摘要
21世纪是人类研究、开发及和平利用海洋的世纪，随着人类对海洋开发利用的不断增加，能够探测水下环境并且自主完成特定作业任务的水下机器人受到国内外研究机构的广泛重视。作为在复杂海洋环境下工作的载体，自主性及安全性是水下机器人的重要特征，智能控制技术是保障其自主性和安全性的重要基础和核心技术。水下机器人智能控制的内涵包括自主规划、运动控制与状态监控。研究水下机器人自主任务规划、智能运动控制、传感器信息融合以及自主监控技术，对于提高水下机器人的智能化水平和加快工程化应用进程具有重要的意义。
水下机器人是具有较强非线性的复杂动态系统，广义预测控制对于模型辨识误差、传感器噪声以及被控系统的时滞和阶次不确定表现出良好的鲁棒性，本文进行了基于广义预测控制算法的水下机器人运动控制的研究工作。从基于牛顿．欧拉方程和神经网络建立水下机器人的动力学模型入手，通过预测模型，根据被控系统的历史信息和未来输入预测其未来输出，采用有限时段滚动优化，并根据被控系统实际输出误差，在线调整预测模型和控制器参数，实现预测模型与控制器的在线调整。
为了研究水下机器人的运动特性，推导了位姿向量在固定坐标系和运动坐标系之间的转换矩阵，根据“海狸”水下机器人的体系结构和运动特点，对转换矩阵进行了简化。根据流体中刚体的牛顿-欧拉方程，建立了“海狸”水下机器人艏向和纵向的动力学模型，利用最小二乘法对动力学模型的参数进行辨识及偏差估计，对“海狸”水下机器人所配置的推进器进行了动态性能分析。
在分析动态递归神经网络用于非线性动态系统辨识的原理及可行性的基础上，推导了改进的Elman网络的动态BP学习算法。以滑动窗口模式，采用截短学习样本的方法，实现改进的Elman网络的在线学习，并进行了存在白噪声和类阶跃信号干扰情况下的非线性动态系统的在线辨识。提出了应用于非线性动态系统神经网络辨识的并行模型和串并模型相融合的改进的系统输出递归方式，既对被辨识系统有一定的滤波能力，又提高了神经网络系统辨识的收敛速度。
在广义预测控制算法方面，对参数未知、参数慢时变以及考虑控制量及控制量变化率受限的线性动态系统进行了广义预测控制的计算机控制研究，对“海狸”水下机器人的动力学模型进行了动态性能分析，利用欧拉差分得到其离散差分方程，基于特殊非线性动态系统可以时变参数线性转化的理论，对具有二次阻力项的水下机器人非线性动力学模型存在白噪声的情况下，进行了艏向、纵向自由度速度、位移方式的广义预测控制研究。
以改进的Elman网络作为多步预测模型，提出并推导了神经广义预测控制律的灵敏度导数计算公式，在存在白噪声干扰和类阶跃信号干扰情况下，分别利用具有在线学习功能的和不具有在线学习功能的神经广义预测控制算法进行了非线性动态系统的预测控制研究和控制误差分析。提出了将具有在线学习功能的神经广义预测控制算法应用于水下机器人的运动控制，并进行了计算机仿真研究，由于改进了神经网络系统输出的递归方式，基于神经网络的广义预测控制相对于基于CARIMA模型的广义预测控制的鲁棒性要好。具有在线学习功能的神经广义预测控制的计算机仿真结果表明具有在线学习功能的神经广义预测控制算法能够实现非线性动态系统的预测控制，且控制效果优于不具有在线学习功能的神经广义预测控制。
The 21~(th) century is the century that man investigate, develop and utilize peacefully the sea, with the development of developing and utilizing the sea, more and more researchers apply themselves to the development of autonomous underwater vehicle(AUV) which can explore the underwater circumstance and accomplish the special missions. As a vehicle which works in complicated oceanic environments, automation and safety are its main character. And intelligent control is the key technology to keep AUV autonomous and safe. Intelligent control includes autonomous mission planning, motion control and status monitoring. So, research on autonomous mission planning, motion control and status monitoring for AUV has the important meaning to improve AUV's intelligence and application.
