无人艇建模及逻辑网络自适应控制方法的研究
|
摘要
近年来,无人水面艇(USV)凭借其体积小、灵活性好、航速高、无人员伤亡等优势,受到了学者们的广泛关注。由于USV的高阶性、非线性、强耦合和强不确定性,建立较为精确的动力学模型具有很大难度。此外受到海风、海浪及其他干扰的影响,USV会产生六自由度的复杂运动,具有很强的随机性和非线性,产生了传统控制手段难以快速精确控制的问题。有效的运动控制系统对提高侦察设备观测效果、武器装备系统精度都是十分重要的。海洋环境的高度动态和不可预测使USV的控制能力需要加强,其控制系统还应具有良好的自适应、自学习能力,从而需要采用先进的控制策略,才能得到满意的操纵性能。智能自适应控制方法非常适用于解决这类问题。本文针对以上问题,研究USV的数学建模以及自适应控制方法,主要工作可概括为以下几个方面：
分析USV在坐标系中的运动和动力学特性,讨论作用在USV上的各种力和力矩,建立USV六个自由度上的数学模型。采用MMG分离型机理建模方法,在Abkowitz模型的基础上把水动力分解为作用在船体、螺旋桨和舵上的三部分,并充分考虑各部分之间的相互干扰影响。
研究LFN逻辑网络理论技术及在USV控制系统中的应用。提出一种LFN逻辑网络结构,并给出其相应的学习算法。采用统一神经元AND_U和OR U作为LFN网络的基本运算单元。以该LFN网络为基础,同时结合Line-of-sight算法,提出基于LFN网络的航迹控制系统。该逻辑网络可以融合先验知识,并且训练结果可以直接转化为复合模糊规则语句。网络采用混合优化策略。网络结构动态优化首先用遗传算法寻找最小的网络结构,再用修剪法进行调整。在参数优化方面,采用梯度法和粒子群算法相结合的混合算法。结合船舶与海洋工程研究的特点和要求,将设计的控制系统置于不同的海洋环境条件下,以Matlab/Simulink为平台进行数字仿真实验。仿真结果表明该方案的有效性。
提出一种基于支持向量回归(SVR)算法和反馈线性化理论的自适应逆控制器,研究该控制器在USV控制系统中的应用。以自适应逆控制基本理论为出发点,采用SVR在线自适应辨识算法建立被控对象的逆模型。首先研究基于SVR的USV自适应逆航向控制方法,再进一步研究简化的航迹模型,结合输入输出反馈线性化理论思想,通过逆动态模型和逆误差补偿项的离线辨识,将辨识的逆模型作为控制器,提出基于反馈线性化SVR方法的航迹自适应逆控制系统。并以Matlab/Simulink为平台进行的数字仿真实验。仿真结果可以得出,该控制方案为解决无人水面艇运动控制问题提供了一个有效的途径。
In recent years, more and more attention has been paid on unmanned surface vehicles (USV) with advantages of small volume, good flexibility, high speed and no casualties. Because of high order, nonlinear, strong coupling and high uncertainties, it is difficult to derive an accurate dynamic model of USV. Furthermore, the six degrees of freedom (DOF) motion model of USV has strong randomicity and nonlinearity under wind, waves and other disturbances, which make it difficult to control using traditional control methods. Efficient control systems are very important to improve the observation effect of reconnaissance equipment and the precision of the weaponry system. The USV control system needs to strengthen its control ability, self-study and self-adaptive abilities for highly dynamic and unpredictable marine environment. Therefore advanced control strategies are kind of need to get satisfactory maneuvering performance. Intelligent control methods are suitable to solve these problems. This dissertation investigates mathematical modeling method and adaptive control methods of USV to slove the above problems. The main work of this study includes the following aspects:
The six DOF model of USV is derived in detail by analyzing all the hydrodynamic forces and moments on the USV including environment wind and wave disturbances. This dissertation adopts the MMG modeling method, in which the hydrodynamics are decomposed into three parts that are hull, propeller and rudder, with adequate consideration of mutual interference.
Logic-based fuzzy networks (LFN) and their application in USV control system are implemented. A five layer LFN framework is established using AND_U and OR_U unineurons. Combined with the line-of-sight guidance method, a design of USV path following system is presented based on the LFN. With prior domain knowledge, the training results can be easily interpreted and directly translated into a series of logic expressions formed over a collection of information granules. Hybrid learning strategies are used in this study. Firstly genetic algorithm is used to minimize the network structure, and then pruning algorithm is adpoted to adjust the structure. Gradient-based learning and paticle swarm optimizition algorithms are used in parameter optimization. Considering the characteristics and requirements of the ship and ocean engineering, numerical simulations are conducted on Matlab/Simulink software under several ocean environmental conditions. The simulation results demonstrate the effectiveness of the proposed approach.
An adaptive controller with combinations of online SVR algorithm and feedback linearization theory is proposed for USV. Starting from adaptive inverse control, an online adaptive SVR algorithm is adopted to identify the control plant's inverse model. The adaptive USV heading control system is presented. Besides that, using simplified track models, a SVR adaptive control method based on feedback linearization for USV track control system is proposed. The identificated inverse model is used as a controller, and adaptive inverse track control system is established through off-line identification of the inverse dynamic model and compensation of inverse error. Using matlab/simulink as the digital simulation tool, numerical simulations are conducted. The simulation results demonstrate that the proposed algorithm provides an alternate effecitive way for USV motion control.
