Hasil untuk "Naval architecture. Shipbuilding. Marine engineering"

Quang-Trung Truong, Yuk-Kwan Wong, Vo Hoang Kim Tuyen Dang et al.

Marine videos present significant challenges for video understanding due to the dynamics of marine objects and the surrounding environment, camera motion, and the complexity of underwater scenes. Existing video captioning datasets, typically focused on generic or human-centric domains, often fail to generalize to the complexities of the marine environment and gain insights about marine life. To address these limitations, we propose a two-stage marine object-oriented video captioning pipeline. We introduce a comprehensive video understanding benchmark that leverages the triplets of video, text, and segmentation masks to facilitate visual grounding and captioning, leading to improved marine video understanding and analysis, and marine video generation. Additionally, we highlight the effectiveness of video splitting in order to detect salient object transitions in scene changes, which significantly enrich the semantics of captioning content. Our dataset and code have been released at https://msc.hkustvgd.com.

Tenglong Li, Jindong Li, Guobin Shen et al.

Spiking transformers are emerging as a promising architecture that combines the energy efficiency of Spiking Neural Networks (SNNs) with the powerful attention mechanisms of transformers. However, existing hardware accelerators lack support for spiking attention, exhibit limited throughput in exploiting fine-grained sparsity, and struggle with scalable parallelism in sparse computation. To address these, we propose FireFly-T, a dual-engine overlay architecture that integrates a sparse engine for activation sparsity and a binary engine for spiking attention. In the sparse engine, we propose a highthroughput sparse decoder that exploits fine-grained sparsity by concurrently extracting multiple non-zero spikes. To complement this, we introduce a scalable load balancing mechanism with weight dispatch and out-of-order execution, eliminating bank conflicts to support scalable multidimensional parallelism. In the binary engine, we leverage the byte-level write capability of SRAMs to efficiently manipulate the 3D dataflows required for spiking attention with minimal resource overhead. We also optimize the core AND-PopCount operation in spiking attention through a LUT6-based implementation, improving timing closure and reducing LUT utilization on Xilinx FPGAs. As an overlay architecture, FireFly-T further incorporates an orchestrator that dynamically manipulates input dataflows with flexible adaptation for diverse network topologies, while ensuring efficient resource utilization and maintaining high throughput. Experimental results demonstrate that our accelerator achieves $1.39\times$ and $2.40\times$ higher energy efficiency, as well as $4.21\times$ and $7.10\times$ greater DSP efficiency, compared to FireFly v2 and the transformer-enabled SpikeTA, respectively. These results highlight its potential as an efficient hardware platform for spiking transformer.

Shraddha Surana, Ashwin Srinivasan, Michael Bain

Engineering information systems for scientific data analysis presents significant challenges: complex workflows requiring exploration of large solution spaces, close collaboration with domain specialists, and the need for maintainable, interpretable implementations. Traditional manual development is time-consuming, while "No Code" approaches using large language models (LLMs) often produce unreliable systems. We present iProg, a tool implementing Interactive Structured Inductive Programming. iProg employs a variant of a '2-way Intelligibility' communication protocol to constrain collaborative system construction by a human and an LLM. Specifically, given a natural-language description of the overall data analysis task, iProg uses an LLM to first identify an appropriate decomposition of the problem into a declarative representation, expressed as a Data Flow Diagram (DFD). In a second phase, iProg then uses an LLM to generate code for each DFD process. In both stages, human feedback, mediated through the constructs provided by the communication protocol, is used to verify LLMs' outputs. We evaluate iProg extensively on two published scientific collaborations (astrophysics and biochemistry), demonstrating that it is possible to identify appropriate system decompositions and construct end-to-end information systems with better performance, higher code quality, and order-of-magnitude faster development compared to Low Code/No Code alternatives. The tool is available at: https://shraddhasurana.github.io/dhaani/

