Search

Real-time and accurate detection of ships plays a vital role in ensuring navigation safety and ship supervision. Aiming at the problems of large parameters, large computation quantity, poor real-time performance, and high requirements for memory and computing power of the current ship detection model, this paper proposes a ship target detection algorithm MC-YOLOv5s based on YOLOv5s. First, the MobileNetV3-Small lightweight network is used to replace the original feature extraction backbone network of YOLOv5s to improve the detection speed of the algorithm. And then, a more efficient CNeB is designed based on the ConvNeXt-Block module of the ConvNeXt network to replace the original feature fusion module of YOLOv5s, which improves the spatial interaction ability of feature information and further reduces the complexity of the model. The experimental results obtained from the training and verification of the MC-YOLOv5s algorithm show that, compared with the original YOLOv5s algorithm, MC-YOLOv5s reduces the number of parameters by 6.98 MB and increases the mAP by about 3.4%. Even compared with other lightweight detection models, the improved model proposed in this paper still has better detection performance. The MC-YOLOv5s has been verified in the ship visual inspection and has great application potential. The code and models are publicly available at https://github.com/sakura994479727/datas. [ABSTRACT FROM AUTHOR]

Objective: In this paper, we propose a Sine chaos mapping-based improved sparrow search algorithm (SSA) to optimize the BP neural network for trajectory prediction of inland river vessels because of the problems of poor accuracy and easy trapping in local optimum in BP neural networks. Method: First, a standard BP model is constructed based on the AIS data of ships in the Yangtze River section. A Sine-BP model is built using Sine chaos mapping to assign neural network weights and thresholds. Finally, a Sine-SSA-BP model is built using the sparrow search algorithm (SSA) to solve the optimal solutions of the neural network weights and thresholds. Result: The Sine-SSA-BP model effectively improves the initialized population of uniform distribution, and reduces the problem that population intelligence algorithms tend to be premature. Conclusions: The test results show that the Sine-SSA-BP neural network has higher prediction accuracy and better stability than conventional LSTM and SVM, especially in the prediction of corners, which is in good agreement with the real ship navigation trajectory. [ABSTRACT FROM AUTHOR]

Turbulator with new shape is utilized in current research to improve thermal efficiency. Hybrid nanomaterial has been involved as carrier fluid and k–ɛ turbulence model was selected for modeling. Simplified equations were solved via FVM and outputs in terms of contours were presented. Stronger secondary eddy is a result of increasing in inlet velocity and revolution which can provide thinner boundary layer and increase temperature gradient but at cost of greater pressure drop. Due to better mixing of nanomaterial in greater Re, higher Nu can be achieved. Higher turbulent intensity can be obtained with insertion of turbulator and convective heat transfer improves. [ABSTRACT FROM AUTHOR]

It is interesting to investigate the number of nanoparticle (NP) and temperature effects on H2O/CuO nanofluid thermal conductivity and the atomic manner in a non-ideal microchannel. The outcomes of the physical features of these structures were supposed using molecular dynamic (MD) method and LAMMPS simulation package. For the study of dynamic properties of nanofluid microchannel system, parameters such as temperature profiles, velocity, density, and potential energy of H2O/CuO atomic structures were calculated. Furthermore, the thermal conductivity of these structures was estimated by the Green–Kubo method in the final step. This simulation shows that nanoparticle number is a crucial parameter in nanofluid movement in a microchannel. Theoretically, via adding CuO nanoparticle to H2O fluid, the maximum rate of velocity, density, temperature, and thermal conductivity of base fluid increases to 0.106 g cm−3, 29.810 A ps−1, 549.217 K, and 0.81 W mK−1 rates, respectively. Moreover, the temperature increase of Cu microchannel increases the rate of density, velocity, temperature, and thermal conductivity of CuO nanofluids. [ABSTRACT FROM AUTHOR]

The purpose of this study is to numerically investigate flow field and turbulent heat transfer of hybrid nanofluid, water–DWCNT–TiO2 in a two-dimensional rectangular channel with triangular and semicircular vortex generators with three different heights of 1, 2 and 3 mm. For numerically modeling this study, SIMPLEC algorithm was used. Therefore, initially, the geometry of channel and the grid points were generated, and then for solving the mathematical equations via finite volume method, ANSYS Fluent was used. The results indicate that with an increase in Reynolds number and volume fraction (φ) of nanoparticles, the average Nusselt number increases. Also, with an increase in the φ, the pressure loss in the channel increases. About the geometrical shape of the vortex generators, results indicate that with using the semicircular vortex generator, average Nusselt number is higher compared to that of triangular vortex generator. Also, by investigating the performance evaluation criteria of thermal–hydraulic, which is a criterion for comparing the positive effect of the Nusselt number increase with the negative effect of pressure drop, results indicate that this criterion is higher for the semicircular vortex generator. [ABSTRACT FROM AUTHOR]