分析USV在坐标系中的运动和动力学特性,讨论作用在USV上的各种力和力矩,建立USV六个自由度上的数学模型。采用MMG分离型机理建模方法,在Abkowitz模型的基础上把水动力分解为作用在船体、螺旋桨和舵上的三部分,并充分考虑各部分之间的相互干扰影响。
研究LFN逻辑网络理论技术及在USV控制系统中的应用。提出一种LFN逻辑网络结构,并给出其相应的学习算法。采用统一神经元AND_U和OR U作为LFN网络的基本运算单元。以该LFN网络为基础,同时结合Line-of-sight算法,提出基于LFN网络的航迹控制系统。该逻辑网络可以融合先验知识,并且训练结果可以直接转化为复合模糊规则语句。网络采用混合优化策略。网络结构动态优化首先用遗传算法寻找最小的网络结构,再用修剪法进行调整。在参数优化方面,采用梯度法和粒子群算法相结合的混合算法。结合船舶与海洋工程研究的特点和要求,将设计的控制系统置于不同的海洋环境条件下,以Matlab/Simulink为平台进行数字仿真实验。仿真结果表明该方案的有效性。
提出一种基于支持向量回归(SVR)算法和反馈线性化理论的自适应逆控制器,研究该控制器在USV控制系统中的应用。以自适应逆控制基本理论为出发点,采用SVR在线自适应辨识算法建立被控对象的逆模型。首先研究基于SVR的USV自适应逆航向控制方法,再进一步研究简化的航迹模型,结合输入输出反馈线性化理论思想,通过逆动态模型和逆误差补偿项的离线辨识,将辨识的逆模型作为控制器,提出基于反馈线性化SVR方法的航迹自适应逆控制系统。并以Matlab/Simulink为平台进行的数字仿真实验。仿真结果可以得出,该控制方案为解决无人水面艇运动控制问题提供了一个有效的途径。
In recent years, more and more attention has been paid on unmanned surface vehicles (USV) with advantages of small volume, good flexibility, high speed and no casualties. Because of high order, nonlinear, strong coupling and high uncertainties, it is difficult to derive an accurate dynamic model of USV. Furthermore, the six degrees of freedom (DOF) motion model of USV has strong randomicity and nonlinearity under wind, waves and other disturbances, which make it difficult to control using traditional control methods. Efficient control systems are very important to improve the observation effect of reconnaissance equipment and the precision of the weaponry system. The USV control system needs to strengthen its control ability, self-study and self-adaptive abilities for highly dynamic and unpredictable marine environment. Therefore advanced control strategies are kind of need to get satisfactory maneuvering performance. Intelligent control methods are suitable to solve these problems. This dissertation investigates mathematical modeling method and adaptive control methods of USV to slove the above problems. The main work of this study includes the following aspects:
The six DOF model of USV is derived in detail by analyzing all the hydrodynamic forces and moments on the USV including environment wind and wave disturbances. This dissertation adopts the MMG modeling method, in which the hydrodynamics are decomposed into three parts that are hull, propeller and rudder, with adequate consideration of mutual interference.
Logic-based fuzzy networks (LFN) and their application in USV control system are implemented. A five layer LFN framework is established using AND_U and OR_U unineurons. Combined with the line-of-sight guidance method, a design of USV path following system is presented based on the LFN. With prior domain knowledge, the training results can be easily interpreted and directly translated into a series of logic expressions formed over a collection of information granules. Hybrid learning strategies are used in this study. Firstly genetic algorithm is used to minimize the network structure, and then pruning algorithm is adpoted to adjust the structure. Gradient-based learning and paticle swarm optimizition algorithms are used in parameter optimization. Considering the characteristics and requirements of the ship and ocean engineering, numerical simulations are conducted on Matlab/Simulink software under several ocean environmental conditions. The simulation results demonstrate the effectiveness of the proposed approach.
An adaptive controller with combinations of online SVR algorithm and feedback linearization theory is proposed for USV. Starting from adaptive inverse control, an online adaptive SVR algorithm is adopted to identify the control plant's inverse model. The adaptive USV heading control system is presented. Besides that, using simplified track models, a SVR adaptive control method based on feedback linearization for USV track control system is proposed. The identificated inverse model is used as a controller, and adaptive inverse track control system is established through off-line identification of the inverse dynamic model and compensation of inverse error. Using matlab/simulink as the digital simulation tool, numerical simulations are conducted. The simulation results demonstrate that the proposed algorithm provides an alternate effecitive way for USV motion control.
引文
[1]吴恭兴.水面智能高速无人艇的控制与仿真：(硕士学位论文).哈尔滨：哈尔滨工程大学,2008.
[2]吴恭兴.无人艇操纵性与智能控制技术研究：(博士学位论文).哈尔滨：哈尔滨工程大学,2010.
[3]高双.高速无人艇的建模与控制仿真：(硕士学位论文).哈尔滨：哈尔滨工程大学,2007.
[4]邱健.致命幽灵—美法联合发展水面无人艇项目.国际展望.2005,2：52-55.
[5]况小梅.水面高速无人艇的概念设计研究：(硕士学位论文).哈尔滨：哈尔滨工程大学,2007.
[6]杨星.船舶结构与设备.武汉：武汉理工大学出版社,2007.
[7]Witt N A J, Miller K M. An adaptive track keeping neural network controller for ship guidance. Proc. Impact of New Technol. on the Marine Industries, Southhampton, U.K.,1993:13-15.
[8]Burns R S. The use of artificial neural networks for the intelligent optimal control of surface ships. IEEE J. Oceanic Eng.1995,2:65-72.
[9]Zhang Y, Hearn G E, Sen P. A Neural Network Approach to Ship Track-Keeping Control. IEEE journal of oceanic engineering.1996,21(4):513-527.
[10]赵邦良,张尧.人工神经网络在船舶自动舵上的应用.华东船舶工业学院学报.1998,12(6)：36-47.
[11]林叶锦,任光.遗传优化的径向基函数船舶模糊控制器.控制理论与应用.2004,21(6)：1036-1040.
[12]陈鸶鹭,程海边.基于模糊神经网络控制的水面无人艇建模与仿真.舰船科学技术.2010,32(11)：134-136.
[13]宋佳,刘胜,李高云.船舶航向最小二乘支持向量机内模控制.电机与控制学报.2009,13(增1)：183-187.
[14]刘胜,宋佳,李高云.船舶保持鲁棒最小二乘支持向量机控制.控制与决策.2010,25(4)：551-561.
