[1]孙国安,赵　明,张廷丰,等.基于肌电预测模型的下肢外骨骼自适应控制方法[J].郑州大学学报(工学版),2025,46(03):34-41.[doi:10.13705/j.issn.1671-6833.2025.03.012]
　SUN Guoan,ZHAO Ming,ZHANG Tingfeng,et al.Adaptive Control Method of Lower Limb Exoskeleton Based on Myoelectric Prediction Model[J].Journal of Zhengzhou University (Engineering Science),2025,46(03):34-41.[doi:10.13705/j.issn.1671-6833.2025.03.012]
点击复制

基于肌电预测模型的下肢外骨骼自适应控制方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
46
期数:
2025年03期
页码:
34-41
栏目:
出版日期:
2025-05-13

文章信息/Info

Title:
Adaptive Control Method of Lower Limb Exoskeleton Based on Myoelectric Prediction Model
文章编号:
1671-6833(2025)03-0034-08
作者:
孙国安1; 2;  赵　明1;  张廷丰2;  张　弼1
1.中国科学院沈阳自动化研究所 机器人学国家重点实验室,辽宁 沈阳 110016;2.辽宁工业大学 电气工程学院,辽宁 锦州 121000
Author(s):
SUN Guoan1; 2;  ZHAO Ming1;  ZHANG Tingfeng2;  ZHANG Bi1
1.State Key Laboratory of Robotics, Shenyang Institute of Automation, CAS, Shenyang 110016, China; 2.School of Electrical Engineering, Liaoning University of Technology, Jinzhou 121000, China
关键词:
康复机器人;  表面肌电信号;  滑模控制;  轨迹跟踪
Keywords:
rehabilitation robot;  surface electromyography signal;  sliding mode control;  trajectory tracking
分类号:
TP242
DOI:
10.13705/j.issn.1671-6833.2025.03.012
文献标志码:
A
摘要:
为提高下肢康复机器人的适应性,实时响应患者意图和适应个体化运动需求,提出了一种基于肌电预测模型的下肢外骨骼自适应控制方法。该方法通过采集股二头肌、股直肌和股外侧肌的表面肌电信号,构建预测患者期望运动轨迹的肌电预测模型。针对系统的不确定性和模型误差,设计了一种自适应滑模控制器,结合肌肉激活度动态调整滑模参数,从而提高机器人的跟踪精度和柔顺性。对5名健康受试者进行实验,分别对肌电模型和滑模控制器进行测试。结果表明:肌电预测模型对髋关节的RMSE为7.94,对膝关节的RMSE为9.31,能够满足轨迹生成需求;相比传统PID控制,自适应滑模控制器的跟踪精度提高了28%,验证了所提方法的有效性。
Abstract:
In order to improve the adaptability of lower limb rehabilitation robot, such as its difficulty to respond to the patient′s intention in real time, and to adapt to individual motion needs, in this study, an adaptive control method of lower limb exoskeleton was proposed based on myoelectric prediction model. By collecting the surface EMG signals of biceps femoris, rectus femoris and lateral femoris muscles, the EMG prediction model was constructed to predict the expected motion trajectory of patients. Aiming at the uncertainties and model errors of the system, an adaptive sliding mode controller was designed to dynamically adjust sliding mode parameters according to muscle activation, so as to improve the tracking accuracy and compliance of the robot. The myoelectric model and sliding mode controller were tested in an experiment with 5 healthy subjects. The results showed that the RMSE of the model was 7.94 for the hip joint and 9.31 for the knee joint, which could meet the need of trajectory generation. Compared with the traditional PID control, the tracking accuracy of the adaptive sliding mode controller was improved by 28%, which proved the effectiveness of the method.

参考文献/References:

[1]GONZALEZ A, GARCIA L, KILBY J, et al. Robotic devices for paediatric rehabilitation: a review of design features[J]. Biomedical Engineering Online, 2021, 20 (1): 89. 