In the present study, the molecular dynamics method is used to probe the aggregation phenomenon of hybrid nanoparticle within platinum microchannel with pyramidal barriers. In molecular dynamics simulations, argon atoms are described as base fluid particles and for the interaction between these atoms, we use Lennard-Jones potential, while the platinum–platinum and Al2O3 nanoparticles interactions are simulated applying the embedded atom method force field. To analyze the achieved simulation results, some physical parameters such as potential energy, temperature, and distance of nanoparticles center of mass are calculated. The results show external magnetic field decrease the aggregation phenomenon in nanoparticles. Numerically, by adding external magnetic field to simulation box, the COM distance of nanoparticles reaches to 2.7 Å and the aggregation time of nanoparticles changes from 1.7 to 2.3 ns. These appropriate effects of external magnetic field from our computational study can be used in the design of heat transfer applications. [ABSTRACT FROM AUTHOR]

This paper studies the generation of entropy and free convective heat transfer of Al2O3/water nanofluid in an inclined enclosure affected by a magnetic field considering radiation effects. There is a circular quadrant at temperature T h in the bottom section of the left wall of the enclosure. The right wall of enclosure is kept at a fixed temperature T c . The other walls are insulated. The governing equations for fluid flow are resolved using the algorithm of SIMPLE. The effect of variations of Rayleigh number (Ra), Hartmann number (Ha), the enclosure angle and concentration of nanoparticles (φ ) on the flow field, isothermal field, entropy field, Nusselt number (Nu), Bejan number (Be) and total generation of entropy is investigated. The results indicate that the Nu enhances by 160% and 40% by augmenting the Ra and decreasing the Ha, respectively. Be diminishes by enhancing the Ra and reducing the Ha. The maximum generation of entropy intensifies by 288% and 39% by augmenting the Ra and reducing the Ha, respectively. The highest average Nusselt umber ( Nu M ) and an overall generation of entropy occur at the inclination angle of 30°. [ABSTRACT FROM AUTHOR]

From the perspective of renewability and environmental pollution, biodiesels are appropriate alternatives to conventional diesel fuels due to their proper combustion behavior and atomization characteristics, which can be influenced by the viscosity as an essential factor. Therefore, the viscosity prediction would be of importance for blend of biodiesel/diesel fuels. For biodiesel/diesel mixtures, the blended viscosity has been predicted with numerous empirical correlations available in the literature. In this work, the viscosity of fuel mixtures was evaluated through Generalized regression neural network (GRNN), Radial Basis Neural Networks (RBFNN), Multi-Layer Perceptron Neural Network (MLPNN), and Cascade Feed-forward Neural Network (CFNN), based on various experimental data. These developed models were then compared in terms of predictive accuracy and available empirical correlations to select the best model. Finally, the proposed model was compared with the most prominent biodiesel viscosity models confirming that the developed model has been superior in predicting the value of viscosity for biodiesel blends with reported values of 0.9997 and 0.87% for parameters of the coefficient of determination (R2) and absolute average relative deviation (AARD%), respectively. • The viscosity of the biodiesel blends was predicted by ANN models. • The best ANN model was selected based on the statistical criteria of R2 and AARD%. • Excellent agreement between the actual data and calculated results was achieved. • Different ANN approaches were applied and compared with empirical correlations. [ABSTRACT FROM AUTHOR]

From the perspective of renewability and environmental pollution, biodiesels are appropriate alternatives to conventional diesel fuels due to their proper combustion behavior and atomization characteristics, which can be influenced by the viscosity as an essential factor. Therefore, the viscosity prediction would be of importance for blend of biodiesel/diesel fuels. For biodiesel/diesel mixtures, the blended viscosity has been predicted with numerous empirical correlations available in the literature. In this work, the viscosity of fuel mixtures was evaluated through Generalized regression neural network (GRNN), Radial Basis Neural Networks (RBFNN), Multi-Layer Perceptron Neural Network (MLPNN), and Cascade Feed-forward Neural Network (CFNN), based on various experimental data. These developed models were then compared in terms of predictive accuracy and available empirical correlations to select the best model. Finally, the proposed model was compared with the most prominent biodiesel viscosity models confirming that the developed model has been superior in predicting the value of viscosity for biodiesel blends with reported values of 0.9997 and 0.87% for parameters of the coefficient of determination (R2) and absolute average relative deviation (AARD%), respectively. • The viscosity of the biodiesel blends was predicted by ANN models. • The best ANN model was selected based on the statistical criteria of R2 and AARD%. • Excellent agreement between the actual data and calculated results was achieved. • Different ANN approaches were applied and compared with empirical correlations. [ABSTRACT FROM AUTHOR]

