Unscented Kalman Filter trained neural networks based rudder roll stabilization system for ship in waves

The large roll motion of ships sailing in the seaway is undesirable because it may lead to the seasickness of crew and unsafety of vessels and cargoes, thus it needs to be reduced. The aim of this study is to design a rudder roll stabilization system based on Radial Basis Function Neural Network (RBFNN) control algorithm for ship advancing in the seaway only through rudder actions. In the proposed stabilization system, the course keeping controller and the roll damping controller were accomplished by utilizing modified Unscented Kalman Filter (UKF) training algorithm, and implemented in parallel to maintain the orientation and reduce roll motion simultaneously. The nonlinear mathematical model, which includes manoeuvring characteristics and wave disturbances, was adopted to analyse ship’s responses. Various sailing states and the external wave disturbances were considered to validate the performance and robustness of the proposed roll stabilizer. The results indicate that the designed control system performs better than the Back Propagation (BP) neural networks based control system and conventional Proportional-Derivative (PD) based control system in terms of reducing roll motion for ship in waves.     

The application of the self-tuning neural network PID controller on the ship roll reduction in random waves

In this paper, we present a mathematical model including seakeeping and maneuvering characteristics to analyze the roll reduction for a ship traveling with the stabilizer fin in random waves. The self-tuning PID controller based on the neural network theory is applied to adjust optimal stabilizer fin angles to reduce the ship roll motion in waves. Two multilayer neural networks, including the system identification neural network (NN1) and the parameter self-tuning neural network (NN2), are adopted in the study. The present control technique can save the time for searching the optimal PID gains in any sea states. The simulation results show that the present developed self-tuning PID control scheme based on the neural network theory is indeed quite practical and sufficient for the ship roll reduction in the realistic sea.     

On the track keeping and roll reduction of the ship in random waves using different sliding mode controllers

In the paper, an autopilot system composed of sliding mode controller and line-of-sight guidance technique are adopted to navigate the ship in random waves by altering the rudder deflection. Two kinds of sliding mode controller are considered; one is the separate system including sway–yaw control and roll control, the other is the compact system considering sway–roll–yaw control altogether. Both track keeping and roll reduction are accomplished by rudder control and the design parameters of controller are optimized by genetic algorithm. The present simulation results show both the separate controller and the compact controller work quite well, either for track keeping or roll reduction while the ship is sailing in random waves. However, the separate controller is recommended due to its simplicity.     

基于深度学习和时空特征融合的海洋渔船密度预测方法

为了从海量渔船轨迹数据中挖掘隐含的信息和知识,进而为渔业行政主管部门的决策提供科学依据,本研究以AIS渔船轨迹数据为研究对象,提出了一种基于深度学习和面向时空特征融合的海洋渔船密度预测方法：首先,利用渔船轨迹数据集对渔船行驶区域进行网格划分;其次,筛选出渔船高密度区域进行研究,避免数据稀疏性问题;再次,根据渔船轨迹数据的时空分析,构建三维时空融合矩阵;最后,通过卷积循环神经网络模型捕获渔船分布的时间和空间特征,并利用卷积神经网络的堆叠加强对空间特征的学习。实验通过东海海域渔船真实轨迹数据进行具体测试,结果表明渔船密度预测值与真实值非常接近,平均绝对误差为4×10-4,模型较好地拟合了渔船密度分布特征,有效地提高了渔船捕捞热点预测的准确性和鲁棒性。     

An internal model control approach to the design ofyaw-rate-control ship-steering autopilot

This technical communication is concerned with the design of inland ship-steering autopilots characterized by turning rate regulation rather than heading regulation found on most ocean-going vessel autopilots. The autopilot design is based on the internal model control approach which allows clear connections between the controller structure and that of the ship model to be established. To fully utilize the limited rudder power without introducing the controller wind-up, which may lead to undesirable long transients, an inverse of the rudder saturation (SAT) and slew rate limitation (SRL) is implemented in the controller. Specifically, an inversion by feedback technique is employed by implementing the noninverted dynamics in a local feedback loop. This resolves the difficulty associated with inversion of the SAT and SRL mathematically. Consequently, high turning rate maneuver can be achieved in case of emergency encounters without causing the controller wind-up. This feature is particularly important for inland ships, since unexpected encounters with other ships are quite common and the capability of quick response is vital to ensure safe maneuvers     

Maneuvering performance of high-speed ships with effect of roll motion

Equations of yaw, sway, roll and rudder motions are formulated to represent realistic maneuvering behavior of high-speed ships such as destroyers. Important coupling terms between yaw, sway, roll and rudder were included on the basis of recent captive model test results of a high-speed ship. A series of computer runs was made by using equations of yaw, sway, roll and rudder motions. Results indicate substantial coupling effects between yaw, roll, and rudder, which introduce changes in maneuvering characteristics and reduce course stability in high-speed operation. These effects together with relatively small GM (which is typical for certain high-speed ships) produce large rolling motions in a seaway as frequently observed in actual operations. Results of digital simulations and captive model tests clearly indicate the major contributing factors to such excessive rolling motions at sea.     

