Neural adaptive robust control of underactuated marine surface vehicles with input saturation

This paper proposes a saturated tracking controller for underactuated autonomous marine surface vehicles with limited torque. First, a second-order open-loop error dynamic model is developed in the actuated degrees of freedom to simplify the design procedure. Then, a saturated tracking controller is designed by utilizing generalized saturation functions to reduce the risk of actuator saturation. This, in turn, improves the transient performance of the control system. A multi-layer neural network and adaptive robust control techniques are also employed to preserve the controller robustness against unmodeled dynamics and environmental disturbances induced by waves and ocean currents. A Lyapunov stability analysis shows that all signals of the closed-loop system are bounded and tracking errors are semi-globally uniformly ultimately bounded. Finally, simulation results are provided for a hovercraft vehicle to illustrate the effectiveness of the proposed controller as a qualified candidate for real implementations in offshore applications.     

NNFFC-adaptive output feedback trajectory tracking control for a surface ship at high speed

An adaptive output feedback controller based on neural network feedback-feedforward compensator (NNFFC) which drives a surface ship at high speed to track a desired trajectory is designed. The tracking problem of the surface ship at low speed has been widely investigated. However, the coupling interactions among the forces from each degree of freedom (DOF) have not been considered in general. Furthermore, the influence of the hydrodynamic damping is also simplified into a linear form or neglected. On the contrary, coupling interactions and the nonlinear characteristics of the hydrodynamic damping can never be neglected in high speed maneuvering situation. For these reasons, the influence of the nonlinear hydrodynamic damping on the tracking precision is considered in this paper. Since the hydrodynamic coefficients of the surface ship at high speed are very difficult to be accurately estimated as a prior, it will be compensated by NNFFC as an unknown part of the tracking dynamics system. The stability analysis will be given by the Lyapunov theory. It indicates that the proposed control scheme can guarantee that all the signals in the closed-loop system are uniformly ultimately bounded (UUB), and numerical simulations can illustrate the excellent tracking performance of the surface ship at high speed under the proposed control scheme.     

Robust adaptive control of underactuated ships on a linear course with comfort

This paper addresses an important problem in ship control application—the robust stabilization of underactuated ships on a linear course with comfort. Specifically, we develop a multivariable controller to stabilize ocean surface ships without a sway actuator on a linear course and to reduce roll and pitch simultaneously. The controller adapts to unknown parameters of the ship and constant environmental disturbances induced by wave, ocean current and wind. It is also robust to time-varying environmental disturbances, time-varying change in ship parameters and other motions of the ship such as surge and heave. The roll and pitch can be made arbitrarily small while the heading angle and sway are kept to be in reasonably small bounds. The controller development is based on Lyapunov’s direct method and backstepping technique. A Lipschitz continuous projection algorithm is used to update the estimate of the unknown parameters to avoid the parameters’ drift due to time-varying environmental disturbances. Simulations on a full-scale catamaran illustrate the effectiveness of our proposed controller.     

基于分布式控制力矩陀螺的水下航行器轨迹跟踪控制

基于控制力矩陀螺群(CMGs)的水下航行器具有低速或零速机动的能力。采用基于分布式CMGs的水下航行器方案,并研究其水平面的轨迹跟踪控制问题。通过全局微分同胚变换将非完全对称的动力学模型解耦成标准欠驱动控制模型,并根据简化的模型构建其轨迹跟踪的误差动力学模型,将轨迹跟踪控制问题转化为误差模型镇定问题。基于一种分流神经元模型和反步法设计了系统的轨迹跟踪控制律,该控制器不需要对任何虚拟控制输入进行求导计算,且能确保跟踪误差的最终一致有界性。仿真结果表明该控制器能够实现在不依赖动力学参数先验知识的情况下对光滑轨迹的有效跟踪。     

Reliability analysis of H-infinity control for a container ship in way-point tracking

Efficient control of ships in a designed trajectory is always a significant charge for ship maneuverings. The purpose of this paper is to design a robust H_∞ controller and a reliability analysis for a container ship in a way-point tracking. First, the H_∞ controller is designed for a container ship because of model parameters’ uncertainties and external disturbances such as waves, winds and ocean currents. Then, to evaluate the reliability of the designed controller, a well-known reliability analysis technique is employed to achieve the predefined heading angle overshoot (that is less than 20%) in way-point tracking. To do this, three random variables including wind speed, wind direction and wave direction are considered as the inputs due to their significant effect on overshoot, compared to other variables. The results demonstrate the capability of the designed H_∞ controller against modeling uncertainties and external disturbances in way point tracking control.     