AUV is complicated non-linear dynamical plant, Generalized Predictive Control(GPC) can systematically take into account real plants constraints in real-time, and is robust with respect to modeling errors, sensor noise. In this paper, some research works about AUV motion control based on GPC are carried out. The dynamical models of the AUV are build with Newton-Euler equations and neural networks and used as multi-step predictive model. With predictive model, based on the passed plant status and future inputs and reference outputs, the future inputs can be predicted, the optimization is real-time. With the actual output error of the real plant, the predictive model or the controller parameters are adjusted. So the optimization is close-loop.
Based on analyzing the mechanical structure of the "Beaver" AUV, to describe the motion of AUV, the world reference frame and the body reference frame are used. The transformation matrix for position and attitude vector between two reference frames are also presented. And the transformation matrix is also simplified to "Beaver" AUV. Based on Newton-Euler equations, the AUV dynamical model for yaw and surge are build, the parameters of the dynamical model are also identified with least square method, and the identification error is considered. The dynamics of the propeller for the "Beaver" AUV is also analyzed.
The on-line learning for Dynamical Recurrent Neural Networks(DRNN) is proposed and realized with sliding window mode, the nonlinear dynamical plant with white noise is identified on-line with the DRNN, fusing the parallel model and series-parallel model, the improved recurrent mode is proposed. This can not only improve the convergence of the DRNN on-line learning but also filter out the noise. And the DRNN with on-line learning is applied to the "Beaver" AUV dynamical model identification successfully.
To GPC, considering the unknown parameters or slowly changing of predictive model and the constraints to the inputs, the indirect and direct adaptive GPC to linear dynamical plant are programmed. The dynamics of the "Beaver" AUV is analyzed. Because a specific non-linear dynamical equations can be linearzed with on-line changing parameters, with Euler differencing equation, the non-linear speed and position dynamical model for AUV are controlled with GPC.
The modified Elman Neural Networks is used as multi-step predictive model, the derivative to reason the Neural Generalized Predictive Control(NGPC) law is analyzed elaborately, the on-line learning and off-line learning NGPC is realized to control the non-linear dynamical plant, the output error is also analyzed, the on-line learning and off-line learning NGPC is applied to the control for "Beaver" AUV yaw and surge speed successfully. Because the improved output recurrent mode, the neural networks based GPC is more robust than CARMA model based GPC. When the controlled dynamical plant is polluted with slow changing noise, the control effect to on-line learning GPC is better than off-line GPC.
引文
[1] 蒋新松，封锡盛等．水下机器人．沈阳：辽宁科学技术出版社，2000：3-32页，422-460页
[2] 张铭钧．水下机器人．北京：海洋出版社，2000：1-7页，74-77页
[3] 施生达．潜艇操纵性．北京：国防工业出版社，1995：15-49页
[4] 张铭钧．基于神经网络和遗传算法的水下机器人运动建模、规划与控制技术研究．哈尔滨工程大学博士学位论文．1998：14-42页，76-94页
[5] D.B.Marco, A.J.Healey. Current developments in underwater vehicle control and navigation: the NPS ARIES AUV. http://web.npa.mil/～me/healey/papers/Ocean2000.pdf
[6] D.B.Marco, A.J.Healey and R.B.RcGhee. Control system architecture, navigation and commucation research using the NPS Phoenix underwater vehicle, http://web.npa.navy.mil/～me/healey/papers/iarp_96.pdf
[7] J.Nie, J.Yuh, E.kardash and T.I.Fossen. On-board sensor-based adaptive control of smaill UUVs in very shall water. International of adaptive control signal process, 2000, 14: 441-452P
[8] T.W.Kim, J.Yuh. Application of on-line neural-fuzzy controllers to AUVs. Information sciences, 2004, 145:169-182P
[9] S.K. Choi, J. Yuh, G.Y. Takashige, Development of the omni-directioanl intelligent navigator. IEEE Robot. Automation, 1995:44-53P
[10] T.Fujii, T.Ura, Y.Kuroda, H.Chiba, Y.Nose, K.Aramaki. Development of a versatile test-bed "Twin-Burger" toward realization of intelligent behaviors of autonomous underwater vehicles. OCEANS'93, Victoria, Canada, 1993:186-192P
[11] C.S.Anan, S.Abdallah and D.Wettergreen. Development of autonomous underwater vehicle towards visual servo control. In Proceedings of the Australian Conference on Robotics and Automation. Melbourne, Australia, 2000:105-110P
[12] D.Wettergreen, C.Gaskett and A.Zelinsky. Autonomous guidance and control for an underwater robotic vehicle. http://users.rsise.anu.edu.au/～rsl/rsl_paper/99fsr.kambara.pdf
[13] D.Wettergreen, C.Gasket and A.Zelinsky. Development of a visually-guided autonomous underwater vehicle. In Proceedings of IEEE OCEANS'98 Conference. Nice, France.