Roll damping characteristics of a small fishing vessel with a central wing

The roll damping characteristics of three models of a 3-ton class fishing vessel representing the bare hull, hull with bilge keels, and hull with bilge keels and a central wing are investigated by the free roll decay tests in calm water and also in uniform head waves in a towing tank. Speed and roll initial angle and OG (distance between the centers of gravity and roll) are varied to check their dependence on roll damping. The experimental results are compared with the numerical results of mathematical modeling by the energy method and the energy dissipation patterns are also compared for these three models. The bilge keel contributes significantly to the increment of the roll damping for zero speed but as speed increases, the lift generated by the central wing contributes significantly to the roll damping increase. In addition, it is shown that the roll damping is more or less influenced by the regular head waves.     

Ant colony fuzzy neural network controller for cruising vessel on river

This paper proposes an ant colony fuzzy neural network (ACFNN) controller for a cruising vessel on a river. The proposed controller comprises an ant colony (AC) algorithm, a fuzzy neural network (FNN) controller, and a switching law. The approximately optimal sailing line and short sailing time are obtained using the AC algorithm. First, the searching pattern of the AC algorithm is constructed using the data of the tidal current, river current, vessel velocity, and position of the coordinate. From a tracking error viewpoint, the switching law determines that the approximately optimal sailing line and the shorter sailing time are obtained using the AC algorithm, and that uncertain nonlinear factors are compensated by the FNN controller. The controller consists of an FNN identifier and a robust controller. The identifier is used to estimate the vessel velocity, and its parameters are tuned online by the adaptive law derived from the Lyapunov function. The robust controller is used to compensate for uncertainties of the tidal current and river current through the estimated law. The output of the ACFNN controller is the sum of the FNN identifier, the robust controller, and an auxiliary function. Finally, a simulation and a practical cruising vessel on a river are performed to verify the effectiveness of the presented controller.     

Seakeeping performance of fishing vessels in irregular waves

A study of the seakeeping performance of a set of fishing vessels is carried out aiming to identify the seakeeping criteria, and vessel conditions that limit the operability of the fishing vessels in certain sea states. Ship motions and derived responses are obtained in fully developed sea states using the transfer functions of the hull forms. Those responses are assessed against the prescribed values, for the chosen criteria, to determine the vessels operational conditions that might result in hazards or seasickness. For the purpose of this study, each fishing vessel is considered operating in sea states 5 and 6, with different Froude numbers and heading angles, and their short term responses are assessed against the most relevant criteria related with the absolute and relative motions, accelerations, slamming and green water on deck. The results obtained show that roll and pitch criteria are most critical for seakeeping performance, and there is a significant influence of the transverse metacentric height, GMt, and the location of the reference checking points in the seakeeping performance of these fishing vessels.     

Analysis of roll motion and stability of a fishing vessel in head seas

The present paper describes an investigation on the relevance of parametric resonance for a typical fishing vessel in head seas. Results for different Froude numbers are discussed based on experimental, numerical and analytical studies.The first region of resonance is investigated. Distinct wave amplitudes are considered. Some intense resonances are found to occur. The paper compares the experimental results with non-linear time simulations of the roll motion. Very good agreement is found, even when large motions take place.Finally, in order to analyze the experimental/numerical results, analytic consideration is given to distinct parameters affecting the dynamic process of roll amplification. The influence of heave, pitch, wave passage effect, speed and roll restoring characteristics are discussed.     

