Precise underwater object detectors can provide Autonomous Underwater Vehicles (AUVs) with good situational awareness in underwater environments, supporting a wide range of unmanned exploration missions. However, the quality of optical imaging is often insufficient to support high detector accuracy due to poor lighting and the complexity of underwater environments. Therefore, this paper develops an efficient and precise object detector that maintains high recognition accuracy on degraded underwater images. We design a Cross Spatial Global Perceptual Attention (CSGPA) mechanism to achieve accurate recognition of target and background information. We then construct an Efficient Multi-Scale Weighting Feature Pyramid Network (EMWFPN) to eliminate computational redundancy and increase the model’s feature-representation ability. The proposed Occlusion-Robust Wavelet Network (ORWNet) enables the model to handle fine-grained frequency-domain information, enhancing robustness to occluded objects. Finally, EMASlideloss is introduced to alleviate sample-distribution imbalance in underwater datasets. Our architecture achieves 81.8% and 83.8% mAP on the DUO and UW6C datasets, respectively, with only 7.2 GFLOPs, outperforming baseline models and balancing detection precision with computational efficiency.
Offshore wind turbines positioned in deepwater areas are increasingly favored due to them providing superior and stable wind resources. However, the dynamic stability of floating offshore wind turbines (FOWTs) under complex environmental loading remains challenging. This study proposes a novel semi-submersible platform featuring a fractal structure inspired by the venation of Victoria Amazonica and investigates the effects of fractal branching level and biomimetic structural height on platform motions, with the aim of enhancing the overall system stability of FOWTs. Within a high-fidelity computational fluid dynamics (CFD) framework coupled with a dynamic fluid–body interaction (DFBI) model and a volume-of-fluid (VOF) wave model, the dynamic responses of the biomimetic platform are investigated under varying fractal dimensions (<i>D</i><sub>f</sub>) and structural heights. The results indicate that increasing fractal complexity enhances the local wall viscosity effect, significantly improving energy dissipation capabilities within the fractal cavities. Specifically, an eight-level fractal structure shows optimal performance, achieving reductions of approximately 16.94%, 23.26%, and 35.63% in heave, pitch, and rotational energy responses, respectively. Additionally, the increasing fractal height further strengthens energy dissipation, markedly enhancing stability, particularly in pitch motion. These findings underscore the substantial potential of biomimetic fractal designs in enhancing the dynamic stability of FOWTs.
Novel cross-media vehicles can operate efficiently in different media where water entry is a critical process. In this paper, a water–air cross-media unmanned vehicle is designed and its hydrodynamic characteristics during water entry are studied. With the use of STARCCM, the movement of the vehicle during water entry was simulated with the adoption of a VOF multiphase flow model and a Schnerr–Sauer cavitation model and its accuracy was tested. The flow field characteristics of the vehicle under common operating conditions, as well as the influence of the initial water entry speed and angle on the motion state and the force endured by the vehicle under different operating conditions, were simulated. The results show that the overall operating attitude of the vehicle is stable, and the influence of the water entry speed is more significant than that of the water entry angle. The research results provide a theoretical basis and technical support for the design and application of cross-media vehicles, helping to promote cross-media navigation technology.
Albert Kjartan Dagbjartarson Imsland, Pablo Balseiro, Sigurd Handeland
et al.
Acoustic lice treatment (AcuLice) is a newly developed system which uses a composite acoustic sound image with low-frequency sound to remove salmon lice (<i>Lepeophtheirus salmonis</i>) from Atlantic salmon (<i>Salmo salar</i>). The effect of AcuLice treatment on salmon lice dynamics was measured by weekly salmon lice counting at a full-scale production facility from mid-summer 2019 to late-spring 2024. We monitored four production cycles, with AcuLice applied for two of the production cycles and with no AcuLice treatment applied during the other two production cycles as control. This is a follow-up study to our previous work. The numbers of salmon lice treatments and of weeks until the first salmon lice treatment were also compared in the two experimental groups. For the small (sessile and mobile stages) salmon lice, a significantly lower number (mean ± SEM) was shown for the AcuLice group (0.73 ± 0.03) compared with the control group (1.18 ± 0.05). For the mature female salmon lice, a significantly lower number (mean ± SEM) was found for the AcuLice group (0.12 ± 0.01) compared with the control group (0.22 ± 0.03). In addition, the mean (±SEM) number of <i>C. elongatus</i> varied between the two experimental groups and was higher in the control group (0.12 ± 0.01) compared with the AcuLice group (0.03 ± 0.01). In addition, a lower number (mean ± SEM) of salmon lice treatments (1.4 ± 0.17 vs. 4.22 ± 0.20) and a longer production period before the first salmon lice treatment occurred was observed for the AcuLice group (11.2 ± 0.1 weeks) compared with the control group (24.1 ± 2.3 weeks). These data suggest that the use of the AcuLice system significantly reduces the number of salmon lice (by 40–60%) and <i>C. elongatus</i> (by 70%) on farmed Atlantic salmon and reduces the need for traditional salmon lice treatments (by 65%).