Tyler Slater

As Large Language Models (LLMs) transition from code completion tools to autonomous system architects, their impact on long-term software maintainability remains unquantified. While existing research benchmarks functional correctness (pass@k), this study presents the first empirical framework to measure "Architectural Erosion" and the accumulation of Technical Debt in AI-synthesized microservices. We conducted a comparative pilot study of three state-of-the-art models (GPT-5.1, Claude 4.5 Sonnet, and Llama 3 8B) by prompting them to implement a standardized Book Lending Microservice under strict Hexagonal Architecture constraints. Utilizing Abstract Syntax Tree (AST) parsing, we find that while proprietary models achieve high architectural conformance (0% violation rate for GPT-5.1), open-weights models exhibit critical divergence. Specifically, Llama 3 demonstrated an 80% Architectural Violation Rate, frequently bypassing interface adapters to create illegal circular dependencies between Domain and Infrastructure layers. Furthermore, we identified a phenomenon of "Implementation Laziness," where open-weights models generated 60% fewer Logical Lines of Code (LLOC) than their proprietary counterparts, effectively omitting complex business logic to satisfy token constraints. These findings suggest that without automated architectural linting, utilizing smaller open-weights models for system scaffolding accelerates the accumulation of structural technical debt.

Chi CAO, Wentao SHI, Baihe WANG et al.

In view of the requirement of establishing an underwater weapon simulation system in an anti-submarine warfare scenario, this paper analyzed the tactical characteristics of unmanned undersea vehicle(UUV), clarified the whole flow of the sub-modules of the UUV for warfare operations, including launch control, wire guide, target detection, target search and tracking, underwater target attack, and other functions. By modelling the various functional sub-modules, a comprehensive anti-submarine warfare simulation model of UUVs was constructed, providing a corresponding dynamic link library to be called for underwater warfare simulation missions. After simulation verification, the constructed UUV simulation model can realize the underwater anti-submarine strike mission according to the battlefield environment information provided by users, such as two-party location and acoustic parameters and provide technical support for the establishment of an underwater weapon countermeasure simulation system.

LIU Changxi, QI Guomin, WANG Jicheng, LI Tianye, YANG Jian, LEI Xia

To promote the process of carbon emission reduction in the electric power industry and achieve the goal of “carbon peaking and carbon neutrality”, the construction of a unified national power market system is being accelerated. A two-stage market clearing model considering load participation in carbon trading is proposed to reduce carbon emissions and facilitate clean energy substitution in the electricity sector. First, an initial carbon quota allocation method for thermal power units based on zero sum gains-data envelopment analysis is introduced, and the electricity market clearing model considering carbon trading is established. Then, based on the market clearing results from the first stage, the new energy consumption of loads is determined using the power flow tracing theory, and the Chinese certified emission reduction (CCER) is calculated. Following CCER carbon offset rules, the second stage of carbon emission trading is initiated, and the secondary electricity market subject to carbon emission constraints, is cleared based on the carbon trading results. Finally, an analysis using the improved IEEE 30-bus system is conducted to validate the effectiveness of the proposed market model. The results show that the proposed model not only helps reduce the carbon emissions from thermal power units but also increases the market share of new energy consumption and lowers average electricity prices. Additionly, the model provides a viable scheme for the large-scale marketization consumption of new energy.

Xingfei Cao, Zhiming Wang, Yahong Zhu et al.

As intelligent vessel technology moves from the proof-of-concept stage to engineering applications, the performance testing and evaluation of autonomous collision avoidance algorithms have become core issues for safeguarding maritime traffic safety. The International Maritime Organization (IMO)’s Maritime Safety Committee (MSC), at its 109th session, agreed to a revised road map for the development of the Maritime Autonomous Surface Ships (MASS) Code; the field has experienced the development stages of single-vessel collision avoidance validation based on COLREGs, multimodal algorithm collaborative testing, and the current construction of a progressive validation system for the integration of a mix of virtual reality and actual reality. In recent years, relevant studies have achieved research achievements, especially in the compatibility of COLREGs and in accurate collision avoidance in complex situations, and other algorithm tests and evaluations have made great breakthroughs. However, a systematic literature review is still lacking. In this paper, we systematically review the research progress of autonomous collision avoidance performance testing and the evaluation of intelligent vessels; summarize the advantages and disadvantages of virtual testing, model testing, and full-scale vessel testing; and analyze the applicability and limitations of mainstream algorithms such as the velocity obstacle algorithm, the artificial potential field algorithm, and reinforcement learning. It focuses on the key technologies such as diverse scene generation, local scene slicing, and the construction of an evaluation index system. Finally, this paper summarizes the challenges faced by autonomous collision avoidance performance testing and the assessment of intelligent vessels and proposes potential technical solutions and future development directions in terms of virtual–real fusion testing, dynamic evaluation index optimization, and multimodal algorithm co-validation, aiming to provide a reference for the further development of this field.