Neural Network Based Robust Controller for Trajectory Tracking of Underwater Vehicles

A robust neural network controller (NNC) is presented for tracking control of underwater vehicles with uncertainties. The controller is obtained by using backstepping technique and Lyapunov function design in combination with neural network identification. Modeling errors and environmental disturbances are considered in the mathematical model. A two-layer neural network is introduced to compensate the modeling errors, while H∞ control strategy is used to achieve the L2-gain performance. The uniformly ultimately bounded (UUB) stabilities of tracking errors and NN weights are guaranteed through the proposed controller. An on-line NN weights tuning algorithm is also proposed. Good performances of the tracking control system are illustrated by the results of numerical simulations.     

基于LSTM的海洋表面短期风速预测研究

为实现对海面风速精确的短期预测,提出了一种基于长短期记忆(LSTM,longshort-termmemory)神经网络的短期风速预测模型,选取OceanSITES数据库中单个浮标站点采集的风速历史数据作为模型输入,经过训练设置最佳参数等步骤,实现了以LSTM方法,对该站点所在海区海面风速在各季节性代表月份海面风速的24 h短期预测。同时通过不同预测时长的实验以及与BP(back propagation)神经网络神经网络和径向基函数神经网络(radialbasisfunctionneuralnetwork,RBF)的预测效果对比实验,证明了LSTM预测方法相比上述两种神经网络预测方法,在海表面风速预测应用中的优越性。最后通过多个海域对应的站点风速数据预测实验,证明了LSTM神经网络模型的普遍适用性,由相关系数和预测误差的分析可知该方法具备应对急剧变化数据的预测稳定性,可以作为海洋表面风速短期预测的一种可靠方法。     

全新世以来泰国湾古气候演化历史———来自地球化学和矿物学证据

为了对海表温度(SeaSurfaceTemperature,SST)和海表盐度(SeaSurfaceSalinity,SSS)数据进行精确的短期预报,基于多站位海洋观测浮标获取的海表温度和海表盐度数据,利用反向传播(BackPropagation,BP)和径向基函数(RadialBasisFunction,RBF)两种神经网络方法开展了短期预测。首先,在预测时长固定为5d的情况下,对比不同训练时长的预测结果的均方误差(MeanSquaredError,MSE),进而确定以20d的观测数据作为训练集的预测结果均方误差最小。然后,以 PAPA 站观测浮标获取的2009年1月、4月、7月和10月各月的前20d温盐数据作为训练集,分别训练BP和 RBF神经网络,将训练好的2种神经网络模型应用于各月第21至25日的温盐数据预测。结果表明:BP和 RBF神经网络均能有效预测海表温盐数据的季节性变化,但 RBF神经网络对不同预测时间的整体预测效果优于 BP神经网络。多站点数据的预测实验进一步验证了 RBF神经网络模型具有较强适用性和更高的准确性。RBF神经网络模型可以作为海表温盐数据短期预报的有力工具。     

无人船运动控制方法综述

为实现无人船海上自主作业,无人船运动控制的快速性、准确性以及鲁棒性亟待提高。首先从全驱动控制和欠驱动控制角度,分别概括了国内外无人船航向控制、航速控制、轨迹跟踪控制以及路径跟踪控制的主流控制方法。其次,归纳总结了处理海洋环境不确定扰动的研究进展,包括扰动的建模和消除、抑制扰动的主流方法。最后,总结了无人船运动控制现状与存在的问题,并从工程应用和理论研究两个角度对未来的研究方向进行了展望。     

基于深度学习的海温观测数据质量控制应用研究

基于国家海洋信息中心质量控制后的西太平洋10度方区约100万站次温盐实测历史调查资料,对经过26种严格质量控制方法的综合海温质量符进行分类分析,首次将深度学习技术应用于海洋数据质量控制多分类(multiclass classification)算法与应用研究.通过人工合成少数类样本和加权损失函数方法减少多数类的频率来降...     

