摘要
针对机械臂动力学模型参数具有不确定性,系统控制精度和收敛速度受到关节摩擦和外部干扰影响的问题,提出一种基于机械臂动力学模型的复合控制策略。结合改进型双幂次趋近律和积分滑模设计滑模控制项,加快跟踪误差的收敛速度;通过3组RBF神经网络分别逼近动力学模型的不确定参数,引入自适应机制对权值进行在线的自适应整定,并采用前述设计的滑模控制项补偿RBF神经网络的逼近误差;利用模糊控制器对关节摩擦和外部干扰进行补偿。仿真结果表明,与基于分块RBF神经网络逼近滑模控制算法相比,所提出的复合控制策略使机械臂关节角速度响应时间缩减39.4%,最大稳态误差缩减76.8%,平均稳态误差缩减62.7%,机械臂关节空间轨迹跟踪的控制精度和响应速度得到显著提高。
To solve the uncertainty of the parameters of the manipulator dynamics model,the control accuracy and convergence rate of the system affected by the joint friction and external interference,a compound control strategy based on the manipulator dynamics model is proposed.Firstly,a modified power-of-two convergence law is used and combined with an integral sliding mode to design a sliding mode control term to shorten the convergence of the tracking error.Secondly,the approximations of the uncertain variables of the dynamical model are accomplished by using the three sets of RBF neural networks and introducing an adaptive mechanism for online self-tuning of weights,the approximation errors of the RBF neural networks are compensated by using the sliding-mode control term designed in the previous section.Finally,the fuzzy controllers are utilized to calculate the coupled joint friction and outside disturbances.The simulation works show that comparing with the chunked RBF neural network to approximate the sliding mode control logy,the proposed hybrid control theory reduces the mechanical arm joint angular rate response time by 39.4%,the largest solid-state error was cut by 76.8%,and the medium-sized solid-state error was cut by 62.7%,improved control preciseness and the responsiveness of the spatial trajectory tracking of the manipulator arm′s joints.
作者
冯嘉庆
张蕾
田冬雨
FENG Jiaqing;ZHANG Lei;TIAN Dongyu(School of Electronic Information,Xi′an Polytechnic University,Xi′an 710048,China;Shaanxi Joint Laboratory of Artificial Intelligence,Xi′an Polytechnic University,Xi′an 710048,China)
出处
《西北工业大学学报》
EI
CAS
CSCD
北大核心
2024年第6期1099-1110,共12页
Journal of Northwestern Polytechnical University
基金
西安市科技计划项目(24GXFW0023)
榆林市科技计划项目(2023⁃CXY⁃184)资助。
关键词
机械臂
轨迹跟踪
自适应RBF神经网络
模糊补偿
积分滑模
mechanical arm
orbit tracking
self-adaptive RBF neural network
fuzzy offset
integral sliding mode
