Driven by global energy transition goals, the large-scale development of offshore wind power imposes rigid requirements for professionalism, standardization, and timeliness on feasibility study reports (FSR). Traditional manual compilation and existing automated methods fail to meet these requirements due to interdisciplinary complexity, poor process controllability, and insufficient domain adaptation. To address these challenges, this paper proposes a configurable and interpretable offshore wind FSR generation system built on a three-tier framework that encompasses “data support, process orchestration, and quality assurance”. The system integrates a YAML-based workflow architecture, multi-level prompt engineering, and a comprehensive evaluation system. Notably, the introduced “Cyclic Aggregation Mode” enables the iterative generation and logical summarization of multi-subproject data, effectively distinguishing this system from traditional linear text generation models. Experimental results demonstrate that the proposed “Retrieval-Augmented Generation (RAG) + Large-scale Language Model (LLM) + Workflow” system outperforms baseline models with key metrics including semantic consistency (0.6592), information coverage (0.3908), structural compliance (0.5123), and an overall score (0.5965). Ablation studies validate the independent contributions of the RAG and Workflow components, thereby establishing the “RAG + LLM + Workflow” paradigm for intelligent professional document generation. This work addresses core challenges related to controllability, accuracy, and interpretability in high-stakes decision-making scenarios while providing a reusable technical pathway for the automated feasibility demonstration of offshore wind power projects.
Marine renewable energy systems, particularly offshore wind and photovoltaic (PV) installations, generate large volumes of heterogeneous maintenance texts. However, the resulting knowledge remains fragmented due to dispersed sources, diverse formats, and domain-specific terminology. To address these challenges, this study proposes a large-scale language model assisted methodology for constructing a multi-source heterogeneous knowledge graph for intelligent operation and maintenance (O&M). The method integrates unified document preprocessing, domain-oriented prompt engineering, large-scale language model-based entity and relation extraction, and multi-level entity normalization. It systematically transforms unstructured documents (e.g., standards, procedures, manuals, inspection records, and environmental reports) into structured triples, enabling the construction of a dynamically evolving O&M knowledge graph. A rigorous ablation study on real-world offshore wind and PV datasets demonstrates that the proposed workflow exhibits exceptional robustness against OCR noise (e.g., scanned artifacts, stamps, and signatures) and substantially improves extraction volume, accuracy, and coverage compared with traditional methods. In particular, combining high-quality preprocessing and optimized prompts yields the most reliable and semantically coherent results. The study provides a practical technical pathway for automated knowledge management in marine renewable energy and offers a foundation for future applications in intelligent diagnostics, predictive maintenance, and digital-twin systems.
The objective of this study is to conduct a review of recycled-carbon-fibre (rCF) wind turbine blades’ feasibility, through a comparison of global and Australian wind sector waste, and a comparison of virgin-carbon-fibre (vCF) with rCF wind turbine blades’ greenhouse-gas GHG-emissions, and, recommend an approach for carbon-fibre CF-use in the fledgling Australian offshore wind industry, based on global-warning-potential GWP. This study assesses the life-cycle GHG-emissions of virgin-carbon-fibre wind turbine blades versus recycled-carbon-fibre wind turbine blades, in both non-structural and structural configurations. All production, use and recycling is assessed in terms of a West Australian context, in which the functional unit is three turbine blades used on an onshore wind farm, towards potential applicability for (as yet, non-existent) offshore WA fields. An approach incorporating a GaBi/Sphera database-study provides a timely screening/preliminary study, in which it was found that non-structural recycled carbon fibre wind turbine blades had very similar GHG emission levels compared to standard virgin carbon fibre blades, with sensitivity analysis revealing that in worst-case scenarios, non-structural carbon fibre has higher GHG emissions. Structurally recycled carbon fibre blades performed significantly better than standard virgin carbon fibre wind turbine blades with a 56% reduction in GHG emissions; savings were not affected significantly by parameter changes during sensitivity analysis. It is evident that recycled-carbon-fibre can significantly reduce wind turbine blades’ GWP and contribute to the circular economy in the fledgling West Australian offshore-wind-turbine sector.
