Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

Assessment of offshore liquid hydrogen production from wind power for ship refueling

Green hydrogen from electrolysis has become the most attractive energy carrier for making the transition from fossil fuels to carbon-free energy sources possible. Especially in the naval sector, hydrogen has the potential to address environmental targets due to the lack of low-carbon fuel options. This study aims at investigating an offshore liquefied green hydrogen production plant for ship refueling. The plant comprises a wind farm for renewable electricity generation, an electrolyzer stack for hydrogen production, a water treatment unit for demineralized water production, and a hydrogen liquefaction plant for hydrogen storage and distribution to ships. A pre-feasibility study is addressed to find the optimal capacities of the plant that minimize the payback time. The model results show that the electrolyzer capacity shall be set equal to a value between 80% and 90% of the wind farm capacity to achieve the minimum payback times. Additionally, the wind farm capacity shall be higher than about 150 MW to limit the payback time to values lower than 11 years for a fixed hydrogen price of 6 €/kg. The Levelized Cost of Hydrogen results to be below 4 €/kg for a wide range of plant capacities for a lifetime of the plant of 25 years. Thus, the model shows that this plant is economically feasible and can be reproduced similarly for different locations by rescaling the different selected technologies. In this way, the naval sector can be decarbonized thanks to a new infrastructure for the production and refueling of liquified green hydrogen directly provided on the sea.     

Multi-innovation auto-constructed least squares identification for 4 DOF ship manoeuvring modelling with full-scale trial data

This research is concerned with the problem of 4 degrees of freedom (DOF) ship manoeuvring identification modelling with the full-scale trial data. To avoid the multi-innovation matrix inversion in the conventional multi-innovation least squares (MILS) algorithm, a new transformed multi-innovation least squares (TMILS) algorithm is first developed by virtue of the coupling identification concept. And much effort is made to guarantee the uniformly ultimate convergence. Furthermore, the auto-constructed TMILS scheme is derived for the ship manoeuvring motion identification by combination with a statistic index. Comparing with the existing results, the proposed scheme has the significant computational advantage and is able to estimate the model structure. The illustrative examples demonstrate the effectiveness of the proposed algorithm, especially including the identification application with full-scale trial data.     

Multi-objective optimization of hybrid PEMFC/Li-ion battery propulsion systems for small and medium size ferries

Hybrid Polymer Electrolyte Membrane Fuel Cells/Lithium-ion battery powertrains are a promising solution for zero-local-emissions marine propulsion. The present study aims to optimize the design and operation of such hybrid powertrain for small-size passenger ferries, taking into account the performance degradation of both fuel cells and batteries. A Mixed-Integer Linear-Programming approach and a hierarchical method are adopted to concurrently minimize the fuel cells degradation, the capital expenditure and the operating expenditure, while constraints are included in the model to limit the battery degradation. The results show that the proposed multi-objective optimization can lead to a reduction of fuel cells degradation by up to 65% compared to a cost-minimization only. However, this can imply an increase in the battery capacity by up to 136%. The proposed method has general validity, and it is a useful tool for both preliminary design and choice of the optimal energy management strategy for ships energy systems.     

Fast and stable operation approach of ship solid oxide fuel cell-gas turbine hybrid system under uncertain factors

This work focuses on investigating the adaptability of solid oxide fuel cell-gas turbine (SOFC-GT) hybrid system for ship application under uncertain factors. The effect of rapids, wind and waves on the performance of ship SOFC-GT is analyzed. In addition, a novel control system combining fuzzy logic theory, temperature feedforward and coordination factor on-line adjustment is proposed to address the problem of load disturbances caused by uncertain factors. The results show that the proposed operation strategy can shorten the thermal response time inside fuel cell stacks by almost 49.97%, meanwhile, reducing the maximum temperature changing rate at the electrochemically active tri-layer cell composed of anode, electrolyte, and cathode (PEN structure) by around 17.86%. Moreover, the reasonable matching between air flow and fuel flow is an essential prerequisite to ensure the safe and efficient operation of ship SOFC-GT. While the SOFC-GT is working at full load, the results indicate that the fuel to air ratio cannot exceed 2.56?10^?2 g/g. Finally, an application scenario of the 5000-ton river-to-sea cargo ship sails from Nanjing Port to Yangshan Port (Eastern China) is conducted to analyze the operation characteristics of ship SOFC-GT under uncertain factors. Two set of 1000 kW SOFC-GT systems with the electrical efficiency of 64.66% is designed for the target ship, the results conclude that the operation strategy of each SOFC-GT system supports 50% load is beneficial in reducing the power tracking time and SOFC temperature overshoot. The average electrical efficiency of 61.45% and 61.04% are achieved in winter and summer typical days respectively in the whole voyage.     

船舶交通管理系统雷达电磁辐射环境影响分析评价

根据船舶交通管理系统雷达的工作模式及技术参数, 计算了雷达天线轴向电场强度及磁场强度瞬时峰值和平均场强的分布;分析了电磁辐射环境影响;根据国家有关技术标准的规定, 给出了船舶交通管理系统雷达天线的水平和垂直达标距离;为雷达站选址与建设提供技术依据。     

Motion sickness and motion characteristics of vessels at sea

Measurements of vessel motion and consequent seasickness amongst passengers have been made on six ships, two hovercraft and a hydrofoil. Data are presented for 20 029 passengers surveyed on 114 voyages involving 370?hours of motion recordings. Vomiting incidence and illness rating were found to be linearly related to the root-mean-square magnitude of the vertical z-axis acceleration. Sickness increased with increasing duration of exposure and a measure of motion ‘dose’ is examined as a convenient way of combining the variables of stimulus magnitude and duration. High frequency motion in hovercraft at about 0·6?Hz was found to be less provoking of sickness than similar magnitudes at lower frequencies. Motion in axes other than the vertical correlated less highly with sickness, although there was some intercorrelation between axes. The results presented enable predictions to be made of seasickness occurrence in marine vessels and other forms of transport where low frequency vertical oscillations are encountered.     

A finite element analysis of ship sections subjected to underwater explosion

This paper presents numerical simulations of dynamic responses of a ship section to non-contact underwater explosion using ABAQUS. The finite element model of the ship section including the size of fluid mesh, initial and boundary conditions etc. has been built up. Comparisons of the acceleration and velocity response between the experimental and numerical results have been investigated. The numerical results agree well with the measured results. Furthermore, the effect of the mass proportional damping factor on the velocity response have been investigated numerically. The dynamic response modes of the ship section subjected to a side-on non-contact underwater explosion are discussed.     

Five decades of Computer-Aided Ship Design

This article will present a synoptical review of key developments in Computer-Aided Ship Design since its inception about five decades ago. Milestone events and major innovations will be identified in several categories of ship design application with the principal emphasis on the methodologies, the modeling and the integration of the ship design process. The discussion will address many specific subtasks of ship design on the common platform of a human-guided, computer-based decision process.     

长江上游城市航道船舶噪声控制装置的研制与应用

由于船舶噪声对城市环境和人民群众生活的影响日益突出,城市航道船舶噪声污染已成为长江上游多个城市急需解决的社会焦点问题。为控制船舶噪声,在现场监测和走访调查基础上,从降低声源噪声和控制噪声传播途径着手,采取了设计制作船用隔声装置控制船舶机械噪声的方法,并同时解决了柴油机的进气和散热问题,以减小对机组功率的影响。经理论研究、设计计算、实验分析和应用测试,结果表明:研制出的长江上游船用隔声装置具有良好的噪声控制效果。