International Journal of Naval Architecture and Ocean Engineering最新文献

{"title":"A U-net based reconstruction of high-fidelity simulation results for flow around a ship hull based on low-fidelity inviscid flow simulation","authors":"Dayeon Kim ,&nbsp;Jeongbeom Seo ,&nbsp;Inwon Lee","doi":"10.1016/j.ijnaoe.2025.100676","DOIUrl":"10.1016/j.ijnaoe.2025.100676","url":null,"abstract":"<div><div>In this study, neural networks are trained to transform inviscid simulation data for flow around a ship hull into data representative of viscous flow simulations. The objective is to provide high-fidelity viscous flow simulation data using machine learning in conjunction with inviscid flow simulation results, which are significantly less time-consuming to generate. This approach has the potential to accelerate high-fidelity flow simulations by a factor of more than 100, enabling simulation-based design for ship hulls with numerous repetitive cases. To create the training dataset, a variety of hull forms are generated from six baseline hull forms using parametric modification function techniques. Inviscid and viscous flow data for each hull are obtained through potential flow analysis and computational fluid dynamics - simulations, respectively. The neural network structure and hyperparameters are subsequently optimized through parametric studies. The trained neural networks are then employed to predict viscous flow simulation data based on inputs comprising inviscid flow data and hull form geometry. The results demonstrate that the neural networks successfully predicted both the pressure distribution around the hull and the free surface elevation. Notably, the ability to predict the free surface elevation is significant, given that inviscid flow simulations inherently lack this capability. Additionally, the neural network's dimensionality reduction feature is utilized to visualize how the flow and hull form data were clustered within the latent space based on baseline hull forms and ship speed.</div></div>","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"17 ","pages":"Article 100676"},"PeriodicalIF":2.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144702179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scheduling optimization of hull block assembly line using constraint programming and discrete-event simulation","authors":"Dong Hoon Kwak ,&nbsp;Ki-Young Cho ,&nbsp;Cheolho Ryu ,&nbsp;Jong Hun Woo","doi":"10.1016/j.ijnaoe.2025.100675","DOIUrl":"10.1016/j.ijnaoe.2025.100675","url":null,"abstract":"<div><div>Scheduling of a block assembly line in a shipyard is commonly known as the Permutation Flow-shop Scheduling Problem (PFSP) in Operation Research (OR), which has been extensively studied in various papers since the 1950s. However, existing solutions often involve simplifying real-world problems with certain assumptions, limiting their practical applicability. In recent times, Constraint Programming (CP) has emerged as a strong alternative to exact algorithms and has been successfully applied to various PFSP problems, addressing the limitations of exact algorithms. In light of this, our study proposes a two-step optimization process to overcome these limitations. First, a new PFSP problem, Multi-Objective PFSP with hard due date constraint (MOPFSP-hd) is introduced. The problem is solved with CP algorithm. Next, the feasibility and objective value of the optimized solution is validated using Discrete-Event Simulation (DES). Two industrial cases are conducted to evaluate the performance of our proposed framework. The experimental results from both cases demonstrated a significant improvement in makespan compared to manually planned schedule. Additionally, the solutions derived from our proposed model are reported to be feasible, while the manually planned schedules are often infeasible by not satisfying all the constraints or encountering delays. Finally, the difference between the objectives calculated from CP and DES model is analyzed quantitatively using Critical Path Method (CPM).</div></div>","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"17 ","pages":"Article 100675"},"PeriodicalIF":3.9,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144720899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to ‘A conceptual study of 15,000 TEU SMR-powered containerships’ [Int. J. Nav. Archit. Ocean Eng. 17 (2025) 100662]","authors":"Kyeongho Kim,&nbsp;ChangSeop Kwon,&nbsp;Sanghwan Kim","doi":"10.1016/j.ijnaoe.2025.100686","DOIUrl":"10.1016/j.ijnaoe.2025.100686","url":null,"abstract":"","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"17 ","pages":"Article 100686"},"PeriodicalIF":3.9,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144996397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative study of vapor pressure requirements for rule-based design of IMO Type C tanks for LCO2: Guidelines for optimizing pressure conditions","authors":"Younseok Choi ,&nbsp;Jinkwang Lee ,&nbsp;Jae Min Lee","doi":"10.1016/j.ijnaoe.2025.100668","DOIUrl":"10.1016/j.ijnaoe.2025.100668","url":null,"abstract":"<div><div>The safe and efficient design of liquefied carbon dioxide (LCO₂) storage tanks is essential for carbon capture, utilization, and storage (CCUS), particularly in maritime transport. IMO Type C pressure vessels are widely used, with minimum design vapor pressure determined by rule-based criteria. These regulations, based on fracture mechanics principles, prevent crack propagation-induced leaks. However, discrepancies between regulatory and operational pressures increase design complexity and iterative modifications. This study presents a thermodynamic framework to assess the gap between rule-based and actual vapor pressures and identifies volume-dependent implications for pressure control and insulation design. Simulations for 1000–5000 m³ tanks show that small tanks (1000–2000 m³) may exceed regulatory pressure limits, requiring enhanced insulation or pressure control. In contrast, large tanks (3000–5000 m³) are governed by conservative rule-based limits, suggesting potential for operational adjustments. The results offer an early-stage design guide balancing efficiency and regulatory compliance, supporting safe, economical marine LCO₂ transport system development.