syed and Mann, with turbulence intensity statistics from the FINO1 platform; the IEC-recommended Mann turbulence spectra with FINO1 platform turbulence intensity; and the Mann turbulence spectra with IEC class C turbulence intensity. The latter configuration is widely used by manufacturers for offshore turbines. We derive and analyze the blade-averaged and rotor-averaged wind speeds, accounting for rotational effects. We then perform statistical, fatigue, and spectral analyses at different mean wind speeds using OpenFAST with the BeamDyn module. We observe that the differences in LaR spectra are consistent with the differences in the blade-averaged and rotor-averaged wind speed spectra. For the same turbulence intensity, the Syed–Mann turbulence model leads to a significant increase in the damage-equivalent fatigue loads of the low-speed shaft below rated wind speeds, by more than 20%. The results obtained using the IEC class C standard are noticeably higher due to its conservatively higher turbulence intensity level.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 667-680"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755700","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":"Study on dynamic response characteristics of reef limestone under underwater explosion and evolutionary patterns of carbon emissions","authors":"Wei Zhao ,&nbsp;Jianping Wang ,&nbsp;Ruihong Wang ,&nbsp;Xianda Yi ,&nbsp;Jingqi Zeng ,&nbsp;Xiuping Lan","doi":"10.1016/j.joes.2025.12.006","DOIUrl":"10.1016/j.joes.2025.12.006","url":null,"abstract":"<div><div>In response to the threats posed by underwater explosions to the stability of island-reef engineering structures and coral reef ecosystems, this study investigates the dynamic response characteristics and carbon emission evolutionary patterns of reef limestone under underwater explosion loads through a multi-parameter coupling analysis method. Based on an equivalent model, 11 test cases were designed to analyze the time-history evolution characteristics of shock waves, velocity, and acceleration responses in reef limestone under varying explosion depths, explosive equivalents, water depths, and standoff distances. A comprehensive evaluation model was subsequently developed by integrating the KMO-PCA-clustering algorithm. The results demonstrate that: (1) Decrease in explosion depth, increase in standoff distance, and reduction in water depth were all found to weaken the dynamic disturbance of rock masses. Although increasing explosive equivalent enhances response intensity, the efficiency improvement demonstrates a nonlinear imbalance with carbon emissions; (2) Based on the KMO-PCA comprehensive evaluation index system, velocity was identified as the core regulatory factor of dynamic responses, with the S7 test case inducing the most severe dynamic disturbance on reef limestone; (3) Cluster analysis of carbon emissions-comprehensive scores verifies the dual benefits of blast parameter optimization in enhancing efficiency and reducing carbon emissions; (4) The carbon emission calculation formula derived from the Sadovsky formula and carbon emission accounting model provides theoretical support and practical references for blast-resistant design of island-reef protection engineering and optimization of green blasting technologies.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 406-427"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755744","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":"System-level remaining useful life prediction methodology based on the dynamic health index of multi-indicator fusion: Two cases of subsea equipment","authors":"Xiaoyan Shao ,&nbsp;Baoping Cai","doi":"10.1016/j.joes.2026.01.003","DOIUrl":"10.1016/j.joes.2026.01.003","url":null,"abstract":"<div><div>System-level remaining useful life (RUL) prediction is challenging because multisensor data fusion requires an integrated representation of multicomponent degradation, and the uncertainty of model parameters is often overlooked during prediction. To address these issues, this study proposes a system-level RUL prediction methodology based on multisensor and multi-indicator information fusion. The main contribution is the development of a dynamic and reliability-driven health index (HI) fusion framework that enables accurate and stable assessment of overall system degradation. In the HI construction process, a system reliability model is established using prior information, and sensitivity analysis is performed to derive the allocation matrix. A dynamic HI prediction model is then formulated by integrating the allocation matrix, indicator-level health states, and a historical-data-based HI degradation model. Furthermore, a dynamic Bayesian network is employed to update degradation parameters and propagate uncertainty, thereby improving prediction robustness under varying operating conditions. The effectiveness and accuracy of the proposed methodology are demonstrated through a field case of a subsea Christmas tree and an experimental case of a subsea blowout preventer system. The predicted system-level RUL and its uncertainty range provide quantitative guidance for optimizing maintenance scheduling, determining inspection intervals, and planning life-extension strategies.