[14] C.S.Anan, T.Brinsmead, S.Abdallah and A.Zelinsky. Preliminary experiments in visual servo control for autonomous underwater vehicle. http://thai.anu.edu.au/publication/iros2001.pdf
[15] C.S.Anan. Autonomous underwater robot: vision and control. The Austrilian national university, master thesis. 2001
[16] W.Naeem, R.Sutton, J.Chudley. System identification, modeling and control of an autonomous underwater vehicle, Proceedings of MCMC2003 conference, Girona, Spain, 2003:37-42P
[17] W.Naeem. Model predictive control of an autonomous underwater vehicle. Proceedings of UKACC 2002 postgraduate symposium, Sheffield, UK, 2002:19-23P
[18] W.Naeem, R.Sutton and S.M.Ahmad. Pure pursuit guidance and model predictive control of an autonomous underwater vehicle for cable/pipeline tracking. Presented in the World Maritime Technology Conference, San Francisco, California, USA, 2003
[19] 孙峻．非线性模型预测理论及应用研究．西北工大博士论文．2002
[20] 孙峻，徐德民．一种充分利用预测信息的广义预测控制律．西北工业大学学报．2002，20(2)：324-327P
[21] T.I.Fossen. Guidance and control of ocean vehicles.John Wiley,1994
[22] T.I.Fossen and S.I.Sagatun. Adaptive control of nonlinear underwater robotic systems. In Proceedings of the 1991 IEEE International Conference on Robotics and Automation, Sacramento, California, 1991: 1687-1695P
[23] D.B.Marco, A.Martins and A.J.Healey. Surge motion identification for NPS Phoenix AUV. In International Advanced Robotics Program, IARP'98, Lafayette, Lousiana, USA, 1998
[24] G. Indiveri. Modeling and identification of underwater Robotic systems. University of Genova, Ph.D Thesis. 1998
[25] M.Caccia, G. Indiveri and G.veruggio. Modeling and identification of open-frame variable configuration unmanned underwater vehicles. Published in IEEE Journal of Ocenic Engineering, 2000, 25(2):227-240P
[26] A.Alessandri, R.Bono, M.Caccia, G. Indiveri and G.veruggio. Experiments on the modeling and identification of the heave motion of the open-frame UUV. In Proceedings of the IEEE OCEANS'98. Nice, France.