[15]张元涛,石为人,李建立,等.基于反馈线性化的船舶自动舵模糊滑模控制.系统仿真学报.2010,22(10)：2337-2341.
[16]曾薄文,朱齐丹,于瑞亭.欠驱动水面船舶的曲线航迹跟踪控制.哈尔滨工程大学学报. 2011,32(10)：1317-1322.
[17]汀洋.基于动态神经模糊模型的欠驱动水面船舶控制：(博士学位论文).大连：大连海事大学,2010.
[18]廖煌雷,庄佳园,李晔,等.欠驱动无人艇轨迹跟踪的滑模控制方法.应用科学学报.2011,29(4)：428-434.
[19]廖煜雷,庞永杰,庄佳园.喷水推进型无人艇航向跟踪的反步自适应滑模控制.计算机应用研究.2012,29(1)：82-84.
[20]Toussaint G J, Basar T, Bullo F. Tracking for Nonlinear Underactuated Surface Vessels with Generalized Forces. Proc. IEEE Conf. Control Applications, Anchorage, Alaska USA,2000:355-360.
[21]Do K D, Jiang Z P, pan J. Robust Global Output Feedback Stabilization of Underactuated Ships on a Linear course. Proc.41 IEEE Conf. Decision and Control, Las Vegas, Nevada USA,2002:1687-1692.
[22]Pettersen K Y, Nijmeijer H. Global Practical Stabilization and Tracking for An Underactuated Ship-A Combined Averaging and Backstepping Approach. Proc.IFAC Conf. System Structure and Control, Nantes, France,1998:59-64.
[23]Pettersen K Y, Lefeber E. Way-Point Tracking control of ships. Proc.40th IEEE Conf. on Decision and Control, Orlando, Florida USA,2001:940-945.
[24]李铁山,杨盐生,郑云峰.不完全驱动船舶航迹控制输入输出线性化设计.系统工程与电子技术.2004,26(7)：945-980.
[25]周岗,姚琼荟,陈永冰,等.不完全驱动船舶直线航迹控制稳定性研究.自动化学报.2007,33(4)：378-384.
[26]翟传润.船舶智能自适应航迹舵的研究：(博士后士学位论文).上海：上海交通大学,2002.
[27]Reyhanoglu M. Exponential Stabilization of an Underactuated Autonomous Surface Vessel. Automatica.1997,33(12):2249-2254.
[28]Godhhavn J M, Fossen T I, Berge S P. Nonlinear and Adaptive Backstepping Designs for Tracking Control of Ships. Int.J. Adapt. Control Signal Processing.1998(12):649-670.
[29]Pettersen K Y, Nijmeijer H. Underactuated Ship Tracking Control:Theory and Experiments. Int. J. Control.2001,74(14):1435-1446.
[30]Gopalswamy S, Hedrick J K. Tracking Nonlinear Non-Minimum Phase Systems Using Sliding Mode. Int. J. Control.1993,57:1141-1158.
[31]Do K D, Jiang Z P, Pan J. Underactuated Ship Global Tracking under Relaxed Conditions. IEEE Trans. on Automat. Control.2002,47(9):1529-1536.
[32]Do K D, Jiang Z P, Pan J. Robust Global Stabilization of Underactuated Ships on a Linear Course:State and Output Feedback. Int. J. Control.2003,76(1):1-17.
[33]周岗,姚琼荟,陈永冰,等.基于输入输出线性化的船舶全局直线航迹控制.控制理论与应用.2007,24(1)：117-121.
[34]孙巧梅,任光.基于自适应SVR逆方法的无人艇航向控制.中国航海.2012,35(4)：17-21.
[35]孙巧梅,任光.基于输入输出线性化SVR的船舶航迹控制.中国造船.2012,53(4)：91-99.
[36]侯媛彬,杜京义,汪梅.神经网络.西安：西安电子科技大学出版社,2007.
[37]Ragazzini J R, Zadeh L A. The analysis of sampled-data systems. AIEE transactions, 1952,71:225-234.
[38]Nyquist H. Regeneration theory. The bell system technical journal,1932,11: 126-147.
[39]Evans W. R. Control system synthesis by root locus method. AIEE Transactions, 1950,69:66-69.
[40]Brockett R. W., Willems J. L.. Frequency domain stability criteria-part Ⅰ. IEEE Transactions on Automatic Control.1965, AC-10:255-261.
[41]Kalman R E. When is a linear control system optimal? Journal of basic engineering, 1964,86:51-60.
[42]Zadeh L A. Fuzzy sets. Information and Control,1965,8:338-353.
[43]Zadeh L A. Fuzzy logic, neural networks and soft computing. Communication. ACM, 1994,37(3):77-84.
[44]Lin C T, Lee C S G. Neural Fuzzy Systems:a Neuro-Fuzzy Synergism to Intelligent Systems. Englewood Cliffs, NJ:Prentice Hall,1996.
[45]Nauck D, Klawonn F, Kruse R. Foundations of Neuro-Fuzzy Systems. New York:Wiley, 1997.
[46]Cheng C H, Hsu C F, Lin C M, et al. Fuzzy-neural sliding-mode control for DC-DC converters using asymmetric Gaussian membership functions. IEEE Trans. Ind. Electron. 2007,54:1528-1536.
[47]Da F, Song W. Fuzzy neural networks for direct adaptive control. IEEE Trans. Ind. Electron.2003,50:507-513.
[48]Wang C H, Lin T C, Lee T T, et al. Adapti ve hybrid intelligent control for uncertain nonlinear dynamical systems. IEEE Trans. Syst. Man Cybern.2002, Part B 32:583-597.
[49]Sui J H, Yu G Z, Zhang W X. A ship motion control system design based on AND-OR Fuzzy neural networks. Proceedings of the 2007 IEEE International Conference on Robotics and Biomimetics. Sanya, China,2007:1194-1199.
[50]Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks,1989,2(2):359-366.
[5l]Lin F J, Lin C H, Shen P H. Self-constructing fuzzy neural network speed control ler for permanent-magnet synchronous motor drive. IEEE Trans. Fuzzy Syst.2001,9: 751-759.
