Adaptive Compensation Control of Closed-chain Lower Limb Rehabilitation Robots Based on the RBF Neural Network

Li Dongqi; Qin Jianjun; Sun Maolin; Zheng Haoran; Li Wei

doi:10.16578/j.issn.1004.2539.2024.04.008

您当前的位置：

首页 >

文章列表页 >

Adaptive Compensation Control of Closed-chain Lower Limb Rehabilitation Robots Based on the RBF Neural Network

Design· Calculation | 更新时间：2024-04-19

- Adaptive Compensation Control of Closed-chain Lower Limb Rehabilitation Robots Based on the RBF Neural Network
- Journal of Mechanical Transmission Vol. 48, Issue 4, Pages: 60-68(2024)
- 作者机构：
  
  1.北京建筑大学机电与车辆工程学院，北京 100044
  2.北京市建筑安全监测工程技术研究中心，北京 100044
  3.国家体育总局运动医学研究所，北京 100061
- 作者简介：
- 基金信息：
- DOI：10.16578/j.issn.1004.2539.2024.04.008
  CLC：
- Published：15 April 2024，
  
  Received：14 December 2022，
  
  Revised：06 March 2023，
扫描看全文
李东琦,秦建军,孙茂琳等.基于RBF神经网络的闭链下肢康复机器人自适应补偿控制[J].机械传动,2024,48(04):60-68.

Li Dongqi,Qin Jianjun,Sun Maolin,et al.Adaptive Compensation Control of Closed-chain Lower Limb Rehabilitation Robots Based on the RBF Neural Network[J].Journal of Mechanical Transmission,2024,48(04):60-68.
李东琦,秦建军,孙茂琳等.基于RBF神经网络的闭链下肢康复机器人自适应补偿控制[J].机械传动,2024,48(04):60-68. DOI： 10.16578/j.issn.1004.2539.2024.04.008.

Li Dongqi,Qin Jianjun,Sun Maolin,et al.Adaptive Compensation Control of Closed-chain Lower Limb Rehabilitation Robots Based on the RBF Neural Network[J].Journal of Mechanical Transmission,2024,48(04):60-68. DOI： 10.16578/j.issn.1004.2539.2024.04.008.

摘要

在下肢康复机器人的康复训练过程中，模型参数、环境干扰等不确定性因素会影响机器人轨迹跟踪的精度。针对这一问题，提出了一种基于径向基函数（Radial Basis Function，RBF）神经网络的自适应补偿控制，该控制方法能够提高机械系统轨迹跟踪的精确性。首先，设计一款具有4种工作模式、运动稳定的闭链卧式下肢康复机器人结构；然后，利用拉格朗日方法求解动力学名义模型，将康复装置的模型参数以及外界干扰等不确定性因素分离出来，并设计基于RBF神经网络的自适应补偿算法对其进行逼近控制；最后，通过Matlab/Simulink环境对其进行仿真验证，证明了该控制策略的有效性。结果显示，在人体步态曲线轨迹跟踪中，提出的基于RBF神经网络的自适应补偿算法相比传统的模糊比例-积分-微分（Proportional Integral Derivative，PID）控制的方法响应速度快、跟踪效果好，且髋关节和膝关节轨迹跟踪的角度误差峰值分别为0.08°和0.13°，远小于患者下肢在康复运动中的转动角度。设计了单腿样机试验，试验结果表明，采用的RBF补偿自适应控制器能够实现高精度的跟踪结果，也能够满足患者在康复训练中安全性的要求。

Abstract

In the rehabilitation training process of lower limb rehabilitation robots

the existence of uncertain factors such as model parameters and environmental interference will affect the accuracy of trajectory tracking of the robot. To solve this problem

an adaptive compensation control based on the radial basis function (RBF) neural network is proposed. This control method can improve the accuracy of mechanical system trajectory tracking. Firstly

a closed chain horizontal lower limb rehabilitation robot structure with four working modes and stable movement is designed. Secondly

the Lagrange method is used to solve the kinetic nominal model

the uncertainty factors such as model parameters and external interference of the rehabilitation device are separated

and the adaptive compensation algorithm based on the RBF neural network is designed for the approximate control. Finally

the Matlab/Simulink environment is used to verify the effectiveness of the control strategy. The results show that

compared with the traditional fuzzy proportional integral derivative (PID) control method

the adaptive compensation algorithm based on the RBF neural network has a faster response speed and better tracking effect in human gait curve trajectory tracking. Moreover

the peak angle errors of the hip joint and the knee joint trajectory tracking are 0.08° and 0.13° respectively

which are much less than the rotation angle of patients' lower limbs in rehabilitation exercise. A single-leg prototype experiment is designed to show that the RBF compensation adaptive controller used in the study can achieve high precision tracking results and meet the safety requirements of patients in rehabilitation training.

