近海底复杂环境中精细观测作业与精确位置控制等技术对自主水下航行器（AUV）提出了更高的要求。为此本文提出一种基于径向基函数神经网络（RBFNN）的新型自抗扰控制方法。利用自适应RBF神经网络的自学习能力，对扩张状态观测器进行优化，使其对模型不确定部分和环境干扰能够自适应估计，并实现将总扰动在线补偿到控制输入中，实现更佳的扰动估计及控制性能。通过仿真实验发现，与传统自抗扰控制（ADRC）相比，不同阶跃输入下，改进方法具有更小的观测误差，控制稳定性更好，且在较低采样频率下依然可以取得理想的控制效果。仿真结果表明，本文方法能够优化扩张状态观测器的性能，提高AUV在不同阶跃输入及采样频率下的稳定性，简化了控制器调参过程，为实际工程应用提供借鉴。
Technologies such as elaborate observation and accurate position control in the complex environment close to seabed have put forward higher requirement for (autonomous underwater vehicle) AUV. This paper proposes a novel (active disturbance rejection control) ADRC method based on (radial basis function neural network) RBFNN compensation. The extended state observer is optimized so that it can adaptively estimate the uncertain part of the model and the environment disturbances. Then the total internal and external disturbances are compensated online into the control input to realize better disturbances estimation and control performance. Through simulation experiment, it is found that, compared with original ADRC, the improved method has smaller observation error and better controller stability under different step inputs. And it's less affected by the sampling frequency. Simulation results show that the method in this paper can optimize the performance of extended state observer, improve the stability of AUV under different step inputs and sampling frequents, simplify the parameter adjustment process, and provide reference for practical engineering application.
2023,45(18): 85-91 收稿日期：2022-05-30
DOI：10.3404/j.issn.1672-7649.2023.18.014
分类号：U675.91
基金项目：深海光学AUV系统研制及示范应用（2020B1111010004）；深渊AUV研制及与自主对接技术研究（XDA22040103）；国家重点研发计划资助项目（2019YFB1310300）；机器人学国家重点实验室资助项目（2021-Z11L02）
作者简介：乌云嘎(1992-),男,硕士研究生,研究方向为水下机器人控制
参考文献：
[1] 黄琰, 李岩, 俞建成, 等. AUV智能化现状与发展趋势[J]. 机器人, 2020, 42(2): 215–231
HUANG Yan, LI Yan, YU Jiancheng, et al. State-of-the-art and development trends of AUV intelligence[J]. ROBOT, 2020, 42(2): 215–231
[2] HAN J Q. From PID to Active disturbance rejection control[J]. IEEE Transactions on Industrial Electronics, 2009, 56(3): 900–906
[3] ZHANG Y N, DENG H, LI Y Z. Depth control of AUV using sliding mode active disturbance rejection control[C]// 2018 3rd International Conference on Advanced Robotics and Mechatronics (ICARM), 2018: 300–305.
[4] RAOUF F, SOFIANE K, MAHMOUD Y, et al. Active disturbance rejection control for robotic systems: A review[J]. Mechatronics, 2021, 80, 102671, ISSN 0957-4158.
[5] LI M N, ZHANG W, S B. Path track control of underwater vehicle based on active disturbance rejection control[C]// 2021 33rd Chinese Control and Decision Conference (CCDC), 2021, pp. 4658–4663.
[6] GAO Z Q. Scaling and bandwidth-parameterization based controller tuning[C]// Proceedings of the 2003American Control Conference, 2003, 4989–4996.
[7] JIN H Y, SONG J C, LAN W Y. On the characteristics of ADRC: a PID interpretation[J]. Science in China, 2020, 63(10): 254–256.
[8] 崔文庆, 王雨桐, 谭文. 用PID控制近似线性自抗扰控制[J]. 控制理论与应用, 2020, 37(8): 1781–1789
[9] CHEN Z Q, QIN B B, SUN M W. Q-Learning-based parameters adaptive algorithm for active disturbance rejection control and its application to ship course control[J]. Neurocomputing, 2020, 408: 51–63
[10] QIN H Y, TAN P L, CHEN Z Q, et al. Deep reinforcement learning based active disturbance rejection control for ship course control[J]. Neurocomputing, 2022, 484: 99–108
[11] 施生达. 潜艇操纵性[M]. 北京: 国防工业出版社, 2021: 10–11.
[12] FOSSEN, THOR I. Handbook of marine craft hydrodynamics and motion control[M]. John Wiley & Sons Ltd, 2021.
[13] 杨超, 张铭钧, 吴珍臻, 等. 作业型水下机器人纵、横倾姿态自适应区域控制方法[J]. 机器人, 2021, 43(2): 224–233.
[14] 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
[15] LIU W T, ZHAO T. An active disturbance rejection control for hysteresis compensation based on neural networks adaptive control[J]. ISA Transactions, 2021, 109: 81–88
[16] CHEN X, LI D H, GAO Z Q et al. Tuning method for second-order active disturbance rejection control[C]// Processings of the 30th Chinese Control Conference, 2011, pp. 6322–6327.
[17] 袁东, 马晓军, 曾庆含, 等. 二阶系统线性自抗扰控制器频带特性与参数配置研究[J]. 控制理论与应用, 2013, 30(12): 1630–1640