[52]Mar J, Lin F J. An ANFIS controller for the car-following collision prevention system. IEEE Trans. Veh. Technol.2001,50:1106-1113.
[53]Lin C J. A GA-based neural fuzzy system for temperature control. Fuzzy Sets Syst. 2004,143:311-333.
[54]Lin C T, Lee C S G. Neural-network-based fuzzy logic control and decision. IEEE Transactions on computer.1991,40(12):1320-1336.
[55]Keller J M, Yager R R, Tahani H. Neural network implementation of fuzzy logic. Fuzzy Sets and Systems.1992,45 (1):1-12.
[56]Yager R R.OWA neurons:A new class of fuzzy neurons. International Joint Conference on Neural Networks,1992:226-230.
[57]Pedrycz W, Reformat M. Genetical ly optimized logic models. Fuzzy Sets and Systems. 2005,150(2):351-371.
[58]隋江华AND-OR模糊神经网络研究及在船舶控制中的应用：(博士学位论文).大连：大连海事大学,2006.
[59]Pedrycz W. Fuzzy equalization in the construction of fuzzy sets. Fuzzy Sets and systems.2001,119(2):329-335.
[60]Pedryez W, Reformat M. Rule-based Modeling of Nonlinear Relationships. IEEE Transactions on Fuzzy Systems.1997,5(2):26-269.
[61]Hirota K, Pedrycz W. OR/AND Neuron in Modeling Fuzzy Set Connective. IEEE Transactions on Fuzzy Systems.1994,2(2):151-161.
[62]隋江华,任光.模糊AND-OR神经网络优化建模方法.广西师范大学学报.2006,24(4)：111-114.
[63]Pedrycz W, Aliev R A. Logic-oriented neural networks for fuzzy neurocomputing. Neurocomputing.2009,73:10-23.
[64]Liang X, Pedrycz W. Logic-based fuzzy networks:A study in system modeling with triangular norms and uninorms. fuzzy sets and systems.160 (2009):3475-3502.
[65]肖健梅,柯玉波,王锡淮.基于支持向量机的非线性系统逆控制.中南大学学报(自然科学版).2007,38：319-323.
[66]Sun Q M, Ren G, Yue J et al. SVM inverse model-based heading control of unmanned surface vehicle.2010 IEEE Youth Conference on Information, Computing and Telecommunications. Beijing,2010:138-141.
[67]袁小芳,王耀南,孙炜.支持向量机-模糊推理自学习控制器设计.控制理论与应用.2006,23(1)：1-6.
[68]何峻峰,张曾科.基于支持向量机的逆系统离散控制方法.清华大学学报.2005,45(1)：100-106.
[69]Chan W C, Chan C W, Cheung K C. On the modelling of nonlinear dynamic system using support vector neural networks. Engineering Applications of Artificial Intelligence, 2001,14(2):105-113.
[70]Rojo-alvarez J L, Martinez-Ramon M, de Prado-Cumplido M. Support Vector Method for Robust ARMA System Identification.IEEE Transactions on Signal Processing.2004, 52(1):155-164.
[71]Suykens J A K, Vandewalle J, De Moor B. Optimal control by least squares support machines. Neural Networks.2001,14(1):23-35.
[72]王定成,方廷健.一种基于支持向量机的内模控制方法.控制理论与应用.2004,21(1)：85-88.
[73]Cao L J, Tay Francis E H. Support Vector Machine with Adaptive Parameters in Financial Time Series Forecasting.IEEE Transactions on Neural Networks.2003,14(6): 1506-1518.
[74]Wang H, Pi D, Sun Y. Online SVM regression algorithm-based adaptive inverse control Nerocomputing.2007,70:952-959.
[75]陈进东,潘丰.基于在线支持向量机的非线性内模控制.计算机工程与应用.2009,45(9)：18-20.
[76]Sun Q M,Ren G. An online adaptive neural approach for tracking control. Ocean Engineering.2013,58:106-114.
[77]张秀凤,尹勇,金一丞.规则波中船舶运动六自由度数学模型.交通运输工程学报.2007,7(3)：40-43.
[78]陈立家.海上多目标船智能避碰辅助决策研究：(博士学位论文).武汉：武汉理工大学2011.
[79]贾欣乐,杨盐生.船舶运动数学模型——机理建模与辨识建模.大连：大连海事大学.1999.
[80]Van Amerongen. Adaptive Steering of Ships-A Model Reference Approach to Improved Manoeuvring and Economical Course-Keeping:(PhD Thesis).The Netherlands:Delft University Of Technology,1982.
[81]Buekley J J, Silar W. A new t-Norm. Fuzzy Sets and Systems.1998,16(1):283-290.
[82]Mesiar R. A note on moderate growth of t-conorms. Fuzzy Sets and Systems.2001, 122(2):357-359.
[83]Wygralak M. Fuzzy Sets with triangular norms and their cardinality theory. Fuzzy Sets and Systems.2001,124(1):1-24.
[84]鲁斌.逻辑神经元研究综述.微机发展.2005,15(11)：131-138.
[85]Glorennec Pierre-Uves. Neuro-fuzzy logic. Proc IEEE-FUZZ. New Orleans,1996:512-518.
[86]陈丹,何华灿,王晖.一种新的基于弱T范数簇的神经元模型.计算机学报.2001,24(10)：1115-1120.
[87]Buekley J.J. et al. On the equivalence of neural nets and fuzzy expert systems Fuzzy sets and systems 100 supplement.1999:145-150.
[88]陈星,刁永峰.三值逻辑神经元模型及推理.湖州师范学院学报.2004,26(2)：59-62.
[89]杨钟瑾,史忠科.神经网络结构优化方法.计算机工程与应用.2004.25(15)：52-54.
[90]米凯利维茨Z.演化程序——遗传算法与数据编码的结合.北京：科学出版社,2000.