[2]ZHOU B, WANG H, HU F, et al. Accurate recognition of lower limb ambulation mode based on surface electromyography and motion data using machine learning[J]. Computer Methods and Programs in Biomedicine, 2020, 193: 105486. 
[3]XIONG D Z, ZHANG D H, ZHAO X G, et al. Synergybased neural interface for human gait tracking with deep learning[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 2271-2280. 
[4]FLEISCHER C, WEGE A, KONDAK K, et al. Application of EMG signals for controlling exoskeleton robots[J]. Biomedizinische Technik Biomedical Engineering, 2006, 51(5/6): 314-319. 
[5]SUZUKI K, MITO G, KAWAMOTO H, et al. Intentionbased walking support for paraplegia patients with robot suit HAL[J]. Advanced Robotics, 2007, 21(12): 1441-1469. 
[6]FAN Y J, YIN Y H. Active and progressive exoskeleton rehabilitation using multisource information fusion from EMG and force-position EPP[J]. IEEE Transactions on Bio-medical Engineering, 2013, 60(12): 3314-3321. 
[7]张弼, 姚杰, 赵新刚, 等. 一种基于肌电信号的自适应人机交互控制方法[J]. 控制理论与应用, 2020, 37 (12): 2560-2570. 
ZHANG B, YAO J, ZHAO X G, et al. An adaptive human-robot interaction control method based on electromyography signals[J]. Control Theory & Applications, 2020, 37(12): 2560-2570. 
[8]赵佳伟, 朱立忠, 陈万鑫, 等. 基于动态运动基元的6自由度下肢外骨骼步态轨迹规划与控制策略[J]. 信息与控制, 2024, 53(1): 33-46. 
ZHAO J W, ZHU L Z, CHEN W X, et al. Gait trajectory planning and control strategy of 6-DOF lower limb exoskeleton based on dynamic movement primitives[J]. Information and Control, 2024, 53(1): 33-46. 
[9]高建设, 刘陆骐, 王杰, 等. 基于模糊控制的上肢康复机器人变导纳控制[J]. 郑州大学学报(工学版), 2024, 45(1): 12-20. 
GAO J S, LIU L Q, WANG J, et al. Variable admittance control of upper limb rehabilitation robot based on fuzzy control[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(1): 12-20. 
[10] LIU J M, ZHANG Y P, WANG J H, et al. Adaptive sliding mode control for a lower-limb exoskeleton rehabilitation robot[C]∥The 13th IEEE Conference on Industrial Electronics and Applications (ICIEA). Piscataway: IEEE, 2018: 1481-1486. 
[11] RAHMAN M H, KITTEL-OUIMET T, SAAD M, et al. Development and control of a robotic exoskeleton for shoulder, elbow and forearm movement assistance[J]. Applied Bionics and Biomechanics, 2012, 9(3): 275-292.
[12] LI X, ZHANG X, LI X, et al. BEAR-H: an intelligent bilateral exoskeletal assistive robot for smart rehabilitation [J]. IEEE Robotics & Automation Magazine, 2022, 29 (3): 34-46. 
[13]魏浩, 张道辉, 谷亚伦, 等. 基于织物的柔性可穿戴上肢运动辅助系统设计[J]. 机器人, 2024, 46(6): 692-702, 712. 
WEI H, ZHANG D H, GU Y L, et al. Design of a fabric-based soft wearable upper-limb motion assistive system [J]. Robot, 2024, 46(6): 692-702, 712. 
[14] LIU G, ZHANG L, HAN B, et al. sEMG-based continuous estimation of knee joint angle using deep learning with convolutional neural network[C]∥2019 IEEE 15th International Conference on Automation Science and Engineering (CASE). Piscataway: IEEE, 2019: 140-145. 
[15]WANG C, GUO W Y, ZHANG H, et al. sEMG-based continuous estimation of grasp movements by long-short term memory network[J]. Biomedical Signal Processing and Control, 2020, 59: 101774. 
[16]张安琳, 张启坤, 黄道颖, 等. 基于CNN与BiGRU融合神经网络的入侵检测模型[J]. 郑州大学学报(工学版), 2022, 43(3): 37-43. 
ZHANG A L, ZHANG Q K, HUANG D Y, et al. Intrusion detection model based on CNN and BiGRU fused neural network[J]. Journal of Zhengzhou University (Engineering Science), 2022, 43(3): 37-43. 
[17]吴振龙, 莫艺鹏, 王荣花, 等. 基于LSTM和粒子群算法的多机组风电功率预测[J]. 郑州大学学报(工学版), 2024, 45(6): 114-121. 
WU Z L, MO Y P, WANG R H, et al. Multi-unit wind power prediction based on long short-term memory and particle swarm optimization[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(6): 114-121. 
[18] HAN J D, DING Q C, XIONG A B, et al. A state-space EMG model for the estimation of continuous joint movements[J]. IEEE Transactions on Industrial Electronics, 2015, 62(7): 4267-4275. 
[19] ZHONG W J, FU X M, ZHANG M M. A muscle synergy-driven ANFIS approach to predict continuous knee joint movement[J]. IEEE Transactions on Fuzzy Systems, 2022, 30(6): 1553-1563. 
[20] SU J H, CHENG T, TAN X W, et al. A recurrent neural network based prediction method for continuous joint angle movement[C]∥2023 IEEE 13th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER). Piscataway:IEEE, 2023: 521-526.

更新日期/Last Update: 2025-05-22