Optimized Structural Design Recommender System A two-step solution for AI-based ship design optimization

Estimating the steel weight of ships during the early conceptual stages is of the utmost importance since it represents about 50% of the lightship weight of the ship. From a technical standpoint, it significantly affects cargo capacity, design speed, stability, and ship safety, thus requiring an accurate estimation. The steel weight is usually evaluated using simple empirical formulations during the concept design, mainly based on the ship’s main particulars. Those formulas are derived by statistical analysis of past projects and can be applied only for the specific ship type (or types) included in the considered database. In the literature, many formulas are present mainly related to cargo ships. Currently, no empirical formulation is available for cruise ships that are applicable in the very early conceptual stages. The present study aims to identify an empirical formulation for estimating the steel weight of a luxury cruise ship based on calibrating a set of existing empirical formulas.

Tensegrity structures, characterized by enhanced stiffness, slender struts, and superior buckling resistance, have found wide-ranging applications in fields such as engineering, architecture, art, biology, and robotics, attracting extensive attention from researchers. The form-finding process, a critical step in the design of tensegrity structures, aims to discover the self-equilibrated configuration that satisfies specific design requirements. Traditional form-finding methods based on force density often require repeated steps of eigenvalue decomposition and singular value decomposition, making the process complex. In contrast, this paper introduces a new intelligent form-finding algorithm that uses the force density method and combines the Coati optimization algorithm with Graph Neural Networks. This algorithm avoids the complex steps of eigenvalue and singular value decomposition and integrates the physical knowledge of the structure, making the form-finding process faster and more accurate. In this algorithm, various force densities are initially randomized and input into a trained Graph Neural Networks to predict a fitness function’s value. Through optimizing the constrained fitness function, the algorithm determines the appropriate structural force density and coordinates, thereby completing the form-finding process of the structure. The paper presents seven typical tensegrity structure examples and compares various form-finding methods. The results of numerical examples show that the method proposed in this paper can find solutions that align with the super-stable line more quickly and accurately, demonstrating its potential value in practical applications.

Part One: Introduction to Structural Design Philosophy of Design Basic Structural Concepts and Material Properties Part Two: Structural Design to British Standards Design in Reinforced Concrete to BS8110/BS8500 Design in Structural Steelwork to BS5950 Design in Unreinforced Masonry to BS5628, BS EN771, BS EN845 and BS EN998 Design in Timber to BS5268 Part Three: Structural Design to the Eurocodes The Structural Eurocodes: An Introduction Eurocode 2: Design of Concrete Structures Eurocode 3: Design of Steel Structures Eurocode 6: Masonry Design Eurocode 5: Timber Design

The study of ship floating balance plays a very important role in the safety of ships. According to certain conditions of ship statics, the nonlinear equations of ship balance can be established with relevant parameters such as ship weight, draft, heeling angle, longitudinal inclination angle and static moment. In this paper, motivated by the least square method, the nonlinear equations of floating equilibrium are transformed to a nonlinear programming problem. The draught, heel and trim of the ship are taken as variables, and inequality constrained by the actual situation. The penalty function for nonlinear programming is considered and minimized by particle swarm optimization. The proposed optimization method simplifies the calculation process by avoiding the calculation of parameters. Numerical results verify the efficiency of the proposed method.

In determining the seaworthiness of the ship, ship inspection is very important to do. KSOP has a very important role in determining the seaworthiness of ships. This study aims to determine the role of marine inspectors in ship inspection at KSOP Class IV Probolinggo. The research used qualitative descriptive methods. Data collection was carried out by surveys and interviews. The results of this study show that the marine inspector has the role and task of preparing to discuss the formulation and implementation of policies, standards, norms, guidelines, criteria, and procedures as well as technical guidance, evaluation, certification, and reporting in the fields of ship design, measurement, construction and stability of ships, nautical, technical, and radio as well as equipment and equipment for ship safety and equipment as well as prevention of pollution from ships and management of ship safety and operation for ships indonesian flags that sail in Indonesian and international waters for all types of ships and all sizes. In the duties of inspection and measurement of ships carried out in the Legal Status and Certification of Ships section, carry out inspection tasks at the Port of Probolinggo. The results of the survey of the marine administration examination and physical examination were obtained that it took an average of 32.57 minutes.