</div></div>","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"17 ","pages":"Article 100668"},"PeriodicalIF":2.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144604145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of object detection accuracy based on the density of 3D point clouds for deep learning-based shipyard datasets","authors":"Ki-Seok Jung ,&nbsp;Dong-Kun Lee","doi":"10.1016/j.ijnaoe.2025.100648","DOIUrl":"10.1016/j.ijnaoe.2025.100648","url":null,"abstract":"<div><div>3D point clouds are a crucial data format for accurately capturing geometric information in large-scale industrial environments such as shipyards. Deep learning-based object detection technology using 3D point clouds enables automated production management and process optimization. However, the large volume characteristic of 3D point clouds remains a challenge due to the resources and time required for data processing and dataset construction. The large volume of 3D point clouds leads to excessive computational costs, storage demands, and time consumption during dataset construction and training. Therefore, it is necessary to appropriately reduce the dataset size for efficient utilization while ensuring object detection performance. This necessitates a study on dataset downsampling strategies that maintain optimal density and detection accuracy. In this study, an experimental dataset similar to the S3DIS (Stanford Large-Scale 3D Indoor Spaces) dataset was constructed. The density of the 3D point clouds was adjusted in five levels by reducing points per unit area by 20% increments. These datasets were applied to a deep learning architecture to analyze object detection accuracy. Subsequently, the findings were applied to a shipyard dataset to streamline large volume point clouds and evaluate detection performance, thereby assessing their practical applicability. The results demonstrated that reducing the experimental dataset density to approximately 20% still maintained object detection accuracy of around 95% IoU for key objects. This indicates that lightweight datasets can reduce processing resources and costs while preserving detection performance. Additionally, applying the approach to real shipyard datasets revealed that object detection was feasible with reduced data (approximately 4.6% of the raw data). This study provides a practical framework for constructing efficient deep learning models for object detection by downsampling datasets in large-scale industrial environments like shipyards. It is expected to contribute to the establishment of automated data management systems for production management and process efficiency enhancement. Further analysis is required to evaluate performance at extreme low densities (below 20%). Moreover, while this study employed simple downsampling techniques, future work should explore the performance of various downsampling methods to optimize detection accuracy.</div></div>","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"17 ","pages":"Article 100648"},"PeriodicalIF":2.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143519503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated design parameter extraction and restoration from 2D propeller drawings","authors":"Jun-Su Park,&nbsp;Seung-Ho Ham","doi":"10.1016/j.ijnaoe.2025.100689","DOIUrl":"10.1016/j.ijnaoe.2025.100689","url":null,"abstract":"<div><div>The shipbuilding industry increasingly needs 3D propeller models from 2D drawings for repair, retrofitting, and energy-saving device (ESD) analysis. However, clients often provide only 2D drawings due to security, making manual information extraction for propeller models time-consuming, labor-intensive, and prone to errors. This highlights the need for automated, accurate extraction techniques. This study proposes a line detection and information extraction method to obtain design parameters from 2D propeller drawings. The method converts PDF drawings to images, preprocesses them, and then uses a path-finding algorithm to detect lines and extract information. This extracted data is converted into design parameters like rake, skew, chord length, camber, and thickness through offset data acquisition. Applying this method to propeller drawings significantly reduces time and effort compared to manual work, greatly improving efficiency and restoration accuracy. The method effectively detects complex and overlapping lines, and the quantitative accuracy of the extracted design parameters has been validated, with most parameters showing less than 1 % error.</div></div>","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"17 ","pages":"Article 100689"},"PeriodicalIF":3.9,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145026763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mitigation of the residual stress and deformation in seam pipe with girth welding and cutting","authors":"Ji-Sun Roh,&nbsp;Myung-Hyun Kim","doi":"10.1016/j.ijnaoe.2025.100657","DOIUrl":"10.1016/j.ijnaoe.2025.100657","url":null,"abstract":"","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"17 ","pages":"Article 100657"},"PeriodicalIF":2.