基于改进三元模型的波纹管型气动软体驱动器神经网络滑模控制  

Neural Network Sliding Mode Control of Bellows-type Pneumatic Soft Actuators Based on Improved Ternary Model

作　　者：吕播阳 孟庆鑫 肖怀 赖旭芝 王亚午 吴敏 LYU Boyang;MENG Qingxin;XIAO Huai;LAI Xuzhi;WANG Yawu;WU Min(School of Automation,China University of Geosciences,Wuhan,430074;Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems,Wuhan,430074;Engineering Research Center of Intelligent Technology for Geo-Exploration,Ministry of Education,Wuhan,430074)

机构地区：[1]中国地质大学(武汉)自动化学院,武汉430074 [2]复杂系统先进控制与智能自动化湖北省重点实验室,武汉430074 [3]地球探测智能化技术教育部工程研究中心,武汉430074

出　　处：《中国机械工程》2024年第8期1414-1425,共12页China Mechanical Engineering

基　　金：国家自然科学基金(62203408);湖北省自然科学基金创新群体项目(2015CFA010);高等学校学科创新引智计划(B17040);中国地质大学(武汉)“地大学者”人才岗位科研启动经费(2022088)。

摘　　要：针对一款波纹管型气动软体驱动器,提出了一种基于改进三元模型的滑模控制方法,并使用RBF神经网络补偿扰动以实现该型驱动器在竖直方向上对期望轨迹的跟踪控制。首先搭建波纹管型气动软体驱动器实验平台,测试并分析该驱动器的动态特性,基于上述动态特性提出波纹管型气动软体驱动器的改进三元模型;然后利用采集到的实验数据,基于最小二乘算法对其进行参数辨识,从而获得所提模型的参数;进而结合改进三元模型设计滑模控制器,使用RBF神经网络对集总扰动进行补偿,并利用Lyapunov方法分析系统的稳定性;最后通过一系列实验验证了所提方法的有效性。A sliding mode control method was proposed based on an improved ternary model for a bellows-type pneumatic soft actuator,and an RBF neural network was used to compensate the aggregate set disturbance to achieve tracking control of the desired trajectory in the vertical direction of this type of actuators.Firstly,an experimental platform was constructed to test and analyse the dynamic characteristics of the bellows-type pneumatic soft actuators.Based on the above dynamic characteristics,an improved ternary model of the bellows-type pneumatic soft actuators was proposed.Meanwhile,the parameters of the proposed model were obtained by using the collected experimental data for parameter identification based on the least squares algorithm.Then,the sliding mode controller was designed in conjunction with the improved ternary model,and the RBF neural network was used to compensate for the aggregate set disturbance.The stability of the system was analysed by using the Lyapunov method.Finally,the effectiveness of the proposed method was verified through a series of experiments.

关 键 词：波纹管 气动软体驱动器 三元模型 滑模控制 径向基函数神经网络 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]