In this study, the rheological behavior of ethylene glycol (EG)-graphene nanosheet nanofluid is examined experimentally. The impacts of mass concentration of nanoparticles (0–5%), temperature (5–65 ° C) and shear rate (0–90 1 s) on the dynamic viscosity of EG-graphene nanofluid are examined. The obtained results showed that incorporating graphene nanoparticles into EG causes fluid behavior to change from Newtonian to power-law non-Newtonian. In addition, it was found that the dynamic viscosity of EG-graphene nanofluid augments by boosting nanoparticle concentration and decreasing temperature. Moreover, the regression technique is utilized to develop predictive correlations of consistency-index and power-law index of the power-law model. The results demonstrated that the R-squared value for the obtained correlations for consistency index and power-law index are 0.925and 0.982, respectively. Unlabelled Image • Rheological behaviour of EG-graphene nanofluid is evaluated experimentally. • Effects of nanoparticle concentration and temperature on the results are assessed. • Correlations are developed to predict the consistency index and power-law index. • The EG-graphene nanofluid follows the Newtonian and non-Newtonian behaviour. • R2 for the obtained correlations for m and n are respectively 0.925 and 0.982. [ABSTRACT FROM AUTHOR]

In current numerical investigation, irreversibility and energy transportation related to free convection though a porous wavy chamber was scrutinized. One of the essential factors in design of unit is irreversibility which should be minimized. The inner wavy surface acts as heat element and chamber is filled with hybrid nanomaterial. New correlations, contours and profiles are main kinds of outputs which achieved by employing CVFEM. As Ra augments, the magnitude of ψ max enhances which indicates higher convective mode, and better cooling rate of inner wall happens. At lowest Ra and Nhs, Nu declines about 57.2% and Be augments about 2.75% with augmenting Lorentz force. Nu becomes 7.5 times greater with growth of Ra when other variables are minimum. Be reduces about 2.49% with rise of Nhs at Ra⁎ = 5, Ha = 20. Portion of thermal irreversibility augments with impose of stronger magnetic field. Growth of Ra leads to domination of convective mode and hence inner wall become colder. Reduction impact of Nhs on Nu become more stronger when buoyancy force augments. In comparison with Ra , Nhs has no sensible impact on Be. [ABSTRACT FROM AUTHOR]

Suspending nanoparticles of ZnO/SiO 2 into the water/EG (70:30) has been performed to study the thermal conductivity (TC) behavior of the nanofluid in the temperature range 20 to 40° C. Homogeneous and stable nanofluid samples at solid volume fractions (φ) of 0.1, 0. 5, 1, 1.5, 2 and 2.5% have been prepared by means of two-step method. Base on the experimental measurements, adding nanoparticles improved the nanofluid k,. At higher temperatures, the greater effect of the solid volume fraction (φ) on TC enhancement has been observed. It is found that at higher volume fractions, there is more sensitivity of the TC to the temperature. However, adding nanoparticles improves the TC of the base fluid in the range of 1.34 to 23.32%. Finally, a regression-based correlation was proposed to calculate the thermal conductivity ratio (TCR). [ABSTRACT FROM AUTHOR]

• Evaluating effects of sonication time on thermal conductivity of Fe 3 O 4 -liquid paraffin nanofluid. • The sonication process is performed at seven temperatures in the range of 20 to 90 °C. • An excessive increase in sonication time can impair nanofluid stability. • Optimal sonication time is 3 h for this nanofluid. • Optimal sonication time is not a function of the temperature and nanoparticles volume fraction. In this study, the duration of sonication efficacy on the thermal conductivity of Fe 3 O 4 -liquid paraffin nanofluid is investigated. The nanofluid is produced at 0.005, 0.01, 0.015, 0.02, 0.025 and 0.03 vol concentrations by applying two-step method. The sonication process is performed in a temperature range of 20–90 °C. The duration of sonication seems to have two important effects: On the one hand, increasing the duration of sonication breaks the nanoparticles clusters, hence distributes the nanoparticles more uniformly which in turn rises thermal conductivity. On the other hand, an excessive increase in the duration of sonication can impair nanofluid stability. The results of experimental tests proved that the optimal duration of sonication is 3 h. The optimal duration of sonication is not dependent on the nanoparticles volume fraction (φ) and temperature. It was found that at the highest temperature and φ (90 °C , 0.03), the greatest thermal conductivity enhancement (28.49%) is obtained. In contrast, at the lowest temperature and φ (20 °C , 0.005) the lowest thermal conductivity enhancement was obtained (2.82%). [ABSTRACT FROM AUTHOR]