Patterns in the spatial distribution of Peruvian anchovy (Engraulis ringens) revealed by spatially explicit fishing data

Peruvian anchovy (Engraulis ringens) stock abundance is tightly driven by the high and unpredictable variability of the Humboldt Current Ecosystem. Management of the fishery therefore cannot rely on mid- or long-term management policy alone but needs to be adaptive at relatively short time scales. Regular acoustic surveys are performed on the stock at intervals of 2 to 4 times a year, but there is a need for more time continuous monitoring indicators to ensure that management can respond at suitable time scales. Existing literature suggests that spatially explicit data on the location of fishing activities could be used as a proxy for target stock distribution. Spatially explicit commercial fishing data could therefore guide adaptive management decisions at shorter time scales than is possible through scientific stock surveys. In this study we therefore aim to (1) estimate the position of fishing operations for the entire fleet of Peruvian anchovy purse–seiners using the Peruvian satellite vessel monitoring system (VMS), and (2) quantify the extent to which the distribution of purse–seine sets describes anchovy distribution. To estimate fishing set positions from vessel tracks derived from VMS data we developed a methodology based on artificial neural networks (ANN) trained on a sample of fishing trips with known fishing set positions (exact fishing positions are known for approximately 1.5% of the fleet from an at-sea observer program). The ANN correctly identified 83% of the real fishing sets and largely outperformed comparative linear models. This network is then used to forecast fishing operations for those trips where no observers were onboard. To quantify the extent to which fishing set distribution was correlated to stock distribution we compared three metrics describing features of the distributions (the mean distance to the coast, the total area of distribution, and a clustering index) for concomitant acoustic survey observations and fishing set positions identified from VMS. For two of these metrics (mean distance to the coast and clustering index), fishing and survey data were significantly correlated. We conclude that the location of purse–seine fishing sets yields significant and valuable information on the distribution of the Peruvian anchovy stock and ultimately on its vulnerability to the fishery. For example, a high concentration of sets in the near coastal zone could potentially be used as a warning signal of high levels of stock vulnerability and trigger appropriate management measures aimed at reducing fishing effort.     

人工神经网络在潮位探测系统中的应用研究

叙述了人工神经网络算法在“Ku波段微波海洋波高/潮位探测系统”中的应用研究成果,介绍了检测微波回波信号中的中频信号和9/256点插值神经网络的设计方法及训练模型,并把这两个网络应用于探测系统,使系统波高/潮位的探测精度提高了1个数量级,还保证了监测的实时性,提出了某些减少训练时间的方法。     

Robust control based on feedback linearization for roll stabilizing of autonomous underwater vehicle under wave disturbances

In the case of Autonomous Underwater Vehicle(AUV) navigating with low speed near water surface,a new method for design of roll motion controller is proposed in order to restrain wave disturbance effectively and improve roll stabilizing performance.Robust control is applied,which is based on uncertain nonlinear horizontal motion model of AUV and the principle of zero speed fin stabilizer.Feedback linearization approach is used to transform the complex nonlinear system into a comparatively simple linear system.For parameter uncertainty of motion model,the controller is designed with mixed-sensitivity method based on H-infinity robust control theory.Simulation results show better robustness improved by this control method for roll stabilizing of AUV navigating near water surface.     

A data-driven method for optimal control of ship motions for safe crew transfer to offshore wind turbines

Due to uncertainties and random behavior of sea loads, presenting an accurate hydrodynamic analysis for motion control of offshore ships is a big challenge. This paper aims to propose a novel method for motion control of a crew transfer vessel (CTV) in order to ensure safe crew transfer to an offshore wind turbine (OWT). For this purpose, we propose a novel neural network observer-based optimal control (NOPC) scheme to tackle unknown dynamics and disturbances, nonlinear effects, and non-symmetric control input saturation constraints. Accordingly, the neural network (NN) structure addresses the Hamilton-Jacobi-Bellman (HJB) equation and forms an optimal control signal remaining in the saturation bounds. The Lyapunov theory guarantees the Ultimately Uniformly Boundedness (UUB) of all signals of the closed-loop system. The high performance of the presented method is demonstrated in regular waves with high frequency in comparison with the previous studies. It is worth mentioning that there are not any limitations to implement the adopted strategy for other offshore applications.     