이 연구에서는 10년간(1997-2006년)의 기상청 AWS(Automatic Weather System) 자료를 이용하여 선박의 안전과 항만구조물 등의 안정성에 매우 중요한 부산 해안의 바람분포 특성을 분석하였다. 그리고 부산 해안의 바람분포 특성을 명확히 파악하기 위하여 해륙풍의 영향을 받지 않는 밀양의 바람분포 특성도 해석하여 비교하였다. 부산 해안의 평균풍속은 밀양보다 강하고, 부산 해안 중에서도 섬인 영도와 가덕도의 평균풍속은 일광, 해운대 및 대연의 그것보다 약 2.0배 강한 특성을 보인다. 상관분석에 의하여, 부산 해안의 월별 평균풍속은 서로 변화 경향이 매우 유사함을 확인하였다. 부산 해안의 월별 평균풍속의 최대값은 9월에 나타나는데, 이는 태풍의 영향과 밀접히 관련되어 있다. 최대 순간풍속도 섬인 영도와 가덕도에서 특히 강하고, 부산 해안의 최대순간풍속은 주로 8-9월에 그 최대값이 관측된다. 부산 해안의 풍향별 관측 횟수의 백분율을 살펴보면, 겨울은 남서풍-북북동풍이 우세하고 봄은 남서풍과 북동풍이 우세하다. 여름의 풍향 분포는 봄과 비슷하고, 가을의 풍향 분포는 겨울과 유사한 경향을 보인다. Wind velocity and wind direction are very important in the viewpoint of ship's safety and stability of port structure. The characteristics of wind distribution in the coast of Busan are analyzed for 10 years from 1997 to 2006 using AWS(Automatic Weather System) data. The characteristics of wind distribution of Miryang, is not affected by the land and sea breeze are also examined to understand clearly the characteristics of wind distribution in the coast of Busan. The mean wind velocity in the coast of Busan is stronger than that of Miryang. The mean wind velocitie at Youngdo and Gadukdo stations of Busan are stronger about 2.0 times than those at IlGwang, Haeundae and Daeyeon stations. The correlation a states show that the variation tendencies of monthly mean wind velocitie in the coast of Busan are very similar. The maximum monthly mean velocitie in the coast of Busan are recorded in September. This re ult is closely related to the influence of typhoon. The maximum instantaneous wind velocitie are also strong at Youngdo and Gadukdo stations and the peaks of maximum instantaneous wind <TEX>$velocit^9$</TEX> are observed mainly from August to September. In the coast of Busan, the SW'ly-NNE'ly wind are prevailing in the winter and the SW'ly and NE'ly wind are predomi snt in the spring. w that the vs of wind direction in the summer and athumn are similar with those in the spring and winter, respectively.

Water entry is a fluid–structure interaction process closely related to the ocean environment. Repeated water entries take place when ships are sailing in an ocean environment, e.g., ocean currents, which greatly affect the ship's safety and stability in navigation. In this paper, we adopt a smoothed particle hydrodynamics method to numerically study the water entry of a bow-flare ship body section under ocean currents. We simulate the process of water entry under different current velocities and analyze in detail the fluid field regarding the free surface evolution, the velocity and pressure distributions, and the body's forces and motions. It is revealed that the ocean current can induce multidirectional fluid impacts, and a stagnation point with zero velocity occurs at the upstream side. Asymmetric fluid fields including the evolution of the free surface and the velocity and pressure distributions around the body can also be found. In addition, discrepancies are caused in the formation time and the range of the high-pressure region. These fluid field changes greatly affect the ship body's dynamic responses. However, the effects of the ocean current are mainly reflected in the direction of the current flow and are relatively small in the direction perpendicular to the flow.

This chapter discusses round bamboo's physical and mechanical properties, including the effect of physical properties, stress–strain relationships, mechanical property variations due to its graded structure, longitudinal mechanical properties, transverse mechanical properties, and methods for determining round bamboo properties. Additionally, the round bamboo grading method, a review of international bamboo structural element design standards, and codes of practice for further bamboo building standardization were also discussed. Appropriate standardized test methods capable of reliably providing fundamental material properties enable the calibration of material resistance factors and the extension of design guidance to various species of round bamboo. Standardized test methods used in well-defined experimental studies also allow for the separation of factors influencing material performance and behavior. This method represents a step toward rational and universal structural design methods for round bamboo. Material property standardization is critical for the development of both traditional and modern construction materials.