Bucket foundations have been widely used in marine engineering, such as offshore wind power, due to their anti-overturning performance and convenient installation. In China’s coastal areas, clay soil is widely distributed, and most of the seabed has layered clay. However, the bearing capacity of bucket foundations in layered soil is significantly different from that in homogeneous soil. Currently, there is relatively little research on the bearing capacity of bucket foundations in layered clay. Therefore, the finite element analysis method is adopted to establish a bearing capacity calculation method of bucket foundations in double-layer clay. The axial failure mechanisms and ultimate bearing capacity of bucket foundations in double-layer clay are deeply discussed, and the corresponding ultimate bearing capacity calculation method is given based on the numerical analysis results. The combined bearing capacity of bucket foundations in double-layer clay is fully analyzed, and the evolution method of V-H, V-M, H-M, and V-H-M failure envelopes is given.
Ports, as key nodes for marine renewable energy consumption and integration with marine industries, are facing the dual pressures of low-carbon transformation and efficient energy utilization. To solve fossil fuel reliance and high carbon emissions from disconnected port berth scheduling and energy optimization, this study proposes a two-stage framework combining the improved Cuckoo Search Algorithm (ICSA) and Stackelberg game. In the first stage, a vessel-centric optimization framework is proposed, which integrates the time-of-use electricity pricing mechanism to coordinate ship operating decisions and port low-carbon objectives. The ICSA is employed to solve the low-carbon berth allocation problem, while synchronously generating the time-series load data of key port handling equipment. In the second stage, a demand response load matrix is established by fully exploiting the battery swapping characteristics of electric trucks and the cold load shifting capability of refrigerated containers. A tripartite Stackelberg game is then conducted among the port energy operator, distributed energy supplier, and port equipment aggregator to optimize energy pricing and multi-energy supply dynamically. Case studies show doubled shore power using vessels, 14% higher berth utilization, and 29.86% lower energy costs. Carbon emissions were significantly reduced, while the proportions of offshore natural gas and renewable energy saw notable increases. This study provides a new approach for the integration of marine energy into port operations, supporting the sustainable development of marine energy industries and the low-carbon transformation of coastal ports.
The Archimedes Screw hydrokinetic turbine (AST) is a promising technology for renewable energy generation in shallow, low-velocity, and bidirectional flows, but the mechanisms governing its torque production remain poorly understood. This study uses computational fluid dynamics (CFD) to investigate the performance and torque-generation mechanism of a three-flight AST inclined at 30° and operating in two configurations previously examined experimentally. Transient simulations were performed in ANSYS Fluent using a sliding mesh and flow-induced rotation approach within an unsteady Reynolds-averaged Navier-Stokes framework with the SST k-ω turbulence model. The results show that pressure forces dominate torque generation, while viscous contributions are comparatively small. Importantly, this behaviour is observed at a relatively low Reynolds number of approximately 4.5 × 104, indicating that Reynolds-number dependence becomes weak at Reynolds numbers substantially lower than those expected in practical deployments. For the first configuration, with the upstream edge of the turbine at the free surface, the CFD model predicted a maximum power coefficient of 0.85 at a tip speed ratio of 1.50, compared with an experimental value of 0.40 at 0.53. For the second configuration, with the downstream edge of the turbine at the free surface, the corresponding maximum power coefficient was 0.82 at a tip speed ratio of 1.51, compared with 0.34 at 0.54, as experimentally observed. The simulations also captured strong cyclic torque variations; the maximum variation in torque was over three times the mean value for both configurations. Comparison of the cavitation and pressure coefficients indicates little likelihood of cavitation at the experimental flow velocity but suggests possible cavitation onset at higher velocities.