[27] P.Ridao, J.Batlle and M.Carreras. Model identification of a low-speed UUV. In proceedings of the 1st IFAC workshop on guidance and control of underwater vehicles, 2003: 47-52P
[28] 于华男．开架式水下机器人辨识与控制技术研究．哈尔滨工程大学博士论文．2003
[29] K.Ishii, T.Ura and T.Fujii. A feed forward neural network for identification and adaptive control of autonomous underwater vehicles. IEEE ICNN'94. 3216-3221P
[30] K.Ishii,T.Fujii and T.Ura. Neural network system for on-line controller adaptation and its application to underwater robot. Proceedings of the 1998 IEEE International Conference on Robotics & Automation, Leuven, Belgium, 1998:756-761P
[31] K.Ishii, T.Fujii and T.Ura. An adaptive neural-net controller system for an underwater vehicle. Control Engineering Practice, 2000, 8: 177-184P
[32] P.V.Ven, C.Flanagan, D.Toal and E.Omerdic. Identification and control of underwater vehicles with the aid of neural networks. http://rhw.staff.ul.ie/omerdic/My%20Papers/RAM2004.pdf
[33] J.Yuh. Design and control of autonomous underwater robots: A Survey. Autonomous Robots, 2000(8):7-24P
[34] J.Yuh, M.West. Underwater Robotics. Advanced Robotics. 2002, 15(5):609-639P
[35] S.M.Zanoli, G.Conte. Remotely operated vehicle depth control. Control Engineering Practice. 2003, 11: 453-459P
[36] H.Kondo, T.Ura. Navigation of an AUV for investigation of underwater structures. Control Engineering Practice. 2004,12:1551-1559P
[37] 沈伟．模糊PID控制在水下机器人运动控制中的应用．哈尔滨工程大学硕士论文．2005
[38] S.M. Smith, G.J.S.Rae and D.T.Anderson. Application of fuzzy logic to the control of an autonomous underwater vehicle. IEEE International Conference on Fuzzy Systems. 1993:1099-1106P
[39] S.M. Smith, G.J.S.Rae, D.T.Anderson and A.M.Shein. Fuzzy logic control of an autonomous underwater vehicle. Control Engineering Practice. 1994: 321-331P
[40] P.A.DeBitetto. Fuzzy logic for depth control of unmanned undersea vehicles. Proceedings of Symposium of.Autonomous Underwater Vehicle Technology. 1994:233-241P
[41] V.Kanakakis, K.P.Valavanis, N.C.Tsourveloudis. Fuzzy-logic based navigation of underwater vehicles. Journal of Intelligent and Robotic Systems. 2004, 40:45-48P
[42] J.Yuh, Jing Nie. Application of non-regressor-based adaptive control to underwater robot: experiment. Computer and Electrical Engineering 2000, 16:169-179P
[43] Jing Nie, Yuh. J, Kardash. E and Fossen T.I. On-board sensor-based adaptive control of small UUVs in very shallow water. International Journal of Adaptive Control and Signal Processing. 1999:201-207P
[44] K.D.Do, J.Pan, Z.P.Jiang. Robust and adaptive path following for underactuated autonomous underwater vehicles. Ocean Engineering. 2004, 31:1967-1997P
[45] P.J.Craven, R.Sutton, R.S.Burns and Y.M.Dai. Multivariable intelligent control strategies for an autonomous underwater vehicle. International Journal of Systems Science.. 1999, 30(9):965-980P
[46] K.Kim, J.Y.Kom, H.S.Choi, K.Y.Lee and W.Seong. The silding mode controller for a test-bed AUV SNUUY Ⅰ. Proceedings of ISOPE Pacific/Asia Offshore Mechanics Symposium. 2002:116-122P
[47] I.Mario, C.Giampiero. Robust control of underwater vehicles: sliding mode vs. LMI syntehsisi. Proceedings of the American Control Conference. 1999, 5:3422-3426P