[91]张火明,杨松林,朱仁庆,等.船舶航行性能优化的模糊遗传算法.中国造船.2002,43(3)：7-15.
[92]Lin W M, Yang C D,Tsay M T. Distribution system planning with evolutionary programming and a reliability cost model. Generation, Transmission & Distribution. 2000,147(60):361-366.
[93]乔俊匕,韩红桂.RBF神经网络的结构动态优化设计.自动化学报.2010,36(6)：865-872.
[94]Wieman C E, Adams W K, Perkins K K. PhET:Simulations That Enhance Learning. Science,2008,322:682-683.
[95]O'Reilly R C. Biologically Based Computational Models of High-Level Cognition. Science,2006,314:91-94.
[96]Marchiori D, Warglien M. Predicting Human Interactive Learning by Regret-Driven Neural Networks. Science,2008,319:1111-1113.
[97]Michael D. Cohen. Learning with Regret. Science,2008,319:1052-1053.
[98]任光,孙巧梅,齐小伟.交互学习神经网络模型及其仿真研究.系统仿真学报.2009,21(17)：5314-5317.
[99]Sun Q M, Ren G, Qi X. Interactive learning neural networks for predicting game behavior. Lecture Notes in Computer Science.2009, LNCS 5551 (Part Ⅰ):774-783.
[100]张丹,李长河.基于混沌的粒子群优化算法研究与进展.软件导刊.2007,11：109-110.
[101]Perez T, Ross A, Fossen T I. A 4-dof Simulink model of a coastal patrol vessel for manoeuvring in waves.7th IFAC Conference on Manoeuveing and Control of Marine Vessels MCMC,2006.
[102]Moreira L, Fossen T I, Soares G C. Path following control system for a tanker ship model. Ocean Engineering.2007(34):2074-2085.
[103]Fossen, T. I. Marine control systems. Trondheim, Norway:Marine Cybernetics,2002.
[104]Morten Breivik. Nonlinear Maneuvering Control of Underactuated Ships:Master of science thesis. Norway:Norwegion University of Science and Technology,2003.
[105]Vapnik V N. The nature of statistical learning theory. NewYork:Springer-Verlag, 1999.
[106]何丹玉.支持向量机逆系统控制方法的研究与应用：(硕士学位论文).合肥：中国科学技术大学,2010.
[107]Bicego M, Figueiredo M A T. Soft clustering using weighted one-class support vector machines. Pattern Recognition.2009(42):27-32.
[108]Vapnik V N. Statistical learning theory. New York:John Wilet,1998.
[109]边肇祺,张学工.模式识别.北京：清华大学出版社,2000.
[110]刘江华,程君实,陈佳品.支持向量机训练算法综述.信息与控制.2002,31(1)：45-50.
[111]Flake G W,Lawrence S.Efficient SVM regression training with SMO. Machine Learni ng,2002,46(3):271-290.
[112]Shilton A, Palaniswami M, Ralph D. Incremental training of support vector machines. IEEE Transactions on Neural Networks.2005,16(1):114-131.
[113]Platt J. Sequential minimal optimization:A fastalgorithm for training support vector machines. Advances in Kernel Methods-Support Vector learning. Cambridge:MIT Press,1999:185-208.
[114]Paquet U, Engelbrecht A P. Training Support Vector Machines with Particle Swarms. In Proceedings of the International Joint Conference on Neural Networks. Portland:Institute of Electrical and Electronics Engineers Inc,2003:1593-1598.
[115]Anguita D, Ridella S, Rivieccio F. Quantum optimization for training support vector machines. Neural Networks.2003,16(5):763-770.
[116]田英杰.支持向量回归机及其应用：(博士学位论文).北京：中国农业大学,2005.
[117]张春华.支持向量机中最优化问题的研究：(博士学位论文).北京：中国农业大学,2004.
[118]于萍.自适应逆控制方法研究及其应用：(博士学位论文).北京：华北电力大学,2006.
[119]王定成,姜斌.支持向量机控制与在线学习方法研究的进展.系统仿真学报.2007,9(6)：1177-1181.
[120]田翔,邓非其.精确在线支持向量回归在股指预测中的应用.计算机工程.2005,31(22)：18-2().
[121]Ma J, Theiler J, Perkins S. Accurate On-line Support Vector Regression. Neural Computation.2003, (15):2683-2703.
[122]田红军,王锡怀,肖健梅.基于SVM的内模控制算法在船舶航向中的应用.2010,5：43-45.
[123]李春文,冯元琨.多变量非线性控制的逆系统方法.北京：清华大学出版社,1991.
[124]陈江辉Buck型逆变器高阶系统布尔型滑模控制及反馈线性化最优控制研究：博士学位论文.广州：华南理工大学,2010.
[125]韩璞,于萍,王东风,等.基于支持向量回归的自适应逆控制方法.华北电力大学学报.2006,33(3)：31-35.
[126]Shin J H, Kim H J, Kim Y D. Adaptive support vector regression for UAV flight control. Neural Networks.2011(24):109-120.
[127]Khalil H K. Nonlinear Systems. New Jersey:Prentice-Hall,2002.
[2]吴恭兴.无人艇操纵性与智能控制技术研究：(博士学位论文).哈尔滨：哈尔滨工程大学,2010.
[3]高双.高速无人艇的建模与控制仿真：(硕士学位论文).哈尔滨：哈尔滨工程大学,2007.
[4]邱健.致命幽灵—美法联合发展水面无人艇项目.国际展望.2005,2：52-55.
[5]况小梅.水面高速无人艇的概念设计研究：(硕士学位论文).哈尔滨：哈尔滨工程大学,2007.
[6]杨星.船舶结构与设备.武汉：武汉理工大学出版社,2007.
[7]Witt N A J, Miller K M. An adaptive track keeping neural network controller for ship guidance. Proc. Impact of New Technol. on the Marine Industries, Southhampton, U.K.,1993:13-15.
[8]Burns R S. The use of artificial neural networks for the intelligent optimal control of surface ships. IEEE J. Oceanic Eng.1995,2:65-72.