关键词

下肢康复机器人闭链结构RBF神经网络不确定性自适应补偿控制

Keywords

Lower limb rehabilitation robotClosed chain structureRBF neural networkUncertainty Adaptive compensation control

references

陈靓，黄玉平，陶云飞，等.基于阻抗模型的下肢康复机器人交互控制系统设计［J］.计算机测量与控制，2020，28（4）：116-120.

CHEN Liang，HUANG Yuping，TAO Yunfei，et al.Design of interactive control system of lower limb rehabilitation robot based on impedance model［J］.Computer Measurement & Control，2020，28（4）：116-120.

张志茹，李宇，芦宇.下肢康复机器人训练在脑卒中偏瘫患者康复中的应用［J］.临床和实验医学杂志，2018，17（4）：412-415.

ZHANG Zhiru，LI Yu，LU Yu.Application of lower limb rehabilitation robot training in rehabilitation of stroke patients with hemiplegia［J］.Journal of Clinical and Experimental Medicine，2018，17（4）：412-415.

潘钰.下肢康复机器人在脊髓损伤步态训练中的应用［C］//北京国际康复论坛，2014：908-912.

PAN Yu.Application of lower limb rehabilitation robot in gait training of spinal cord injury［C］//Beijing International Rehabilitation Forum，2014：908-912.

侯增广，赵新刚，程龙，等.康复机器人与智能辅助系统的研究进展［J］.自动化学报，2016，42（12）：1765-1779.

HOU Zengguang，ZHAO Xinguang，CHENG Long，et al.Research progress of rehabilitation robots and intelligent assistance systems［J］.Acta Automatica Sinica，2016，42（12）：1765-1779.

BERNHARDT M，FREY M，COLOMBO G，et al.Hybrid force-position control yields cooperative behaviour of the rehabilitation robot LOKOMAT［C］//Proceedings of the 2005 IEEE 9th International Conference on Rehabilitation Robotics，2005：536-539.

KOOPMAN B，VAN A E H F，VAN D K H.Selective control of gait subtasks in robotic gait training：foot clearance support in stroke survivors with a powered exoskeleton［J］.Journal of NeuroEngineering and Rehabilitation，2013，10（1）：3.

EMKEN J L，HARKEMA S J，BERES-JONES J A，et al.Feasibility of manual teach-and-replay and continuous impedance shaping for robotic locomotor training following spinal cord injury［J］.IEEE Transactions on Biomedical Engineering，2008，55（1）：322-334.

袁海辉，葛一敏，甘春标.不确定性扰动下双足机器人动态步行的自适应鲁棒控制［J］.浙江大学学报（工学版），2019，53（11）：2049-2057.

YUAN Haihui，GE Yimin，GAN Chunbiao.Adaptive robust control for dynamic walking of biped robot with uncertain perturbation［J］.Journal of Zhejiang University （Engineering Science），2019，53（11）：2049-2057.

钟斌.不确定关节机器人模型的神经网络补偿自适应控制［J］.机械科学与技术，2017，36（3）：372-377.

ZHONG Bin.Uncertain robot joints model of neural network adaptive compensation control［J］.Mechanical Science and Technology for Aerospace Engineering，2017，36（3）：372-377.

LOOPEZ R，AGUILAR H，SALAZAR S，et al.Adaptive control for passive kinesiotherapy ELLTIO［J］.Journal of Bionic Engineering，2014，11（4）：581-588.

HUSSAIN S，XIE S Q，JAMWAL P K.Control of a robotic orthosis for gait rehabilitation［J］.Robotics and Autonomous Systems，2013，61（9）：911-919.

