基于特征模型的5阶关节伺服系统扰动补偿策略

Disturbance Compensation Strategy for Fifth-order Joint Servomechanism Based on Characteristic Model

针对工业机器人关节伺服系统负载时变和模型不确定性问题,提出将线性扩张状态观测器和基于特征模型的全系数自适应控制相结合的控制策略。建立双惯量柔性关节动力学模型并得到关节伺服系统5阶扩张状态方程。基于该模型设计5阶线性扩张状态观测器,通过该观测器估计系统总扰动并进行扰动补偿,并证明观测器收敛性。基于特征建模的方法,通过实验数据和梯度下降法对特征参数进行辨识,并基于参数值设计全系数自适应控制律,将该控制律结合线性扩张状态观测器设计一种控制策略,对系统进行精确控制。实验结果表明,新的控制策略使系统在变负载扰动工况下的定位精度达到0.003°,正弦信号跟踪误差保持在0.92°以内,系统具有较强的鲁棒性和控制精度。

A control strategy combining the linear extended state observer and full coefficient adaptive control based on characteristic model is proposed for the time-varying load and model uncertainties of industrial robot joint servomechanism.A two-inertia flexible joint dynamics model is established,and the equation of the fifth-order extended state of joint servomechanism was obtained.A fifth-order linear extended state observer is designed based on the model,through which the total disturbance of the system is estimated and compensated,and the convergence of the observer is proved.Based on the method of characteristic modeling,the characteristic parameters are identified by experimental data and gradient descent method,and the full coefficient adaptive control law is designed based on the parameter values.A control strategy is designed to accurately control the system by combining the control law with the linear extended state observer.The experimental results show that the proposed control strategy is used to make the positioning accuracy of the system reach 0.003°under the condition of variable load disturbance and the sinusoidal signal tracking error keep within 0.92°.The system has strong robustness and control accuracy.