[48] L.R.Wang, J.C.Liu and Y.R.Xu. Sliding mode control of an autonomous underwater vehicle. Proceedings of 2002 International Conference on Machine learning and Cybemetics. Beijing, P.R.China.2002:247-251P
[49] 王丽荣．水下机器人变结构控制技术的研究．哈尔滨工程大学硕士论文．2003
[50] K.Narendra, K.Parthasarathy. Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks. 1990, 1(1):4-27P
[51] J.H.Li, P.M.Lee and B.H.Jun. A nerual network adaptive controller autonomous diving control of an autonomous underwater vehicle. International Journal of Control, Automation and Systems. 2004, 2(3):374-383P
[52] J.Guo, F.C.Chiu and C.C.Huang. Adaptive control of an autonomous underwater vehicle testbed using neural networks. In Proceedings of the IEEE OCEANS'95.1995, 2:1033-1039P
[53] W.J.Pepijn, C.Flanagan and D.Toal. Neural network control of underwater vehicles. Engineering application of Artificial Intelligence. 2005, 18:533-547P
[54] F.J.Song, S.M.Smith. Design of sliding mode fuzzy controllers for an autonomous underwater vehicle with system model. In Proceedings of the IEEE OCEANS'2000. 2000, 2:835-840P
[55] J.Guo, F.C.Chiu and C.C.Huang. Design of a sliding mode fuzzy controller for the guidance and control of an autonomous underwater vehicle. Ocean Engineering. 2003, 30:2137-2155P
[56] T.W.Kim, J.Yuh. Application of on-line neuro-fuzzy controller to AUVs, Information Sciences. 2002, 145:169-182P
[57] D.W.Clarke, C.Mohtadi and P.C.Tuffs. Generalized predictive control-Part 1: the basic algorithm. Automatica. 1987, 23(2): 137-148P
[58] D.W.Clarke, C.Mohtadi and P.C.Tuffs. Generalized predictive control-Part 2: extensions and interpretations. Automatica. 1987, 23(2): 149-163P
[59] D.W. Clarke, C.Mohtadi. Properites of generalized predictive control. Automatica. 1989, 25(6):859-875P
[60] D.W. Clarke. Advances in model-based predictive control, in advances in model-based predictive control. By D.W.Clarke, Oxford University press, 1994
[61] 席裕庚，耿晓军，陈虹．预测控制性能研究的新进展．控制理论及其应用．2000，17(4)：469-475页
[62] 席裕庚．预测控制．北京：国防工业出版社，1993
[63] 王伟．广义预测控制理论及其应用．北京：科学出版社，1998
[64] 王伟．广义预测自适应控制的直接算法及全局收敛性分析．自动化学报．1995，21(1)：57-62页
[65] 王伟．一种广义预测自适应控制的直接解法．自动化学报．1996，22(3)：270-276页
[66] 钟璇．广义预测控制理论及其应用研究．浙江大学博士论文．1999
[67] D.Soloway, P. J.Haley. Neural generalized predictive control: A Newton-Raphson implementation. NASA Technical Memorandum 110244. Langley Research Center, Hampton, Virginia, 1997
[68] P. J.Haley, D.Soloway, B.Gold. Real-time adaptive control using neural generalized predictive control. 1999 American Control Conference. San Diego, California. 1999
[69] P.J.Haley, D.Soloway.Generalized predictive control for active flutter. Control Systems Magazine. 1997, 17(4):64-70P
[70] EH.Sφrensen, M.Nφrgaard, O.Ravn, N.K.Poulsen, Implementation of neural network based non-linear predictive control. Neurocomputing. 1999, 28: 37-51P
[71] H.Temurtas. Neural generalized predictive control: robotic manipulator with cubic and sinusoidal trajectory. Turkish Symposium on Artificial Intelligence and Neural Networks, TAINN. 2003
[72] 王雪松，程玉虎．一种基于时间差分算法的神经网络预测控制系统．信息与控制．2004，33(5)：531-535页
[73] 温淑焕，王科平．基于Elman网络的鲁棒型广义预测控制方法研究．系统工程学报．2004，19(5)：503-506页
[74] M.Lazar, O.Pastravanu. A neural predictive controller for non-linear systems. Mathematics and Computers in Simulation. 2002, 60:315-324P