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 681-696"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755698","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":"Development of a novel impact test system based on electromagnetic loading technology","authors":"Ming Cai Xu ,&nbsp;Tao Wang ,&nbsp;Jin Pan ,&nbsp;Quan Liang Cao ,&nbsp;Xiao Xiang Li","doi":"10.1016/j.joes.2026.01.001","DOIUrl":"10.1016/j.joes.2026.01.001","url":null,"abstract":"<div><div>The purpose of the present paper is to propose a novel approach of impact test system based on electromagnetic loading (EML) technology, which could provide more efficient and flexible experiment method with large range of impact velocity. The numerical simulations with multi-physics field coupling models are conducted to investigate the characteristics of the designed impact test system. The influence of discharge parameters including voltages and capacitances on the current, Lorentz force (electromagnetic force) and dynamic performance of the indenter in the magnetic field are studied. The empirical formulae for predicting the impact velocity, Lorentz force, initial kinetic energy and impulse are developed by regressing the numerical results, which could be used to design impact loading cases. The designed electromagnetic loading system was adopted to conduct the impact tests of polyurethane block as buffer under different discharge energy, and the corresponding experimental results are used to verify the numerical modelling technology. The impact load with various peak various and duration to tested structure could be designed by adjusting the stiffness of buffer and discharge parameters. The EML system could provide conveniently various kinematic energies by adjusting capacitance and discharge voltage, in which the maximum impact velocity is 102 m/s at present study.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 649-666"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755706","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":"Multidimensional nonstationary Gaidai reliability assessment for UIKKU tanker operational safety, by novel 4-parameter Weibull estimator","authors":"Oleg Gaidai ,&nbsp;Shicheng He ,&nbsp;Mahmoud El-Wazery ,&nbsp;Ahmed Elkelity ,&nbsp;Alaa Elsayed ,&nbsp;Jinlu Sheng ,&nbsp;Yan Zhu","doi":"10.1016/j.joes.2025.12.009","DOIUrl":"10.1016/j.joes.2025.12.009","url":null,"abstract":"<div><div>This benchmark case study introduces recently developed state-of-the-art general purpose multi-modal nonstationary reliability assessment method for marine, offshore, and naval structures, suitable for physically measured multidimensional dynamic systems. Existing reliability methodologies predominantly focus on univariate or bivariate systems, frequently failing to adequately address the interdependencies among the key components of high dimensional systems. The principal research aim of this case study was to illustrate the technical potential and adaptability of the proposed recently developed multimodal reliability approach through its application to the onboard dynamic measurements collected during Arctic operation of Finnish UIKKU oil/chemical tanker. The hull of the UIKKU tanker encountered ice loads throughout its polar expedition, making it pertinent to evaluate potential risks of structural hull damage. The UIKKU's vessel hull was outfitted to monitor ice-induced strains and loadings in real-time at multiple crucial (hot-spot) he hull plating locations. The overall structural behavior of the vessel during intermittent collisions with surrounding ice ridges was examined by measuring longitudinal bending stresses and vertical accelerations. This case study's findings may enhance the International Association of Classification Societies (IACS) standards and standardization for commercial polar vessels. Advocated multivariate reliability concept is aimed at aiding vessel captains in case reliability factors are analyzed in real time using live streaming sensor data, according to DNV requirements.</div><div>Novelty of this case study lies in cross-validation of the proposed multidimensional reliability concept, employing comprehensive unfiltered onboard sensor-measured data as input, combined with a novel 4-parameter Weibull maximum likelihood estimator with semi-analytical model parameter solution. The proposed generic multidimensional structural reliability concept facilitates precise design prognostics for nonstationary multivariate systems, characterized by multiple failure modes and nonlinear interdependencies among critical components or dimensions of the system.</div></div>","PeriodicalId":48514,"journal":{"name":"Journal of Ocean Engineering and Science","volume":"11 2","pages":"Pages 458-468"},"PeriodicalIF":11.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147755710","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}