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An advanced technique to adjust hull girder load: Part 1 = generalisation","authors":"Chang Hwan Jang ,&nbsp;Do Kyun Kim","doi":"10.1016/j.ijnaoe.2025.100645","DOIUrl":"10.1016/j.ijnaoe.2025.100645","url":null,"abstract":"<div><div>In this study (Part 1), a method is proposed to adjust the loads to achieve the target hull girder load with or without local loads on ships and ship-like structures. Each force or pressure load is referred to as a local load and the sum of forces and moments integrated with respect to the station is referred to as the hull girder load or global load. The hull girder load is composed of axial force (AF), vertical shear force (VSF), horizontal shear force (HSF), torsional moment (TM), vertical bending moment (VBM) and horizontal bending moment (HBM), each of which is related to each other by forces in the x, y and z directions. The adjustment of hull girder loads is required in hull structural analyses with various model extents and boundary conditions. In the whole ship model, it is necessary to implement more accurate hull girder loads and in the cargo hold, fore and aft body model, it is necessary to adjust the hull girder loads calculated from local loads to the target value. In the adjustment of the hull girder load, it is not only important to adjust it more accurately to the target value, but also the distribution of the added load is very important. In general, the hull girder load is adjusted to the target value by adding forces in the x, y and z directions to nodes in the cross section of the hull. If the forces are placed by considering only the position of the nodes, the loads may be concentrated or applied in a different direction from the placement of the elements, resulting in unexpected stresses or deformations in the structural analysis. It is necessary to consider not only the node position but also the size and orientation of the element for force distribution. In this paper, the load distribution at each node is obtained from the product of the directional effective area of the element and the stress field of the beam. The proposed method is validated by adjusting the hull girder loads to the target value for a beam structure with idealised hull. The method proposed in this study will be applied to actual ships in Part 2 (Jang and Kim, 2025a), and its applicability and extendibility are to be verified. This is considered to be beneficial for ship and offshore structural designers including oil/gas and ocean mobilities.</div></div>","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"17 ","pages":"Article 100645"},"PeriodicalIF":2.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143349961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A route planning method for small ships in coastal areas based on quadtree","authors":"Dong-Guen Jeong ,&nbsp;Myung-Il Roh ,&nbsp;In-Chang Yeo ,&nbsp;Ki-Su Kim ,&nbsp;Jun-Sik Lee","doi":"10.1016/j.ijnaoe.2025.100647","DOIUrl":"10.1016/j.ijnaoe.2025.100647","url":null,"abstract":"<div><div>Route planning for large commercial ships generally revolves around economic factors, such as fuel consumption and travel distance, which are often influenced by maritime weather conditions. In contrast, small ships navigating coastal areas, such as yachts, prioritize safety and navigational convenience. Although extensive research has been conducted on route planning for commercial ships, more studies focusing on small ships are required. This study introduces a novel route planning method for coastal areas tailored to small ships. The proposed method begins by generating quadtree charts derived from an S-57 chart. Considering the lower computational performance typically observed for small ships, a quadtree chart offers a more efficient solution than a traditional regular grid. This structure allows for high-resolution representation only where necessary, considering water depth and coastal obstacles to ensure safe navigation. The route planning process comprises two layers: high-level and low-level. The high-level layer uses lower-resolution charts to outline a general route between the departure and arrival points and to identify key entrances along the way. The low-level layer, which employs higher-resolution charts, generates a detailed route from the departure point to the entrance and from the entrance to the arrival point. The final step involves smoothing to ensure a seamless and navigationally efficient route. Adopting a hierarchical approach can significantly enhance the efficiency of route planning by utilizing a multi-level structure, thereby reducing the time required for route planning. This methodology enables more effective responses in continuous maritime environments, ensuring high efficiency even during real-time route updates and modifications. The proposed method was applied to the coastal areas of the Republic of Korea to assess its effectiveness. In this study, the proposed method was compared with conventional chart generation methods. The results demonstrate that the method provides suitable and safe route planning for small ships, offering a reliable approach for coastal area navigation.</div></div>","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"17 ","pages":"Article 100647"},"PeriodicalIF":2.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on sound radiation mechanism of rectangular cross-section shell based on noise source identification method","authors":"Lu Tan ,&nbsp;Han Xiao ,&nbsp;Xiao-Jun Lv ,&nbsp;Zhi-Yong Xie","doi":"10.1016/j.ijnaoe.2025.100650","DOIUrl":"10.1016/j.ijnaoe.2025.100650","url":null,"abstract":"<div><div>To reveal the acoustic radiation mechanism of rectangular cross-section shells, a noise source identification method for irregular shells is proposed. This method decouples the fluid-structure interaction vibration by using the method of structural-finite-element coupled with fluid-boundary-element, and obtains the vibration and pressure of the shell. Subsequently, using these results as input, the noise source identification of the shell is accomplished by solving the acoustic radiation mode decomposition problem of non-uniform discrete models. Specifically, by designing a decoupling approach for the fluid-structure interaction vibration, the subsequent acoustic radiation mode decompositions can utilize the same acoustic radiation impedance matrix, thereby enhancing the computational efficiency. Utilizing this method, the main acoustic radiation forms rectangular cross-section shell and their related laws were analyzed, and the general acoustic radiation mechanism of the shell was revealed. This provides essential theoretical and technical support for the precise noise reduction of the rectangular cross-section shell.</div></div>","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"17 ","pages":"Article 100650"},"PeriodicalIF":2.3,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143562610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}