Ilya V. Buynevich, Michael Savarese, H. Allen Curran

Quaternary carbonate strandplains serve as archives of land–sea interaction, including the impacts of storms and tsunamis. Incipient lithification, especially of compound beach/dune ridges within the action zone of salt spray, presents challenges to geological research, which is often limited to exposures. This study combines aerial image analysis with geophysical datasets to assess the morphostratigraphy and internal structure of the Freedom Beach Strandplain along southern Eleuthera Island, The Bahamas. Color-intensity analysis of field photographs and satellite images revealed general patterns that can be used to distinguish between areas with different grayscale parameters (sand-covered surfaces, lithified ridges, vegetation, etc.). Cross-shore (dip-section) high-resolution (800 MHz) georadar images across ten ridges (A-J) documented the internal architecture of swash-aligned ridge–swale sets. Signatures attributed to storms include truncations in shore-normal radargrams, scour features in alongshore (strike-section) images, and an extensive accumulation of large mollusk shells along one of the oldest ridges (ridge J). Preliminary radiocarbon dating yielded ages of up to 600 years, suggesting intense storms with 50–60-year periodicity as a possible mechanism for ridge formation.

Xiaohan Xu, Peng Qin, Zhenyu Li et al.

Landslide impacts into water generate impulse waves that, in confined basins and along steep coasts, escalate swiftly into hazardous near-shore surges. In this study, we present a scenario-aware workflow using gradient boosting and <i>k</i>-means clustering, and explain them using Shapley additive explanations (SHAPs). Two cases are addressed: forecasting at water entry (Scenario I) with predictors Froude number <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>F</mi><mi>r</mi></mrow></semantics></math></inline-formula>, relative effective mass <i>M</i>, and relative thickness <i>S</i>; and pre-event assessment (Scenario II) with predictors Bingham number <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>B</mi><mi>i</mi></mrow></semantics></math></inline-formula>, relative moving length <i>L</i>, and relative initial mass <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>M</mi><mi>i</mi></mrow></semantics></math></inline-formula>. Using 270 controlled physical-model experiments, we benchmark six learning algorithms under 5-fold cross-validation. Gradient boosting delivers the best overall accuracy and cross-scenario robustness, with XGBoost close behind. Scenario I attains a coefficient of determination <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.941, while Scenario II achieves <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi>R</mi><mn>2</mn></msup><mo>=</mo><mn>0.865</mn></mrow></semantics></math></inline-formula>. Residual analyses indicate narrower spreads and lighter tails for the top models. SHAP reveals physics-consistent controls: <i>M</i> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>F</mi><mi>r</mi></mrow></semantics></math></inline-formula> dominate Scenario I, whereas initial mass and the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>B</mi><mi>i</mi></mrow></semantics></math></inline-formula> dominate Scenario II; interactions <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>F</mi><mi>r</mi><mo>×</mo><mi>S</mi></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>M</mi><mi>i</mi><mo>×</mo><mi>B</mi><mi>i</mi></mrow></semantics></math></inline-formula> clarify non-linear amplification of wave amplitude and height. The cluster–predict–explain framework couples predictive skill with physical transparency and is directly applicable to coastal hazard screening and integration into shoreline early-warning workflows.