SHI J，XU L，CHENG G，et al.Trajectory tracking control based on RBF neural network of the lower limb rehabilitation robot［C］//2020 IEEE International Conference on Mechatronics and Automation （ICMA），Beijing，China.2020：117-123.

ZHANG P，ZHANG J，ZHANG Z.Design of RBFNN-based adaptive sliding mode control strategy for active rehabilitation robot［J］.IEEE Access，2020，8：155538-155547.

麻天照.下肢外骨骼康复机器人控制系统设计与研究［D］.成都：电子科技大学，2015：14-15.

MA Tianzhao.Design and research on control system of lower limb exoskeleton rehabilitation robot［D］.Chengdu：University of Electronic Science and Technology of China，2015：14-15.

南登崑.康复医学［M］.4版.北京：人民卫生出版社，2011：46-48.

NAN Dengkun.Rehabilitation medicine［M］.4th ed.Beijing：People's Medical Publishing House，2011：46-48.

李醒.上肢康复机器人拉格朗日动力学简化建模方法的研究［J］.科技创新导报，2015，12（28）：42-43.

LI Xing.Research on simplified Lagrange dynamic modeling method of upper limb rehabilitation robot［J］.Science and Technology Innovation Herald，2015，12（28）：42-43.

尹贵，张小栋，陈江城，等.模型不确定的下肢康复机器人轨迹跟踪自适应控制［J］.电子测量与仪器学报，2016，30（11）：1750-1757.

YIN Gui，ZHANG Xiaodong，CHEN Jiangcheng，et al.Adaptive control of trajectory tracking for lower limb rehabilitation robot with model uncertainty［J］.Journal of Electronic Measurement and Instrumentation，2016，30（11）：1750-1757.

马东，董力元，王立玲，等.移动机器人RBF神经网络自适应PD跟踪控制［J］.控制工程，2020，27（12）：2092-2098.

MA Dong，DONG Liyuan，WANG Liling，et al.RBF neural network adaptive PD tracking control for mobile robots［J］.Control Engineering of China，2020，27（12）：2092-2098.

穆海芳，郭凯，胡波.基于模糊RBF神经网络的康复机器人控制［J］.黑龙江工业学院学报（综合版），2022，22（1）：75-79.

MU Haifang，GUO Kai，HU Bo.Control of rehabilitation robot based on fuzzy RBF neural network［J］.Journal of Heilongjiang University of Technology （Comprehensive Edition），2022，22（1）：75-79.

刘宇，付乐乐，邹新海，等.基于RBF神经网络的MEMS惯性传感器误差补偿方法［J］.重庆理工大学学报（自然科学），2021，35（1）：197-202.

LIU Yu，FU Lele，ZOU Xinhai，et al.Error compensation method for MEMS inertial sensor based on RBF neural network［J］.Journal of Chongqing University of Technology （Natural Science），2021，35（1）：197-202.

程思远，陈广锋.下肢康复外骨骼机器人模糊PID控制研究与仿真［J］.测控技术，2019，38（12）：22-28.

CHENG Siyuan，CHEN Guangfeng.Lower limb rehabilitation exoskeleton robot research and simulation fuzzy PID control［J］.Measurement & Control Technology，2019，38（12）：22-28.

国家技术监督局.中国成年人人体尺寸：GB 10000—1988［S］.北京：中国标准出版社，1988：2-5.

State Bureau of Technical Supervision.Human dimensions of Chinese adults：GB 10000—1988［S］.Beijing：Standards Press of China，1988：2-5.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Adaptive Back-stepping Control of Harmonic Drive Based on the RBF Neural Network

Dynamic Meshing Force Analysis of Parallel Planetary Gear based on RBF Neural Network

Dynamic Surface Control of Harmonic Drive Mechanism based on RBF Neural Network

Related Author

Song Gang

Chen Manyi

Qiu Linfeng

Zhang Jie

Xia Yuan

Xiaohua Hao

Xuewen Song

Jianli Zhang

Related Institution

School of Mechanical and Electronic Engineering, Wuhan University of Technology

Shaoxing Institute for Advanced Research, Wuhan University of Technology

Zhejiang Laifual Drive Co., Ltd.

School of Mechanical Engineering，North University of China

Department of Environmental Engineering and Technology， China Institute for Radiation Protection

⁰