In this study, aqueous solution of CaCl 2 /SiO 2 nanoparticles has been used as a desiccant in a gas–liquid hollow fiber membrane (HFM) air dehumidifier contactor system. The heat and mass (H/M) transfer properties HFM energy exchanger with CaCl 2 /H 2 O-SiO 2 as desiccant solution studied experimentally for first time. Effects of different parameters on H/M transfer characteristics of system, including the nanoparticle concentration, liquid flow rate and liquid temperature were examined experimentally. The experiments arranged for desiccant temperatures of 20 °C and 26 °C, desiccant solutions of 0, 1%wt and 2%wt concentration and flow rates of 1.1, 1.25, 1.4 and 1.7 ml/s. The results indicated that the influence of particles on moisture removal rate is the greatest for the conditions of highest solution temperature and the highest particle. By introducing nanofluid solution as liquid desiccant in system the enhancing effect of reducing desiccant temperature on moisture removal lessens and declined to zero by increasing the solution flow rate with a high descending rate. For 2%wt nanoparticle concentration by 53% increase of absorbent flow rate, the value of temperature effectiveness reduced by 30%. This justifies adiabatic application of hollow fiber membrane systems with nanofluid desiccant. [ABSTRACT FROM AUTHOR]

Atmospheric pollution from maritime traffic is rising sharply and has brought great challenges to maritime management. The purpose of the study aims to establish a reliable approach to estimate the number of pollutants emitted by ships. The temporal, spatial and voluminal emission intensity of CO 2 , NO X , CO, NMVOC, PM 2.5 and SO 2 are investigated using the Ship Traffic Emission Assessment Model. Then, the inaccuracy of the Ship Traffic Emission Assessment Model is evaluated by calculating the emission fluctuations at switch points between different operation modes. The results revealed that ship speed could significantly affect the temporal, spatial and voluminal emission intensities of ships. Compared to temporal and voluminal emission, the intensity of spatial emission increases dramatically when the speed is close to 0. In addition, it was also shown that the Ship Traffic Emission Assessment Model induces an inaccuracy whenever the ship changes the operation mode. The research results provide guidance to plan the operation and management strategies to reduce pollutants from ships. • Ship emission is investigated using the STEAM model. • Temporal, spatial and voluminal emission intensities of ships are estimated. • The inaccuracy of the STEAM model is evaluated at switch points. • Ship emissions could be reduced by limiting the sailing speed. [ABSTRACT FROM AUTHOR]

Flow past a rotating cylinder is investigated using a two-dimensional discrete vortex simulation method in this study. The simplified Navier–Stokes equation is solved based on the relationship between the surface pressure gradient and the generated surface vortex strength. The Reynolds number based on the cylinder diameter and flow velocity is 105. The non-dimensional rotation rate, α (the ratio of the cylinder surface velocity and flow velocity), is varied between 0 and 19, and four different wake formations (vortex shedding, weak vortex shedding, wake, and rotating wake formations) have been derived by the imposed rotation. The relationship between the hydrodynamics and wake formation is illustrated. Under vortex shedding and weak vortex shedding formations, periodical hydrodynamics is induced. Under wake formation, no gap between the positive-vorticity and negative-vorticity layers results in the steady hydrodynamics. The separation of the rotating wake induces the huge fluctuation of hydrodynamics under rotating wake formation. These are significant for a flow control technique and for the design of ocean and civil engineering structures. With the increasing rotation rate, the variation of mean hydrodynamics has been discussed and the maximum mean hydrodynamics is considered to be decided by the rotation rate. According to these wake formations, the vortex shedding, weak vortex shedding, wake, and rotating wake areas are identified. Combining the initial, increasing, and equivalent areas for mean hydrodynamics, two different area-divisions have been conducted for mean hydrodynamics and the relationship between the two area-divisions has been illustrated. Finally, the disappearance of vortex shedding and variation of the Strouhal number have been discussed in detail. The critical value for the disappearance of vortex shedding is α ≈ 3.5, and the Strouhal number remains steady initially and then decreases. [ABSTRACT FROM AUTHOR]