[9]Zhang Y, Hearn G E, Sen P. A Neural Network Approach to Ship Track-Keeping Control. IEEE journal of oceanic engineering.1996,21(4):513-527.
[10]赵邦良,张尧.人工神经网络在船舶自动舵上的应用.华东船舶工业学院学报.1998,12(6)：36-47.
[11]林叶锦,任光.遗传优化的径向基函数船舶模糊控制器.控制理论与应用.2004,21(6)：1036-1040.
[12]陈鸶鹭,程海边.基于模糊神经网络控制的水面无人艇建模与仿真.舰船科学技术.2010,32(11)：134-136.
[13]宋佳,刘胜,李高云.船舶航向最小二乘支持向量机内模控制.电机与控制学报.2009,13(增1)：183-187.
[14]刘胜,宋佳,李高云.船舶保持鲁棒最小二乘支持向量机控制.控制与决策.2010,25(4)：551-561.
[15]张元涛,石为人,李建立,等.基于反馈线性化的船舶自动舵模糊滑模控制.系统仿真学报.2010,22(10)：2337-2341.
[16]曾薄文,朱齐丹,于瑞亭.欠驱动水面船舶的曲线航迹跟踪控制.哈尔滨工程大学学报. 2011,32(10)：1317-1322.
[17]汀洋.基于动态神经模糊模型的欠驱动水面船舶控制：(博士学位论文).大连：大连海事大学,2010.
[18]廖煌雷,庄佳园,李晔,等.欠驱动无人艇轨迹跟踪的滑模控制方法.应用科学学报.2011,29(4)：428-434.
[19]廖煜雷,庞永杰,庄佳园.喷水推进型无人艇航向跟踪的反步自适应滑模控制.计算机应用研究.2012,29(1)：82-84.
[20]Toussaint G J, Basar T, Bullo F. Tracking for Nonlinear Underactuated Surface Vessels with Generalized Forces. Proc. IEEE Conf. Control Applications, Anchorage, Alaska USA,2000:355-360.
[21]Do K D, Jiang Z P, pan J. Robust Global Output Feedback Stabilization of Underactuated Ships on a Linear course. Proc.41 IEEE Conf. Decision and Control, Las Vegas, Nevada USA,2002:1687-1692.
[22]Pettersen K Y, Nijmeijer H. Global Practical Stabilization and Tracking for An Underactuated Ship-A Combined Averaging and Backstepping Approach. Proc.IFAC Conf. System Structure and Control, Nantes, France,1998:59-64.
[23]Pettersen K Y, Lefeber E. Way-Point Tracking control of ships. Proc.40th IEEE Conf. on Decision and Control, Orlando, Florida USA,2001:940-945.
[24]李铁山,杨盐生,郑云峰.不完全驱动船舶航迹控制输入输出线性化设计.系统工程与电子技术.2004,26(7)：945-980.
[25]周岗,姚琼荟,陈永冰,等.不完全驱动船舶直线航迹控制稳定性研究.自动化学报.2007,33(4)：378-384.
[26]翟传润.船舶智能自适应航迹舵的研究：(博士后士学位论文).上海：上海交通大学,2002.
[27]Reyhanoglu M. Exponential Stabilization of an Underactuated Autonomous Surface Vessel. Automatica.1997,33(12):2249-2254.
[28]Godhhavn J M, Fossen T I, Berge S P. Nonlinear and Adaptive Backstepping Designs for Tracking Control of Ships. Int.J. Adapt. Control Signal Processing.1998(12):649-670.
[29]Pettersen K Y, Nijmeijer H. Underactuated Ship Tracking Control:Theory and Experiments. Int. J. Control.2001,74(14):1435-1446.
[30]Gopalswamy S, Hedrick J K. Tracking Nonlinear Non-Minimum Phase Systems Using Sliding Mode. Int. J. Control.1993,57:1141-1158.
[31]Do K D, Jiang Z P, Pan J. Underactuated Ship Global Tracking under Relaxed Conditions. IEEE Trans. on Automat. Control.2002,47(9):1529-1536.
[32]Do K D, Jiang Z P, Pan J. Robust Global Stabilization of Underactuated Ships on a Linear Course:State and Output Feedback. Int. J. Control.2003,76(1):1-17.
[33]周岗,姚琼荟,陈永冰,等.基于输入输出线性化的船舶全局直线航迹控制.控制理论与应用.2007,24(1)：117-121.
[34]孙巧梅,任光.基于自适应SVR逆方法的无人艇航向控制.中国航海.2012,35(4)：17-21.
[35]孙巧梅,任光.基于输入输出线性化SVR的船舶航迹控制.中国造船.2012,53(4)：91-99.
[36]侯媛彬,杜京义,汪梅.神经网络.西安：西安电子科技大学出版社,2007.
[37]Ragazzini J R, Zadeh L A. The analysis of sampled-data systems. AIEE transactions, 1952,71:225-234.
[38]Nyquist H. Regeneration theory. The bell system technical journal,1932,11: 126-147.
[39]Evans W. R. Control system synthesis by root locus method. AIEE Transactions, 1950,69:66-69.
[40]Brockett R. W., Willems J. L.. Frequency domain stability criteria-part Ⅰ. IEEE Transactions on Automatic Control.1965, AC-10:255-261.
[41]Kalman R E. When is a linear control system optimal? Journal of basic engineering, 1964,86:51-60.
[42]Zadeh L A. Fuzzy sets. Information and Control,1965,8:338-353.
[43]Zadeh L A. Fuzzy logic, neural networks and soft computing. Communication. ACM, 1994,37(3):77-84.
[44]Lin C T, Lee C S G. Neural Fuzzy Systems:a Neuro-Fuzzy Synergism to Intelligent Systems. Englewood Cliffs, NJ:Prentice Hall,1996.
[45]Nauck D, Klawonn F, Kruse R. Foundations of Neuro-Fuzzy Systems. New York:Wiley, 1997.