Layered berthing method and experiment of unmanned surface vehicle based on multiple constraints analysis

Considering the dynamic changes of unmanned surface vehicle (USV) in berthing tasks, the planning and control modes are divided into two phases: the remote phase and the terminal phase. According to the main influencing factors of the two phases, an improved artificial potential field method is proposed to complete autonomous berthing trajectory planning based on the analysis of environment constraint, berth point constraint and USV’s dynamics constraint. Combining with the dynamic characteristics and control objectives at different phases of berthing and analyzing the fuzzy rule regulation strategy of USV’s heading and speed control, an improved adaptive fuzzy PID control method is proposed to solve the control problem of USV, which is influenced by weak maneuver, large disturbance, limited water area and strong shore effect. Finally, the comparative test of berthing simulation verifies the superiority of the proposed control method. The autonomous berthing field experiment is completed based on the "Dolphin-I" small USV. It verifies the validity and feasibility of the proposed autonomous berthing method.     

端口受控哈密顿方法的电力双推进无人船航向航速控制

以电力双推进无人船航速航向控制为主要研究问题,使用永磁同步电机作为无人船螺旋桨的驱动电机,采用基于端口受控哈密顿(PCH)方法,有效的降低了系统损耗,使无人船驱动系统输出功率得到了优化。仿真结果表明,系统能较快达到稳定状态,实现了无人船的速度控制要求,提升了无人船系统的续航能力。     

包含温度因子的海水地球物理模型函数建模研究

以SeaWinds散射计为例,利用其L2A卫星测量数据和相应的海面浮标测量数据,以温度作为独立变量,借助人工神经网络首次尝试建立了包含温度因子的海水地球物理模型函数。建模实验结果表明,在3—15m.s-1风速范围内,对于两种极化方式,后向散射系数先随温度的升高而增大,当风速大于某一数值后,又随温度的升高而减小,但两种极化方式的转折风速存在差异。该研究结果为海面微波散射机理认识的进一步深入和模型函数精度的进一步提高展示了潜在的可能途径。     

基于雷达高度计增益自动控制数据的风速反演算法研究

基于Jason-1卫星雷达高度计与NDBC(National Data Buoy Center)浮标的时空匹配数据集,利用BP(Back Propagation)神经网络方法建立了基于后向散射系数σ₀与有效波高(Significant Wave Height,SWH,)的双参数(σ₀-H_sw)风速反演模型,并探讨利用AGC(Automatic Gain Control)来代替σ₀对风速反演的可行性进行研究。结果表明,所建立的σ₀-SWH风速反演均方根优于0.3 m/s(风速范围为0.5~20 m/s); AGC-SWH模型反演精度偏低(1.3 m/s),但在星星交叉定标的基础上,模型精度提高了0.9 m/s。这个研究工作尤其是交叉定标基础上的AGC-SWH模型反演流程对"HY-2"海面风速反演有一定的借鉴意义。     

基于观测和再分析数据的LSTM深度神经网络沿海风速预报应用研究

基于海洋气象历史观测资料和再分析数据等,利用LSTM深度神经网络方法,开展在有监督学习情况下的海面风场短时预报应用研究。以中国近海5个代表站为研究区域,通过气象台站观测数据和ERA-Interim 6 h再分析数据构建数据集。选取21个变量作为预报因子,分别构建两个LSTM深度神经网络框架(OBS_LSTM和ALL_LSTM)。经与2017年WRF模式6 h预报结果对比分析,得出如下结论:构建的两个LSTM风速预报模型可以大幅降低风速预报误差,RMSE分别降低了41.3%和38.8%,MAE平均降低了43.0%和40.0%;风速误差统计和极端大风分析发现,LSTM模型能够抓住地形、短时大风和台风等敏感信息,对于大风过程预报结果明显优于WRF模式;两种LSTM模型对比发现,ALL_LSTM模型风速预报误差最小,具有很好的稳定性和鲁棒性,OBS_LSTM模型应用范围更广泛。     

台湾海峡及其邻近海域表层水叶绿素α含量时空变化特征

从物理过程和营养输送方面讨论了2006～2007年台湾海峡及其邻近海域表层水叶绿素口含量的时空变化特征及其调控因素．结果表明,台湾海峡表层水体从南至北叶绿素。含量的季节变化存在着明显差异．在北部海区叶绿素口含量平均值以春季居高,冬季最低;中部海区以秋季最高,夏季最低;南部较反常,以冬季最高,夏季最低．浙闽沿岸流、海峡暖流及上升流所造成的营养盐输入方式的差异可能是决定海峡叶绿素口含量季节分布南北差异的关键因素．分析结果还表明,春、夏季叶绿素口含量的分布在南部和北部海域均主要受营养盐限制,秋季叶绿素口含量在南部和北部海域分别主要受到磷酸盐含量和水温的影响,冬季叶绿素α含量在南部和北部海域分别主要受到硝酸盐含量和水温的影响．     