Yimiao Gu, Yanmin Zeng, Hui Shan Loh

The widespread adoption of liquefied natural gas (LNG) as a marine fuel has driven the development of LNG bunkering operations in global ports. Major international hubs, such as Shenzhen Port, have implemented ship-to-ship (STS) bunkering practices. However, this process entails unique safety risks, particularly hazards associated with vapor cloud dispersion caused by bunkering hose releases. This study employs the Phast software developed by DNV to systematically simulate LNG release scenarios during STS operations, integrating real-world meteorological data and storage conditions. The dynamic effects of transfer flow rates, release heights, and release directions on vapor cloud dispersion are quantitatively analyzed under daytime and nighttime conditions. The results demonstrate that transfer flow rate significantly regulates dispersion range, with recommendations to limit the rate below 1500 m³/h and prioritize daytime operations to mitigate risks. Release heights exceeding 10 m significantly amplify dispersion effects, particularly at night (nighttime dispersion area at a height of 20 m is 3.5 times larger than during the daytime). Optimizing release direction effectively suppresses dispersion, with vertically downward releases exhibiting minimal impact. Horizontal releases require avoidance of downwind alignment, and daytime operations are prioritized to reduce lateral dispersion risks.

Juan C. Rocha, Jean-Baptiste Jouffray, Frida Bengtsson et al.

Climate change and other anthropogenic pressures are likely to induce tipping points in marine ecosystems, potentially leading to declines in primary productivity and fisheries. Despite increasing attention to nature-related financial risks and opportunities within the ocean economy, the extent to which these tipping points could affect investors has remained largely unexplored. Here we used satellite data to track fishing vessels operating in areas prone to marine regime shifts, as identified by their loss of resilience and vulnerability to marine heatwaves, and uncovered their corporate beneficial owners and shareholders. Despite some data gaps, we identified key countries, companies, and shareholders exposed to tipping risk. We also outline the potential challenges and opportunities that these actors may face if marine ecosystems shift to less productive states.

Nikhil Patnaik, Joseph Hallett, Awais Rashid

Writing secure code is challenging and so it is expected that, following the release of code-generative AI tools, such as ChatGPT and GitHub Copilot, developers will use these tools to perform security tasks and use security APIs. However, is the code generated by ChatGPT secure? How would the everyday software or security engineer be able to tell? As we approach the next decade we expect a greater adoption of code-generative AI tools and to see developers use them to write secure code. In preparation for this, we need to ensure security-by-design. In this paper, we look back in time to Saltzer & Schroeder's security design principles as they will need to evolve and adapt to the challenges that come with a world of AI-generated code.

Huanyu Ou, Yuli Hu, Zhaoyong Mao et al.

Subject to an autonomous underwater vehicle (AUV) with rigorously limited space and weight, the high-power-density propulsion motor urgently needs an efficient cooling method to improve reliability and stability. In this paper, a cooling improvement method based on heat bridges (HBs) is proposed for the shell-mounted propulsion motor (SmPM) of the AUVs. First, the electromagnetic and thermal characteristics of a 150 kW SmPM are analyzed using a numerical method. Then, a prototype was developed and tested to verify the accuracy of the numerical calculation. Subsequently, in order to further improve the cooling performance of the motor with minimal weight increment, this paper proposes HBs mounted on the end winding. The maximum winding temperature of the motor containing the proposed HBs is decreased by 20 K at the rated operation state. Based on the validated numerical method, the effects of topologies, materials, and geometric parameters on the cooling effect are investigated. Furthermore, according to the required operating time, the SmPM is optimized based on the cooling performance improvement provided by the proposed HBs. The results show that in addition to the benefit of the cooling improvement contributed by the proposed HB, the weight of the propulsion motor is reduced by 7.14%.

Long Chen, Guanyu Hu, Zhenfang Zhao et al.