[46]Cheng C H, Hsu C F, Lin C M, et al. Fuzzy-neural sliding-mode control for DC-DC converters using asymmetric Gaussian membership functions. IEEE Trans. Ind. Electron. 2007,54:1528-1536.
[47]Da F, Song W. Fuzzy neural networks for direct adaptive control. IEEE Trans. Ind. Electron.2003,50:507-513.
[48]Wang C H, Lin T C, Lee T T, et al. Adapti ve hybrid intelligent control for uncertain nonlinear dynamical systems. IEEE Trans. Syst. Man Cybern.2002, Part B 32:583-597.
[49]Sui J H, Yu G Z, Zhang W X. A ship motion control system design based on AND-OR Fuzzy neural networks. Proceedings of the 2007 IEEE International Conference on Robotics and Biomimetics. Sanya, China,2007:1194-1199.
[50]Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks,1989,2(2):359-366.
[5l]Lin F J, Lin C H, Shen P H. Self-constructing fuzzy neural network speed control ler for permanent-magnet synchronous motor drive. IEEE Trans. Fuzzy Syst.2001,9: 751-759.
[52]Mar J, Lin F J. An ANFIS controller for the car-following collision prevention system. IEEE Trans. Veh. Technol.2001,50:1106-1113.
[53]Lin C J. A GA-based neural fuzzy system for temperature control. Fuzzy Sets Syst. 2004,143:311-333.
[54]Lin C T, Lee C S G. Neural-network-based fuzzy logic control and decision. IEEE Transactions on computer.1991,40(12):1320-1336.
[55]Keller J M, Yager R R, Tahani H. Neural network implementation of fuzzy logic. Fuzzy Sets and Systems.1992,45 (1):1-12.
[56]Yager R R.OWA neurons:A new class of fuzzy neurons. International Joint Conference on Neural Networks,1992:226-230.
[57]Pedrycz W, Reformat M. Genetical ly optimized logic models. Fuzzy Sets and Systems. 2005,150(2):351-371.
[58]隋江华AND-OR模糊神经网络研究及在船舶控制中的应用：(博士学位论文).大连：大连海事大学,2006.
[59]Pedrycz W. Fuzzy equalization in the construction of fuzzy sets. Fuzzy Sets and systems.2001,119(2):329-335.
[60]Pedryez W, Reformat M. Rule-based Modeling of Nonlinear Relationships. IEEE Transactions on Fuzzy Systems.1997,5(2):26-269.
[61]Hirota K, Pedrycz W. OR/AND Neuron in Modeling Fuzzy Set Connective. IEEE Transactions on Fuzzy Systems.1994,2(2):151-161.
[62]隋江华,任光.模糊AND-OR神经网络优化建模方法.广西师范大学学报.2006,24(4)：111-114.
[63]Pedrycz W, Aliev R A. Logic-oriented neural networks for fuzzy neurocomputing. Neurocomputing.2009,73:10-23.
[64]Liang X, Pedrycz W. Logic-based fuzzy networks:A study in system modeling with triangular norms and uninorms. fuzzy sets and systems.160 (2009):3475-3502.
[65]肖健梅,柯玉波,王锡淮.基于支持向量机的非线性系统逆控制.中南大学学报(自然科学版).2007,38：319-323.
[66]Sun Q M, Ren G, Yue J et al. SVM inverse model-based heading control of unmanned surface vehicle.2010 IEEE Youth Conference on Information, Computing and Telecommunications. Beijing,2010:138-141.
[67]袁小芳,王耀南,孙炜.支持向量机-模糊推理自学习控制器设计.控制理论与应用.2006,23(1)：1-6.
[68]何峻峰,张曾科.基于支持向量机的逆系统离散控制方法.清华大学学报.2005,45(1)：100-106.
[69]Chan W C, Chan C W, Cheung K C. On the modelling of nonlinear dynamic system using support vector neural networks. Engineering Applications of Artificial Intelligence, 2001,14(2):105-113.
[70]Rojo-alvarez J L, Martinez-Ramon M, de Prado-Cumplido M. Support Vector Method for Robust ARMA System Identification.IEEE Transactions on Signal Processing.2004, 52(1):155-164.
[71]Suykens J A K, Vandewalle J, De Moor B. Optimal control by least squares support machines. Neural Networks.2001,14(1):23-35.
[72]王定成,方廷健.一种基于支持向量机的内模控制方法.控制理论与应用.2004,21(1)：85-88.
[73]Cao L J, Tay Francis E H. Support Vector Machine with Adaptive Parameters in Financial Time Series Forecasting.IEEE Transactions on Neural Networks.2003,14(6): 1506-1518.
[74]Wang H, Pi D, Sun Y. Online SVM regression algorithm-based adaptive inverse control Nerocomputing.2007,70:952-959.
[75]陈进东,潘丰.基于在线支持向量机的非线性内模控制.计算机工程与应用.2009,45(9)：18-20.
[76]Sun Q M,Ren G. An online adaptive neural approach for tracking control. Ocean Engineering.2013,58:106-114.
[77]张秀凤,尹勇,金一丞.规则波中船舶运动六自由度数学模型.交通运输工程学报.2007,7(3)：40-43.
[78]陈立家.海上多目标船智能避碰辅助决策研究：(博士学位论文).武汉：武汉理工大学2011.
[79]贾欣乐,杨盐生.船舶运动数学模型——机理建模与辨识建模.大连：大连海事大学.1999.
[80]Van Amerongen. Adaptive Steering of Ships-A Model Reference Approach to Improved Manoeuvring and Economical Course-Keeping:(PhD Thesis).The Netherlands:Delft University Of Technology,1982.
[81]Buekley J J, Silar W. A new t-Norm. Fuzzy Sets and Systems.1998,16(1):283-290.
[82]Mesiar R. A note on moderate growth of t-conorms. Fuzzy Sets and Systems.2001, 122(2):357-359.
[83]Wygralak M. Fuzzy Sets with triangular norms and their cardinality theory. Fuzzy Sets and Systems.2001,124(1):1-24.