[75] J.M.Zamarreno, P.Vega. Neural predictive control. Application to a highly non-linear system. Engineering Applications of Artificial Intelligence. 1999, 12:149-158P
[76] A.G.Parlos, S.Parthasarathy, A.F.Atiya. Neural-predictive process control using on-line controller adaptation. IEEE Transactions on Controll Systems Technology. 2001, 9(5): 741-755P
[77] N.Constantin. Adaptive neural predictive Ttechniques for nonlinear control. Studies on Informatics and Control. 2003, 12(4): 285-291P
[78] L.A.Gonzalez. Design, modeling and control of autonomous underwater vehicles. University of Western Australia. Bachelor Thesis. 2004
[79] 黄堃洋．开架式无人小艇之设计、动态分析与控制．台湾：国立中山大学硕士论文．2000
[80] D.R.Yoerger, J.G.Cookie and J.J.E.Slotine. The influence of thruster dynamics on underwater vehicle behavior and their incorporation into control system design. IEEE Journal of Ocean Engineering. 1990, 15(3): 167-178P
[81] A.J.Healey, S.M.Rock, S.Cody, D.Miles and J.RBrown. Toward an improved understanding of thruster dynamics for underwater vehicles. IEEE Journal of Ocean Engineering. 1995, 20(4):354-361P
[82] R.Bachmayer, L.L.Whitcomb and M.A.Grosenbaugh. An accurate four-quadrant nonlinear dynamical model for marine thrusters: theory and experimental validation. IEEE Journal of Ocean Engineering, 2000, 25(1): 146-159P
[83] C.L.Tsukamoto, W.Lee, J.Yuh, S.K.Choi and J.Lorentz. Comparison study on advanced thruster control of underwater robots. In IEEE International Conference on Robotics and Automation. Albuquerque, NewMexico, USA. 1997:1845-1850P
[84] L.L.Whitcomb and D.R.Yoerger. Development, comparison and preliminary experimental validation of non-linear dynamic thruster models. IEEE Journal of Ocean Engineering. 1999, 24(1):1-15P
[85] L.Ljung. System identification-theory for the unser. Beijing: Tsinghua University Press. 2002
[86] S.E.Cherif, G.Lebret and M.Perrier. Identification and control of a submarine vehicle. In Proceedings of the 5th IFAC symposium on robot control. Nantes, France. 1997:307-312P
[87] A.Alessandri, M.Caccia, G.Indiveri and G.Veruggio. Application of LS and EKF techniques to the identification of underwater vehicles. In proceedings of the IEEE international conference on control applications. Trieste, Italy. 1998: 1084-1088P
[88] 刘建成，刘学敏，徐玉如．极大似然值法在水下机器人系统辨识中的应用．哈尔滨工程大学学报．2001，22(5)：1-4页
[89] D.A.Smallwood. Advances in dynamical modeling and control fo underwater robotic vehicles. The Johns Hopkins University. Ph.D Thesis. 2003
[90] D.A.Smallwood, L.L.Whitcomb. adaptive identification of dynamically positioned underwater robotic vehicles. IEEE transactions on control system technology. 2003, 11(4):505-515P
[91] 李言俊，张科．系统辨识理论及应用．北京：国防工业出版社．2003
[92] P.Barak. Smoothing and identification by an adaptive degree polynomial filter. Analytical Chemistry. 1995, 67(17):2758-2765P
[93] P.S.Sastry, G.Santharam, and K.P.Urmikrishnan. Memory neuron networks for identification and control of dynamical systems. IEEE Transactions on Nerual Networks. 1994, 5(2): 306-319P
[94] J.Henriques, P.Gil, A.Dourado and H.D.Ramos. Application of a recurrent neural network in on-line modeling of real-time systems. Proceedings of Eann-Engineering Applications of Neural Networks. Gibraltar.1998: 118-121P