Maritime transport serves about 80% of world trade among transport modes and is of great importance for the global economy as it has a great impact on economic development. The aim of this study is to examine the studies on maritime transport between 2010-2023 by bibliometric analysis method. For this purpose, the Web of Science database was searched using the terms "maritime transport", "waterway transport", "sea transport" and 574 publications with this term in the title were found. These publications were then filtered as articles and 395 article studies were visualised and interpreted using VOSviewer mapping method. It was observed that the highest number of publications in the time period considered was in 2023 with 48 publications. Following the analysis, "maritime transport" was the most used keyword, appearing 81 times. Kum Fai Yuen (5 publications, 176 citations) and Harilaos N. Psaraftis (5 publications, 132 citations) are the researchers with the most publications, co-authorship, and citations. With 43 publications, China is the nation with the most publications. Once more, with 570 citations, China is the most referenced nation. TransNav: International Journal on Marine Navigation and Safety of Sea Transportation is found to have the highest number of publications (24 publications).

THE stability of ships is a subject that has attracted considerable attention of late. Many disasters have happened to ships through insufficient stability, and have caused scientific men as well as practical naval architects to apply themselves to a renewed and close investigation of the subject. The result is that the ideas which till late prevailed respecting it are seen to be often superficial and incomplete, and in some cases not entirely free from error.

The existing stability criterion for semi submersible drilling platforms requires righting moment energy in excess of wind heel energy to allow for dynamic effects. Dynamic effects have been studied by testing a scale model of a semi submersible platform to evaluate the effect of wind velocity, center of gravity, air gap, and moorings ontendency to capsize in survival wave conditionsrelative motion between leeward deck edge and wave surface as a measure of down flooding tendency. FOREWORD At the occasion of the 1971 Offshore Technology Conference, the research panel on Offshore Mobile Platforms had its first meeting. Designated as Panel MS-3 of the Marine Systems committee, under the continuing research activities of the Society of Naval Architects and Marine Engineers, it has a se 1ect representation of drilling con tractors, oil companies, regulatory agencies and naval architects. Its purpose was set forth to identify and to promote research in such vital areas associated with mobile platforms towards more adequate design, construction and operation. By the following year, the panel had clearly identified the assessment of stability of mobile platforms as one of the most important and pressing problems, particularly in regard to the semi-submersible. The existing criteria, as promulgated by the u. S. Coast Guard and the American Bureau of Shipping (Reference I), were considered inadequate to properly assess the various dynamic influences on the platform and its inherent ability to resist them. A program of research was indicated. By OTC 1973, the program was on its way. Davidson Laboratory of Stevens Institute of Technology was selected to perform the initial research, and funds were being accumulated from solicitations through the industry, to where by mid-summer the first phase of experimental work was begun. This paper discusses the rationale leading to the panel IS conclusion that a research project of this type was both necessary and urgent, along with an outline of the full intended program. The gist of the paper, however, is the presentation of the experimental work done during the second half of last year, as a major part of this research, and which resulted in some valuable observations and a few surprises. EXAMINING THE PRESENT STABILITY CRITERIA Dissatisfaction with the present stability criteria as applied to semi-submersibles has existed since their adoption in the 1968 ABS rules. (It may be noted that many panel MS-3 members have also been serving on the ABS rules committee.) Based on a U. S. Coast Guard criterion for the stability of a surface ship in roll, somewhat empirically derived, it does not adequately account for the excitations nor responses of the semi-submersibleto the possible environment. Figure I shows the now familiar curves of requirement for stability; taken from the detail requirements as set forth in Reference I and as later amended in Reference 2. It shows an overturning moment curve, calculated for a steady wind speed, superimposed on the vessel IS righting moment curve of static stability, all in calm water.

Nowadays, many countries are looking towards sustainability as a goal because our world has limited resources and serious environmental impacts. In the construction industry, the process of sustainable selection of structural material is considered one of the keys to achieve more sustainable construction. In this paper, the theories of decision making are utilised to develop an approach for evaluation and ranking the structural materials over their total life based on sustainability criteria using multi-attribute decision-making methods. One of them is Analytical Hierarchy Process which is utilised to build the problem hierarchical structure and assign weights of the predetermined sustainable factors. The other is Technique for Order Preference by Similarity to the Ideal Solution which is utilised to rank the structural materials within both each material life cycle phase and the complete material life cycle phases. The third is the concept of entropy by Shannon to evaluate the weight factor for each phase of material life cycle. The proposed approach presents an objective, systematic and comprehensive method for the sustainable ranking of materials that links between the structural element design and the sustainable selection of materials.

