Parameters Self-Tuning for Depth Control of AUV Based on RBF Neural Network
-
摘要: 为了保证自主水下航行器(AUV)能够精确潜入固定深度海域, AUV垂平面控制技术非常重要。在基于比例-积分-微分(PID)控制设计控制器的过程中, 为保证控制器能够较好地控制AUV跟踪指定轨迹, 需要对PID参数进行调整, 但参数设定需要反复尝试, 不仅耗费大量时间, 而且不能保障其最优效果。为解决这一问题, 提出了一种基于径向基函数(RBF)神经网络的参数自整定PID控制方法。首先建立AUV垂平面运动模型, 然后设计RBF神经网络结构, 基于梯度下降方法给出了RBF参数以及PID参数的迭代公式, 并设计离散式PID控制器, 最后通过数值仿真验证了所提方法的有效性。仿真结果说明, AUV可以在较短时间内达到指定深度, 且PID各参数均能完成自整定。
-
关键词:
- 自主水下航行器 /
- 深度控制 /
- 径向基函数神经网络 /
- 比例-积分-微分控制 /
- 自整定
Abstract: The autonomous undersea vehicle(AUV) vertical plane control technology is very important while accurately diving into the sea at a fixed depth. In the process of designing the controller based on proportional-integral-deriva- tive(PID) control, the PID parameters need to be adjusted to guarantee that the controller can control the AUV to track specified trajectory accurately, but the parameter setting needs to be tried repeatedly, which consumes much time and cannot guarantee its optimal effect. In order to solve this problem, a PID control method based on radial basis function(RBF) neural network is proposed in this paper for parameter self-tuning. Firstly, a motion model of AUV vertical plane is established, and the RBF neural network structure is designed. Then, an iterative formula of RBF parameters and PID parameters is given based on the gradient descent method, and a discrete PID controller is designed. Finally, the effectiveness of the proposed control method is verified by numerical simulation. Simulation results show that AUV can reach specified depth in a short time, and the PID parameters can be self-tuned. -
[1] Paull L, Saeedi S, Seto M, et al. AUV Navigation and Localization: A Review [J]. IEEE Journal of Oceanic En-gineering, 2014, 39(1): 131-149. [2] Marani G, Song K C, Yuh J. Underwater Autonomous Manipulation for Intervention Missions AUVs[J]. Ocean Engineering, 2009, 36(1): 15-23. [3] 杨泽文, 贾鹤鸣, 宋文龙, 等. 基于高增益观测器的AUV水平面轨迹跟踪控制[J]. 计算机工程与应用, 2017, 53(11): 26-30.Yang Ze-wen, Jia He-ming, Song Wen-long, et al. Horizontal Trajectory Tracking Control of AUV Based on High Gain Observer[J]. Computer Engineering and Ap-plications, 2017, 53(11): 26-30. [4] 李璐琼, 张福斌, 李勇强. 基于自治水下机器人纵向运动的滑模定深控制 [J]. 电子设计工程, 2013, 21(7): 59-61, 64.Li Lu-qiong, Zhang Fu-bin, Li Yong-qiang. Application of Sliding Mode Control for AUV Depth[J]. Electronic Design Engineering, 2013, 21(7): 59-61, 64. [5] 万磊, 张英浩, 孙玉山, 等. 复杂环境下的欠驱动智能水下机器人定深跟踪控制[J]. 上海交通大学学报, 2015, 49(12): 1849-1854.Wan Lei, Zhang Ying-hao, Sun Yu-shan, et al. Depth Control of Underactuated AUV Under Complex Environment[J]. Journal of Shanghai Jiaotong University, 2015, 49(12): 1849-1854. [6] 王洪斌, 苏博, 王跃灵, 等. 