[95] J.Henriques, A.Dourado. Multivariable adaptive control using a recurrent neural network. Proceedings of Eann-Engineering Applications of Neural Networks. Gibraltar. 1998:118-121P
[96] Y.M.Chiang, L.C.Chang and F.J.Chang. Comparison of static feed-forward and dynamic feed-forward neural networks for rainfall-runoff modeling. Journal of Hydrology. 2004, 290:297-311P
[97] V.Prasad, B.W.Bequette. Nonlinear system identification and model reduction using artificial neural networks. Computers and Chemical Engineering. 2003, 27:1741-1754P
[98] A.Aussem. Dynamical recurrent neural networks towards predictionand modeling of dynamical systems. Neurocomputing. 1999, 28: 207-232P
[99] A.Yazdizadeh, K.Khorasani. Adaptive time delay neural network structure for nonlinear system identification. Neurocomputing.2002, 47:207-240P
[100] 魏民祥，闫桂荣，沈亚鹏．基于动态神经网络非线性结构辨识的研究．应用力学学报，2000，17(2)：110-113页
[101] 刘贺平，张兰玲，孙一康．多层局部回归神经网络的非线性系统预测模型．北京科技大学学报，2000，22(2)：190-192P
[102] M.W.Mak, K.W.Ku and Y.L.Lu. On the improvement of the real time recurrent learning algorithm for recurrent neural networks. Neurocomputing. 1999, 24:13-36P
[103] A.G.Parlos, O.T.Rais and A.F.Atiya. Multi-step-ahead prediction using dynamical recurrent neural networks. Neural Networks. 2000, 13: 765-786P
[104] P.Werbos. Backpropagation through time: what it does and how do itProceedings of IEEE. 1990, 78(10): 1550-1560P
[105] S.Stroeve. An analysis of learning control by backpropagation through time. Neural Networks. 1998, 11: 709-721P
[106] R.Williams; D.Zipser. Gradient-based learning algorithms for recurrent networks and their computational complexity. Backpropagation. Edit by Yves Chauvin and D. Rumelhart, Chap. 13.1995, 433-486P
[107] K.S.Narendra, K.Parthasarathy. Gradient methods for the optimization of dynamical systems containing neural networks. IEEE Transactions on Neural Networks. 1991, 2(2):252-262P
[108] 郭健．一类非线性系统广义预测控制研究．南京理工大学博士论文．2002
[109] 郭健，陈庆伟等．一类非线性系统的自适应预测控制．控制理论与应用．2002，19(1)：68-72页
[110] 郭健，陈庆伟等．一类非线性系统的稳定自适应控制．控制理论与应用．2003，20(4)：603-606页
[111] 郭健，陈庆伟等．补偿预测误差非线性系统广义预测控制．南京理工大学学报．2005，29(2)：127-131页
[112] A.M.Alotaiwi. Generalized predictive control of ship coupling motions using active flume tanks. Old Dominion University. Ph.D Thesis. 2003
[113] J.S.Riedel and A.J.Healy. Model based predictve control of AUVs for station keeping in a shallow water wave environmnet. http://web.nps.navy.mil/～me/healey/papers/iarp_jeff.PDF
[114] 葛锁良，陈学军，邱丹．神经网络预测控制及其在二级倒立摆中的仿真．自动化技术与应用．2005，24(6)：4-12页
[115] 宫赤坤，闫雪．基于RBF神经网络的预测控制．上海理工大学学报．2005，27(5)：421-424页
[116] N.Constantin. Adaptive neural predictive technologies for non-linear control. Studies in Informatics and Control. 2003, 12(4):285-291P
[117] 李奇安．广义预测控制算法简化实现方法研究．浙江大学博士论文．2005
[118] 卢勇，徐向东．基于神经网络模型的锅炉广义预测控制．热能动力工程．2001，16(1)：55-58页，69页
[119] W.Naeem, R.Sutton, and S.M.Ahmad, LQG/LTR control of an autonomous underwater vehicle using a hybrid guidance law. In Proceedings of GCUV'03 conference. Newport, UK. 2003: 35-40P
[120] W.Naeem, R.Sutton, S. M.Ahmad and R.S.Bums. A Review of Guidance Laws Applicable to Unmanned Underwater Vehicles. Journal of Navigation. 2003, 56(1): 15-29P
[121] 李和军．水下机器人的神经网络预测控制技术研究．哈尔滨工程大学硕士论文．2004
[122] 张铭钧，段群杰．基于神经网络的水下机器人运动预测控制方法．中国造船．2001，42(3)：43-51页