Performance of a northwestern Mediterranean bottom trawl fleet: How the integration of landings and VMS data can contribute to the implementation of ecosystem-based fisheries management

The European Union has established a framework to achieve or maintain good environmental status in the marine environment by 2020. The Marine Strategy Framework Directive requires the application of the ecosystem approach to the management of human activities, covering all sectors having an impact on the marine environment. However, fisheries in the Mediterranean are far from a systematic implementation of an ecosystem-based fisheries management (EBFM). Aiming to address this issue, this study explores the potential of the relationship between daily yield by vessel (landings and income by species) and vessel position (known via vessel monitoring system) as a tool for fleet management. This approach is possible due to the current dynamics of Mediterranean fleets, with vessels returning daily to the harbour where landings are registered as weight and income by vessel. Moreover, vessels of >15 m total length have been compulsory monitored by VMS since 2005. A bottom trawl fleet that operates in the northwestern Mediterranean was chosen to develop this approach. Different groups of trawlers were identified, which could be linked to the strategies displayed by the fishermen that were mainly driven by the target species dynamics. Accurate knowledge of the fishing targets driving the fleet dynamics and of the fishing strategies at the vessel level (i.e. fishing ground habitat where the fishing pressure is exerted and corresponding landings) are shown to be a feasible tool for fleet management.     

基于BiLSTM模型的远洋渔船类型识别研究

船舶自动识别系统(Automatic identification system,AIS)为渔业资源和渔船捕捞活动管理和研究提供了可能.明确船舶作业类型是开展AIS信息渔业研究应用前提,为渔业研究和管理提供渔船捕捞类型基础数据支撑,保障渔船作业安全和监督非法捕捞渔业活动,作者通过搜集整理3000多艘已知类型船舶信息,从...     

Application of a vessel monitoring system to advance sustainable fisheries management—Benefits received in Taiwan

Vessel monitoring systems (VMS) are considered important instruments for fisheries monitoring, control and surveillance (MCS) to reverse the current depressed state of the world’s fisheries, and have been mandated worldwide by fishery management agencies. The essential function of the system is to provide near-real time vessel position; the potential applications could, however, be more than that. This study explores the additional benefits, with practical examples, that Taiwan has received from implementing the system: in improving the quantity and quality of logbooks recovered, obtaining access to fishery-independent fishing effort estimates and prompt catch/effort reporting, enabling the possibility of regional management and understanding of both fleet dynamics and vessel behavior, and increasing efficiency of vessel safety protection. For other distant-water fishing nations, Taiwan’s experiences serve to demonstrate how the application of VMS technology can advance sustainable fisheries management.     

Stability of small fishing vessels in longitudinal waves

The dynamic stability of fishing vessels in longitudinal regular waves is investigated, both analytically and experimentally. In particular, the influence of stern shape on the parametric stability of fishing vessels is studied. Vessels TS and RS have very similar main characteristics, but their sterns are different. Although their linear responses are comparable, both analytical and experimental investigations indicate substantial differences in their dynamic stability in longitudinal regular waves. Strong resonances are found for the vessel with the deep transom. The analytical method takes into consideration the effects of the heave and pitch motions and wave passage and shows good agreement with experimental results. Stability limits are obtained for different conditions and are used as an aid in the discussion of the results obtained in the tests when relevant parameters are changed, such as wave amplitude and frequency, metacentric height and roll damping moment.     

An assessment of fuzzy logic vessel path control

A fuzzy logic controller for ship path control in restricted waters is developed and evaluated. The controller uses inputs of heading, yaw rate, and lateral offset from the nominal track to produce a commanded rudder angle. Input variable fuzzification, fuzzy associative memory rules, and output set defuzzification are described. Two maneuvering situations are evaluated: track keeping along a specified path where linearized regulator control is valid; and larger maneuvers onto a specified path where nonlinear modeling and control are required. For the track keeping assessment, the controller is benchmarked against a conventional linear quadratic Gaussian (LQG) optimal controller and Kalman filter control system. The Kalman filter is used to produce the input state variable estimates for the fuzzy controller as well. An initial startup transient and regulator control performance with an external hydrodynamic disturbance are evaluated using linear model simulations of a crude oil tanker. A fully nonlinear maneuvering model for a smaller product tanker is used to assess the larger maneuvers     

海洋作业渔船管理系统的设计与运行试验

对渔政管理指挥系统建设项日中的业务软件部分渔船管理系统的设计方案进行了介绍。根据我国渔洋作业渔船的实际管理模式，提出了渔船管理系统设计方案。系统通过网络化的业务处理和管理流程，规范渔船建造、审批、登记以及捕捞许可证发放等管理业务，实现渔船控制指标的统一分配，以控制捕捞业发展规模和保护我国的渔业资源。系统以Microsoft VB6．0，Delphi6．0开发，在Window98／2000／XP环境下运行。通过运行试验，对系统运行环境进行了评估，为渔政管理信息化的建设、系统升级提供了经验和技术依据。