基于粒子群优化的AUV定深跟踪有限时间控制[C]//第37届中国控制会议论文集.武汉: 中国控制会议, 2018. [7] Narasimhan M, Singh S N. Adaptive Optimal Control of an Autonomous Underwater Vehicle in the Dive Plane Using Dorsal Fins[J]. Ocean Engineering, 2006, 33(3): 404-416. [8] 杨泽文, 贾鹤鸣, 宋文龙, 等. 欠驱动AUV水平面轨迹跟踪的反步控制研究[J]. 机电工程, 2017, 34(11): 1338-1342.Yang Ze-wen, Jia He-ming, Song Wen-long, et al. Back-stepping Control of the Underactuated AUV in Horizontal Plane Trajectory Tracking[J]. Journal of Mechanical & Electrical Engineering, 2017, 34(11): 1338-1342. [9] Khodayari M H, Balochian S. Modeling and Control of Autonomous Underwater Vehicle(AUV) in Heading and Depth Attitude via Self-Adaptive Fuzzy PID Controller[J]. Journal of Marine Science & Technology, 2015, 20(3): 559-578. [10] Wei C, Wei Y, Zeng J. Back-stepping Control of Under-actuated AUV’s Depth Based on Nonlinear Disturbance Observer[C]//Proceedings of the 2015 34th Chinese Control Conference (CCC). Hangzhou, China: CCC, 2015. [11] 贾鹤鸣, 何东旭, 林荣鹏, 等. 基于反步滑模的AUV深度控制研究[J]. 科技创新与生产力, 2018(6): 21-24, 27.Jia He-ming, He Dong-xu, Lin Rong-peng, et al. Research on Depth Control of AUV Based on Backstepping Sliding Mode[J]. Sci-Tech Innovation & Productivity, 2018(6): 21-24, 27. [12] 郭小溪, 李刚, 闫伟杰. 基于遗传算法整定PID的自主潜器深度控制[J]. 长春理工大学学报(自然科学版), 2010, 33(3): 37-39.Guo Xiao-xi, Li Gang, Yan Wei-jie. PID Controller Based On GA For AUV Depth Control[J]. Journal of Changchun University of Science and Technology(Natural Science Edition), 2010, 33(3): 37-39. [13] 王宏健, 陈子印, 贾鹤鸣, 等. 具有PID反馈增益的自主水下航行器反步法变深控制[J]. 控制理论与应用, 2012, 29(9): 1139-1145.Wang Hong-jian, Chen Zi-yin, Jia He-ming, et al. Back-stepping Method with PID Gain Tuning in Diving Control of Autonomous Underwater Vehicle[J]. Control Theory & Applications, 2012, 29(9): 1139-1145. [14] Li J H, Lee P M. A Neural Network Adaptive Controller Design for Free-Pitch-Angle Diving Behavior of an Autonomous Underwater Vehicle[J]. Robotics & Autonomous Systems, 2005, 52(2): 132-147. [15] 汪伟, 边信黔, 王大海. AUV深度的模糊神经网络滑模控制[J]. 机器人, 2003, 25(3): 209-212.Wang Wei, Bian Xin-qian, Wang Da-hai. Fuzzy Neural Network Sliding-Mode Control Of Auto Depth For AUV[J]. Robot, 2003, 25(3): 209-212. [16] 梅新华, 周祥龙. 基于BP网络的双舵型AUV深度控制算法应用[J]. 水雷战与舰船防护, 2017, 25(3): 79-81.Mei Xin-hua, Zhou Xiang-long. Application of Depth Control Algorithm for Double-Rudder Type AUV Based on BP Network[J]. Mine Warfare & Ship Self-Defence, 2017, 25(3): 79-81. [17] Do K D. Control of Ships and Underwater Vehicles[M]. London: Springer 2009. [18] Broomhead D S, Lowe D. Multivariable Functional Interpolation and Adaptive Networks[J]. Complex Systems, 1988, 2(3): 321-355.
点击查看大图
计量
- 文章访问数: 539
- HTML全文浏览量: 20
- PDF下载量: 322
- 被引次数: 0