[84]鲁斌.逻辑神经元研究综述.微机发展.2005,15(11)：131-138.
[85]Glorennec Pierre-Uves. Neuro-fuzzy logic. Proc IEEE-FUZZ. New Orleans,1996:512-518.
[86]陈丹,何华灿,王晖.一种新的基于弱T范数簇的神经元模型.计算机学报.2001,24(10)：1115-1120.
[87]Buekley J.J. et al. On the equivalence of neural nets and fuzzy expert systems Fuzzy sets and systems 100 supplement.1999:145-150.
[88]陈星,刁永峰.三值逻辑神经元模型及推理.湖州师范学院学报.2004,26(2)：59-62.
[89]杨钟瑾,史忠科.神经网络结构优化方法.计算机工程与应用.2004.25(15)：52-54.
[90]米凯利维茨Z.演化程序——遗传算法与数据编码的结合.北京：科学出版社,2000.
[91]张火明,杨松林,朱仁庆,等.船舶航行性能优化的模糊遗传算法.中国造船.2002,43(3)：7-15.
[92]Lin W M, Yang C D,Tsay M T. Distribution system planning with evolutionary programming and a reliability cost model. Generation, Transmission & Distribution. 2000,147(60):361-366.
[93]乔俊匕,韩红桂.RBF神经网络的结构动态优化设计.自动化学报.2010,36(6)：865-872.
[94]Wieman C E, Adams W K, Perkins K K. PhET:Simulations That Enhance Learning. Science,2008,322:682-683.
[95]O'Reilly R C. Biologically Based Computational Models of High-Level Cognition. Science,2006,314:91-94.
[96]Marchiori D, Warglien M. Predicting Human Interactive Learning by Regret-Driven Neural Networks. Science,2008,319:1111-1113.
[97]Michael D. Cohen. Learning with Regret. Science,2008,319:1052-1053.
[98]任光,孙巧梅,齐小伟.交互学习神经网络模型及其仿真研究.系统仿真学报.2009,21(17)：5314-5317.
[99]Sun Q M, Ren G, Qi X. Interactive learning neural networks for predicting game behavior. Lecture Notes in Computer Science.2009, LNCS 5551 (Part Ⅰ):774-783.
[100]张丹,李长河.基于混沌的粒子群优化算法研究与进展.软件导刊.2007,11：109-110.
[101]Perez T, Ross A, Fossen T I. A 4-dof Simulink model of a coastal patrol vessel for manoeuvring in waves.7th IFAC Conference on Manoeuveing and Control of Marine Vessels MCMC,2006.
[102]Moreira L, Fossen T I, Soares G C. Path following control system for a tanker ship model. Ocean Engineering.2007(34):2074-2085.
[103]Fossen, T. I. Marine control systems. Trondheim, Norway:Marine Cybernetics,2002.
[104]Morten Breivik. Nonlinear Maneuvering Control of Underactuated Ships:Master of science thesis. Norway:Norwegion University of Science and Technology,2003.
[105]Vapnik V N. The nature of statistical learning theory. NewYork:Springer-Verlag, 1999.
[106]何丹玉.支持向量机逆系统控制方法的研究与应用：(硕士学位论文).合肥：中国科学技术大学,2010.
[107]Bicego M, Figueiredo M A T. Soft clustering using weighted one-class support vector machines. Pattern Recognition.2009(42):27-32.
[108]Vapnik V N. Statistical learning theory. New York:John Wilet,1998.
[109]边肇祺,张学工.模式识别.北京：清华大学出版社,2000.
[110]刘江华,程君实,陈佳品.支持向量机训练算法综述.信息与控制.2002,31(1)：45-50.
[111]Flake G W,Lawrence S.Efficient SVM regression training with SMO. Machine Learni ng,2002,46(3):271-290.
[112]Shilton A, Palaniswami M, Ralph D. Incremental training of support vector machines. IEEE Transactions on Neural Networks.2005,16(1):114-131.
[113]Platt J. Sequential minimal optimization:A fastalgorithm for training support vector machines. Advances in Kernel Methods-Support Vector learning. Cambridge:MIT Press,1999:185-208.
[114]Paquet U, Engelbrecht A P. Training Support Vector Machines with Particle Swarms. In Proceedings of the International Joint Conference on Neural Networks. Portland:Institute of Electrical and Electronics Engineers Inc,2003:1593-1598.
[115]Anguita D, Ridella S, Rivieccio F. Quantum optimization for training support vector machines. Neural Networks.2003,16(5):763-770.
[116]田英杰.支持向量回归机及其应用：(博士学位论文).北京：中国农业大学,2005.
[117]张春华.支持向量机中最优化问题的研究：(博士学位论文).北京：中国农业大学,2004.
[118]于萍.自适应逆控制方法研究及其应用：(博士学位论文).北京：华北电力大学,2006.
[119]王定成,姜斌.支持向量机控制与在线学习方法研究的进展.系统仿真学报.2007,9(6)：1177-1181.
[120]田翔,邓非其.精确在线支持向量回归在股指预测中的应用.计算机工程.2005,31(22)：18-2().
[121]Ma J, Theiler J, Perkins S. Accurate On-line Support Vector Regression. Neural Computation.2003, (15):2683-2703.
[122]田红军,王锡怀,肖健梅.基于SVM的内模控制算法在船舶航向中的应用.2010,5：43-45.
[123]李春文,冯元琨.多变量非线性控制的逆系统方法.北京：清华大学出版社,1991.
[124]陈江辉Buck型逆变器高阶系统布尔型滑模控制及反馈线性化最优控制研究：博士学位论文.广州：华南理工大学,2010.
[125]韩璞,于萍,王东风,等.基于支持向量回归的自适应逆控制方法.华北电力大学学报.2006,33(3)：31-35.
[126]Shin J H, Kim H J, Kim Y D. Adaptive support vector regression for UAV flight control. Neural Networks.2011(24):109-120.
[127]Khalil H K. Nonlinear Systems. New Jersey:Prentice-Hall,2002.