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
吕播阳 1孟庆鑫 1肖怀 1赖旭芝 1王亚午 1吴敏1
作者信息
- 1. 中国地质大学(武汉)自动化学院,武汉,430074;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;地球探测智能化技术教育部工程研究中心,武汉,430074
- 折叠
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R B F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.
Abstract
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 aggre-gate 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 characteris-tics,an improved ternary model of the bellows-type pneumatic soft actuators was proposed.Mean-while,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Key words
bellow/pneumatic soft actuator/ternary model/sliding mode control/radial basis function(RBF)neural network引用本文复制引用
基金项目
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)
出版年
2024
国家科技期刊平台
NSTL
万方数据