Graph Neural Networks (GNNs) have been proven effective in modeling graph data, mostly depending on the in-distribution assumption. While in the out-of-distribution (OOD) scenarios, especially for the more challenging node-level task, the feature and structure distribution shifts between training and test nodes lead to performance degradation. To improve node-level OOD generalization, typical approaches introduce graph augmentation to enrich the training environments and conduct invariant learning to learn stable representations across various augmented environments. However, their graph augmentations emphasize diversity but neglect the preservation of invariant patterns which are fundamental to invariant learning. Moreover, most of them simply conduct the classic invariant learning objective but lack the consideration of the graph-specific structure information. Therefore, to mitigate their weakness, we propose a Structure-aware Invariant learning framework for Node-level Graph OOD generalization (SING). Specifically, we develop the invariance constraint regularization terms during the optimization of augmentations. Additionally, we define the structure embedding to elucidate the structural property and design the structure embedding alignment loss to optimize the augmentations and the invariant representations. By introducing the structure information, we further integrate the unique structural property into invariant learning, thereby boosting the invariant message-passing GNNs. The extensive experiments on the transductive GOOD benchmark and the inductive datasets empirically validate our superior OOD generalization performance to baselines.

The integration of artificial intelligence (AI) with bioinformatics has initiated a transformative shift in drug discovery, redefining how pharmaceutical research and development are conducted. This review examines both the current state and emerging prospects of AI-driven strategies across the drug discovery pipeline, from target identification and molecular design to clinical applications. Advances in machine learning, deep learning, graph neural networks, transformers, foundation models, and quantum computing have shown remarkable potential in overcoming long-standing bottlenecks of conventional drug development, which on average requires 12.5 years and over $2 billion to bring a single drug to market. The AI in pharmaceuticals market, valued at $1.8 billion in 2023, is projected to reach $13.1 billion by 2030, reflecting a compound annual growth rate of 18.8%. Landmark breakthroughs such as AlphaFold, which has generated over 200 million predicted protein structures and more than 20,000 citations, have established new paradigms in structural biology and drug design, while emerging tools like RFdiffusion and AlphaFold3 further extend capabilities into de novo protein design and multi-omics integration. AI-enabled workflows have demonstrated the ability to compress discovery timelines from five years to as little as 12–18 months and reduce costs by up to 40%. Despite these advances, significant challenges remain, including issues of data quality and bias, model transparency and interpretability, computational resource demands, and ethical concerns regarding privacy and algorithmic fairness. This review synthesizes findings from recent studies to provide a roadmap for the responsible and reproducible integration of AI into bioinformatics and drug discovery, while outlining critical gaps and future research priorities essential for clinical translation.

Maritime transportation is the cornerstone of the global economy, making understanding vessel activities and their impacts vital. This paper presents a graph-based approach for classifying navigational statuses of vessel trajectories, employing a hierarchical multi-classification deep learning framework using Automatic Identification System (AIS) data. AIS messages are first segmented into continuous tracks, then divided into fixed-size mini-trajectories called a ‘trajectlet’. Labels are assigned using domain knowledge and rule-based methods. Each trajectlet is modelled as a directed acyclic graph, capturing sequential and spatio-temporal movement dynamics. A Graph Neural Network (GNN) first classifies the AIS messages within each trajectlet as ‘stationary’ or ‘underway’. These node-level predictions are then pooled and combined with global features of each trajectlet, and then passed through a multi-layer perceptron to classify the entire trajectlet into one of four navigational statuses. The framework is validated on AIS data from vessels in UK waters, achieving 98% accuracy and F-score, and a 99% AUC–ROC, demonstrating strong predictive performance. This method enhances understanding of vessel operations and supports applications in emissions modelling, economic forecasting, autonomous navigation, and maritime situational awareness. • Models AIS messages as graphs with spatio-temporal and sequential links. • Classifies vessel status using feature-level attention in a GNN framework. • Combines node and graph-level outputs in a hierarchical multi-level classification. • Achieves 98% accuracy and F1-score, 99% AUC–ROC on UK AIS data. • Supports autonomy, port monitoring, emissions and economic modelling.