针对AUV在复杂环境下的非线性运动问题，提出一种基于多层感知器人工神经网络（MLP-ANN）的自适应PID控制方案用来实现AUV航向自适应控制。为解决PID固定增益在AUV复杂运动中不能保证高质量响应问题，通过构造人工神经网络模型，使用该模型根据航行状态确定自适应PID控制器的参数变化趋势，并引入动量项在梯度下降法中计算得到更新的参数变化量，实现控制器参数自适应变化，通过Matlab仿真实验表明该方案的可行性。
For the nonlinear motion problem of AUVs in complex environments, an adaptive PID control scheme based on a multilayer perceptron artificial neural network (MLP-ANN) is proposed to achieve adaptive control of AUV heading. To address the issue that fixed PID gains cannot ensure high-quality response in complex AUV motion, an artificial neural network model is constructed. This model determines the parameter variation trend of the adaptive PID controller based on the navigation state. A momentum term is introduced in the gradient descent method to calculate the update parameter variations, achieving adaptive changes in controller parameters. Matlab simulation experiments demonstrate the feasibility of this scheme.
2025,47(10): 72-77 收稿日期：2024-7-8
DOI：10.3404/j.issn.1672-7649.2025.10.012
分类号：U674
基金项目：国家自然科学基金面上项目（52372356）；国家自然科学基金资助项目（52201364）
作者简介：张代雨（1988-），男，博士副教授，研究方向为水下航行器多学科设计优化
参考文献：
[1] 宋保维, 潘光, 张立川, 等. 自主水下航行器发展趋势及关键技术[J]. 中国舰船研究, 2022, 17(5): 27-44.
SONG B W, PAN G, ZHANG L C, et al. Development trend and key technologies of autonomous underwater vehicles[J]. Chinese Journal of Ship Research, 2022, 17(5): 27-44.
[2] 王芳, 万磊, 李晔, 等. 欠驱动AUV的运动控制技术综述[J]. 中国造船, 2010, 51(2): 227-241.
WANG F, WAN L, LI Y, et al. A review of motion control technology for underactuated AUVs[J]. China Shipbuilding, 2010, 51(2): 227-241.
[3] ZHAO SIDE, YUH J. Experimental study on advanced underwater robot control[C]// IEEE Transactions on Robotics, 2005.
[4] 赵蕊, 许建, 王淼, 等. 基于遗传算法和分数阶技术的水下机器人航向控制[J]. 中国舰船研究, 2018, 13(6): 87-93.
ZHAO R, XU J, WANG M, et al. Heading control of AUV based on GA and fractional order technology[J]. Chinese Journal of Ship Research, 2018, 13(6): 87-93.
[5] CHEN Z, ZHANG Y G, NIE Y, et al. Adaptive sliding mode control design for nonlinear unmanned surface vessel using RBFNN and disturbance-observer[J]. IEEE Access, 2020, (8): 45457–45467.
[6] 夏国清, 汤莉. 基于动态神经网络的AUV航向自适应控制[J]. 船舶工程, 2009, 31(2): 46-49.
XIA G Q, TANG L. Adaptive heading control of AUV based on dynamic neural network[J]. Ship Engineering, 2009, 31(2): 46-49.
[7] 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]. Marine Science and Technology, 2015, 20: 559–578.
[8] 敖邦乾, 姜孝均, 董泽芳, 等. 基于神经网络-PID 控制的水面无人艇控制系统设 计[J]. 控制工程, 2024, 31(7): 1178-1184.
AO B Q, JIANG X J, DONG Z F, et al. Design of unmanned surface vehicle control system based on neural Network-PID control[J]. Control Engineering of China, 2024, 31(7): 1178-1184.
[9] JI H L, PAN M L. A neural network adaptive controller design for free-pitch-angle diving behavior of an autonomous underwater vehicle[J]. Robotics and Autonomous System, 2005, 52(2-3), 132–147.
[10] YANG M, SHENG Z B, YIN G, et al. A recurrent neural network based fuzzy sliding mode control for 4-DOF ROV movements[J]. Ocean Engineering, 2022, 256, 111509,
[11] MUKUND N, SAHJENDRA N S. Adaptive optimal control of an autonomous underwater vehicle in the dive plane using dorsal fins[J]. Ocean Engineering, 2006, 33(3-4): 404–416.
[12] 郭琳钰, 高剑, 焦慧锋, 等. 基于RBF神经网络的自主水下航行器模型预测路径跟踪控制[J]. 西北工业大学学报, 2023, 41(5): 871-877.
GUO L Y, GAO J, JIAO H F, et al. Model predictive path tracking control of autonomous underwater vehicle based on RBF neural network[J]. Journal of Northwestern Polytechnical University, 2023, 41(5): 871-877.
[13] 张肖江, 周春桂, 王志军, 等. 基于BP神经网络PID的水下无人航行器舵机驱动智能控制系统[J]. 探测与控制学报, 2023, 45(2): 109-114.
ZHANG X J, ZHOU C G, WANG Z J, et al. Underwater UAV steering gear driven intelligent control system based on BP neural network[J]. Journal of Detection and Control, 2023, 45(2): 109-114.
[14] 包涛, 董早鹏, 张波, 等. 基于GD-FNN和参考模型的无人艇航向鲁棒自适应控制[J]. 船舶力学, 2021, 25(5): 598-606.
BAO T, DONG Z P, ZHANG B, et al. Robust adaptive heading control of high-speed USV based on GD-FNN[J]. Ship Mechanics, 2021, 25(5): 598-606.