Bias correction of sea surface temperature retrospective fore-casts in the South China Sea

Offline bias correction of numerical marine forecast products is an effective post-processing means to improve forecast accuracy. Two offline bias correction methods for sea surface temperature(SST) forecasts have been developed in this study: a backpropagation neural network(BPNN) algorithm, and a hybrid algorithm of empirical orthogonal function(EOF) analysis and BPNN(named EOF-BPNN). The performances of these two methods are validated using bias correction experiments implemented in the South...     

Sea surface temperature retrieval based on simulated microwave polarimetric measurements of a one-dimensional synthetic aperture microwave radiometer

Compared with traditional real aperture microwave radiometers, one-dimensional synthetic aperture microwave radiometers have higher spatial resolution. In this paper, we proposed to retrieve sea surface temperature using a one-dimensional synthetic aperture microwave radiometer that operates at frequencies of 6.9 GHz, 10.65 GHz,18.7 GHz and 23.8 GHz at multiple incidence angles. We used the ERA5 reanalysis data provided by the European Centre for Medium-Range Weather Forecasts and a radiation transmission forward model to calculate the model brightness temperature. The brightness temperature measured by the spaceborne one-dimensional synthetic aperture microwave radiometer was simulated by adding Gaussian noise to the model brightness temperature.Then, a backpropagation(BP) neural network algorithm, a random forest(RF) algorithm and two multiple linear regression algorithms(RE1 and RE2) were developed to retrieve sea surface temperature from the measured brightness temperature within the incidence angle range of 0°–65°. The results show that the retrieval errors of the four algorithms increase with the increasing Gaussian noise. The BP achieves the lowest retrieval errors at all incidence angles. The retrieval error of the RE1 and RE2 decrease first and then increase with the incidence angle and the retrieval error of the RF is contrary to that of RE1 and RE2.     

Sedimentary control on the formation of a multi-superimposed gas system in the development of key layers in the sequence framework

Based on core observations, well logs and test results of siderite-bearing mudstone from the Benxi Formation to the Member 2 of the Shanxi Formations in the Linxing block, northeastern Ordos Basin, a logging identification model for siderite-bearing mudstone (key layer) was established. The porosity characteristics and sealing property were quantitatively evaluated by logging data. Sedimentary control on the formation of multi-superimposed gas-bearing system in the development of key layers in the sequence framework was also discussed. The results showed that the siderite-bearing mudstone has obvious logging response characteristics, e.g., high photoelectric absorption cross-section index (PE), high density (DEN), high amplitude natural gamma ray (GR), low acoustic (AC), low resistivity (M2RX) and low neutron porosity (CNCF). The quantitatively evaluated results of the porosity characteristics and sealing property for the key layer showed that the key layer has the characteristics of low porosity (with an average of 1.20 percent), low permeability (with an average of 2.29 × 10⁻⁸μm²), and high breakthrough pressure (with an average of 12.32 MPa) in the study area. This layer acts as an impermeable gas barrier in a multi-superimposed gas system. The results also indicated that the material composition of the multi-superimposed gas-bearing system can be established by the sequence stratigraphic framework. The sedimentary evolution results in a cyclic rhythm of material composition vertically. The spatial distribution of the corresponding transgressive event layer near the maximum flooding surface (MFS) in the sequence framework restricts the spatial distribution of the key layer with high breakthrough pressure and low porosity, which constitutes the gas-bearing system boundary. The siderite-bearing mudstone formed near the MFS in the second-order sequence and constitutes a stable comparison of the first-order gas-bearing system boundary, which has a wide range of regional distribution and stable thickness. The siderite-bearing mudstone formed near the MFS in the third-order sequence is often incompletely preserved due to the late (underwater) diversion channel erosion and cutting. This layer forms the coal-bearing reservoirs, which we termed as a second-order gas-bearing system in adjacent third-order sequences to form a uniform gas-bearing system.