In the petroleum industry, the transport of offshore crude oil via pipelines may suffer damage known as wax precipitation. This reduces the flow capacity of the crude oil, reducing its transport efficiency. Under extreme conditions, this may also result in serious damage to equipment. To help alleviate this problem, the petroleum transport and flow characteristics of offshore waxy crude oil in pipelines are investigated, together with the development of several options to help minimize wax precipitation. This paper reviews the current research status for reducing wax precipitation and enhancing crude oil flow in offshore pipelines. Specifically, reducing the viscosity of waxy crude oil, strengthening the process technology of the pipeline and the related flow mechanisms are each investigated. This paper also identifies and discusses areas of study that require further investigation. • Offshore crude oil wax deposition is generated by the precipitation of wax crystals in crude oil. • DRAs, PPD, microbial and hydrate inhibitor decrease the viscosity by reducing the generation of wax crystals. • Skin effect electrical heat tracing increase the temperature of pipeline internal to reduce wax deposition. • Inner wall coating reduces the flow resistance of pipe internal to enhance flows of crude oil. • Hernandez Model, Singh Model and Rygg Model describe the multiphase flow characteristics of crude oil in offshore oil pipelines. [ABSTRACT FROM AUTHOR]

Collision avoidance for unmanned surface vehicles (USVs) is significant for the fulfillment of autonomous navigation. Generally, classical collision-avoidance algorithms are proposed for relatively simple encounter situation, in this scenario only two USVs are stressed. Furthermore, to generate the rational manoeuvre operations, it is necessary that USVs should abide by International Regulations for Preventing Collision at Sea (COLREGS). However, COLREGS has not paid attention to rules for multi-USV collision-avoidance problem. Furthermore, those collision-avoidance rules in COLREGS have not been quantified for USVs. Following that, this paper utilizes deep reinforcement learning (DRL) algorithm to resolve collision-avoidance for USVs even in complex encounter situations. Within our DRL algorithm, related COLREGS is quantified properly and integrated into the DRL model, and then encounter situation of USVs is formulated as environmental observation value, accordingly a set of decision making is reached by decision-making neural network, and the reward function is designed for updating network parameters iteratively. Consequently, collision avoidance for USVs can be achieved eventually. By employing our DRL algorithm, collision avoidance for USVs under generous complex scenarios are resolved with the aid of corresponding intelligent decision-making operations. Simulation results verify the effectiveness of our DRL algorithm. [ABSTRACT FROM AUTHOR]

Abstract The shipping industry has valued wind energy in the last decades due to the global increasingly severe environmental situation. The sail-assisted vessels have employed generous types of sails to exploit wind energy and reduce the energy consumption. To meet the ever-increasing energy saving requirements of sail-assisted vessels, this paper investigates the hard sail design optimization and energy efficiency enhancement problems for sail-assisted vessel. By using parametric section airfoil parametrization (PARSEC) method and particle swarm optimization algorithm, we fulfill the optimization of the wingsail aerodynamic design. The performance of our optimized airfoil has been verified by multi-point theory, computational fluid dynamics (CFD) examination, and energy efficiency design index (EEDI) calculation. The maximum lift-to-drag ratio of the coupled wingsails has increased by 10 % than that of the arc-shaped sail. And the vessel equipped with our coupled wingsails can remarkably reduce EEDI by 18.2 % and 4 % when compared to non-sails vessel, and the vessel equipped with variable-camber sail (VCS), respectively. [ABSTRACT FROM AUTHOR]

With the growth of the shipping trade, inland water traffic is getting more prosperous than ever. Meanwhile, the shipping risk in inland rivers increases gradually. In this paper, a path planning model based on the safety potential field theory is proposed for inland ships from the perspective of navigation risk. Firstly, different navigation risks for inland ships are defined based on the safety potential field theory for three types of obstacles including static obstacles, dynamic obstacles and waterway bank walls. Secondly, different potential fields are used to quantify the different navigation risks. Then, the superposition field is formulated by summing the above three potential fields, and the spatial distribution of the safety potential field is obtained. Finally, the minimum navigation risk points on each cross section, which is perpendicular to the navigation direction, are selected to formulate the optimal path. In addition, a case study of overtaking scenario is conducted using the proposed model. The simulation results show that the model can effectively describe the navigation risk, which could be used to generate the optimal path for ships in inland rivers. This research is of great importance for ship navigation in inland rivers. • A ship path planning model is proposed based on navigation risks in inland rivers. • The navigation risk of ships is quantified based on safety potential field theory. • Navigation risks are distinguished for static obstacles, dynamic obstacles and waterway bank walls. • A case study of an overtaking scenario is conducted to verify the model. [ABSTRACT FROM AUTHOR]