The aim of this study was to explore the connection between growth and feeding ecology and mercury (Hg) levels in Japanese anchovy (<i>Engraulis japonicus</i>). We measured the amounts of Hg and stable carbon and nitrogen isotopes in the muscle of 143 Japanese anchovy specimens obtained from the open seas of the Northwest Pacific Ocean (39°2′ N~42°30′ N, 154°02′ E~161°29′ E) between June and July 2021. The results showed that there were significant differences (<i>p</i> < 0.05) in the δ¹³C and δ¹⁵N values of Japanese anchovies across all body length groups. As individuals grew, δ¹³C tended to decrease first and then increase, and δ¹⁵N tended to gradually increase. The standard ellipse corrected area showed an increasing and subsequently decreasing pattern with growth. It reached its greatest value (0.80) in the 111–120 mm group. Compared to the body length group of 91–120 mm, the niche overlap decreased for the 121–140 mm group in Japanese anchovy. Hg levels increased gradually with body length. Linear regression models revealed a positive correlation between Hg levels and δ¹³C in fish. Hg levels increased gradually, while δ¹⁵N remained relatively constant in the 7–9‰ range. In our study, a distinct shift in diet was observed for Japanese anchovy with increasing body length, and the differences in diet among life stages could be responsible for the changes in Hg levels.

María Isabel Lamas Galdo, Tomás Guillén Díaz, Pablo Rubial Yáñez et al.

Raúl Rodríguez Arias, Jorge Enrique Carreño Moreno, Frederico Cupello et al.

Jisang Ha, Myung-Il Roh, Ki-Su Kim et al.

Lorenz Graf-Vlachy

Software engineering capabilities are increasingly important to the success of economic and political blocs. This paper analyzes quantity and quality of software engineering research output originating from the US, Europe, and China over time. The results indicate that the quantity of research is increasing across the board with Europe leading the field. Depending of the scope of the analysis, either the US or China come in second. Regarding research quality, Europe appears to be lagging the other blocs, with China having caught up to and even having overtaken the US over time.

Xianwei Xie, Baozhi Sun, Xiaohe Li et al.

An accurate fuel consumption prediction model is the basis for ship navigation status analysis, energy conservation, and emission reduction. In this study, we develop a black-box model based on machine learning and a white-box model based on mathematical methods to predict ship fuel consumption rates. We also apply the Kwon formula as a data preprocessing cleaning method for the black-box model that can eliminate the data generated during the acceleration and deceleration process. The ship model test data and the regression methods are employed to evaluate the accuracy of the models. Furthermore, we use the predicted correlation between fuel consumption rates and speed under simulated conditions for model performance validation. We also discuss applying the data-cleaning method in the preprocessing of the black-box model. The results demonstrate that this method is feasible and can support the performance of the fuel consumption model in a broad and dense distribution of noise data in data collected from real ships. We improved the error to 4% of the white-box model and the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> to 0.9977 and 0.9922 of the XGBoost and RF models, respectively. After applying the Kwon cleaning method, the value of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> also can reach 0.9954, which can provide decision support for the operation of shipping companies.

Ping Wu, Linxi Yang, Wangxin Li et al.

The challenging nature of nearshore tunnel construction environments introduces a multitude of potential hazards, consequently escalating the likelihood of incidents such as water influx. Existing construction safety risk management methodologies often depend on subjective experiences, leading to inconsistent reliability in assessment outcomes. The multifaceted nature of construction safety risk factors, their sources, and structures complicate the validation of these assessments, thus compromising their precision. Moreover, risk assessments generally occur pre-construction, leaving on-site personnel incapable of recommending pragmatic mitigation strategies based on real-time safety issues. To address these concerns, this paper introduces a construction safety risk assessment approach for nearshore tunnels based on multi-data fusion. In addressing the issue of temporal effectiveness when the conflict factor K in traditional Dempster–Shafer (DS) evidence theory nears infinity, the confidence Hellinger distance is incorporated for improvement. This is designed to accurately demonstrate the degree of conflict between two evidence chains. Subsequently, an integrated evaluation of construction safety risks for a specific nearshore tunnel in Ningbo is conducted through the calculation of similarity, support degree, and weight factors. Simultaneously, the Revit secondary development technology is utilized to visualize risk monitoring point warnings. The evaluation concludes that monitoring point K7+860 exhibits a level II risk, whereas other monitoring points maintain a normal status.