Mislav Maljković, Ivica Pavić, Toni Meštrović
et al.
The maneuverability of ships is influenced by several factors, including ship design, size, propulsion system, hull shape, and external conditions such as wind, waves, and currents. The size, shape, and arrangement of the hull, rudder, and propeller are decisive for maneuverability. Hydrodynamic forces such as bank effect and squat significantly impact the maneuverability of large ships in narrow channels. With the increasing trend of building ever-larger ships, the demand to evaluate the maneuvering performance of the ship at the design stage has become more critical than ever. Both experimental and computational methods are used to obtain accurate maneuvering characteristics of vessels. In this study, the methods for predicting ship maneuvering characteristics are analyzed using a systematic review based on the preferred reporting items for systematic reviews and meta-analyses (PRISMA). This article contributes to a deeper understanding of the hydrodynamic capabilities of ships and identifies possible future challenges in the field of ship hydrodynamics. The findings inform educators and the shipping industry about the importance of predicting the maneuvering performance of ships, with an emphasis on the education and training of seafarers needed to make timely decisions in critical situations.
This paper evaluates the contributing factors to maritime dangerous goods (DG) transport accidents by integrating the Entropy Weight (EW) and Grey Relational Analysis (GRA) methods. For this purpose, investigation reports of maritime DG transport accidents that occurred worldwide between 2000 and 2023 are derived from the International Maritime Organization’s Integrated Shipping Information System (IMO GISIS) database’s Marine Casualties and Incidents (MCI) module. Eleven main ship operations and thirteen primary causes were selected by analysing accident investigation reports. The weights of main ship operations are calculated utilizing the EW method. The correlational degrees of the primary causes are then calculated using the GRA method. Most maritime DG transport accidents occur during unberthing, bunkering, and pilotage operations. The most common contributing factors of maritime DG transport accidents are collisions and occupational accidents. Specifically, maritime DG transport accidents are most likely to be caused by collisions during sailing, passage, maneuvering, and bunkering operations, as well as occupational accidents during cargo loading, anchoring, berthing, and mooring operations. The results of this paper can support stakeholders in developing the needed policies to guarantee the safety of maritime DG transport.
Luca Micoli, Tommaso Coppola, Roberta Russo
et al.
This work focuses on the modeling of a zero-emissions, high-speed catamaran ferry employing a full-electric propulsion system. It addresses the global emphasis on full-electric vessels to align with IMO regulations regarding ship emissions and energy efficiency improvement. Using the AVL Cruise-M software, this research verified the implementation of an onboard fuel cell power-generating system integrated with a propulsion plant, aiming to assess its dynamic performance under load variations. The catamaran was 30 m long and 10 m wide with a cruise speed of 20 knots. The power system consisted of a proton-exchange membrane fuel cell (PEM) system, with a nominal power of 1600 kWe, a battery pack with a capacity of 2 kWh, two 777 kW electric motors, and their relative balance of the plant (BoP) subsystems. The simulation results show that the battery effectively supported the PEM during the maneuvering phase, enhancing its overall performance and energy economy.
Marikka Heikkilä, Heidi Himmanen, Olli Soininen
et al.
The maritime industry is rapidly evolving with digital technologies, aiming to enhance efficiency, safety, and sustainability. Recent interest has focused on autonomous vessels and the digitalization of ports, yet fairway development has lagged behind. To effectively support the growing digital and autonomous marine traffic, it is essential that fairways are also upgraded and modernized. Addressing this need, this study examines key elements of Smart Fairways, with a particular focus on Finland’s maritime infrastructure. This research contributes to the development of the Smart Fairways concept by identifying five foundational and ten advanced Smart Fairway service elements. The main finding highlights the foundational role of communication systems in the development of more advanced Smart Fairway services such as Enhanced Vessel Traffic Service, Port just-in-time Service, Remote Pilotage, and Digital Twin of the Physical Fairway.
Jingqian Guo, Lingshuai Meng, Mengmeng Feng
et al.
The widespread use of Unmanned Underwater Vehicles (UUVs) in seafloor observatory networks highlights the need for docking stations to facilitate rapid recharging and effective data transfer. Floating docks are promising due to their flexibility, ease of deployment, and recoverability. To enhance understanding and optimize UUV docking with floating docks, we employ dynamic fluid body interaction (DFBI) to construct a seabed moored suspended dock (SMSD) model that features a guiding funnel, a suspended body, and a catenary of a mooring chain. This model simulates SMSD equilibrium stabilization in various ocean currents. Then, a UUV docking model with contact coupling is developed from the SMSD model to simulate the dynamic contact response during docking. The accuracy of the docking model was validated using previous experimental data. Through investigation of the UUV docking response results, sensitivity studies relating to volume, moment of inertia, mass, and catenary stiffness were conducted, thereby guiding SMSD optimization. Finally, sea tests demonstrated that the SMSD maintained stability before docking. During docking, the SMSD’s rotation facilitated smooth UUV entry. After the UUV docked, the SMSD was restored to its original azimuth, confirming its adaptability, stability, and reliability.