详细信息
基于肌电信号的膝关节跨越障碍角度预测方法
Prediction of knee joint angle when crossing obstacles based on myoelectric signals
文献类型:期刊文献
中文题名:基于肌电信号的膝关节跨越障碍角度预测方法
英文题名:Prediction of knee joint angle when crossing obstacles based on myoelectric signals
作者:陈天麟[1];戴佺民[1,2];程光[1,2];马勇杰[1];孙佰鑫[1];刘伟锋[1];许晓容[2]
第一作者:陈天麟
机构:[1]北京联合大学机器人学院,北京100101;[2]北京联合大学城市轨道交通与物流学院,北京100101
第一机构:北京联合大学机器人学院
年份:2020
卷号:37
期号:10
起止页码:1293-1301
中文期刊名:中国医学物理学杂志
外文期刊名:Chinese Journal of Medical Physics
收录:CSTPCD;;CSCD:【CSCD_E2019_2020】;
基金:北京市自然科学基金-市教委重点基金(KZ201811417048);北京市自然科学基金-轨道交通联合基金(L191006);北京联合大学人才强校优选计划(BPHR2020DZ03)。
语种:中文
中文关键词:膝关节;跨越障碍;肌肉电信号;BP神经网络;角度预测
外文关键词:knee joint;obstacle crossing;myoelectrical signal;BP neural network;angle prediction
摘要:为解决人体跨越障碍物时膝关节角度输出的问题,针对性设计一种穿戴式信号获取实验台,对下肢运动姿态进行运动分析,将肌肉电信号及关节角度信号作为运动数据,对信号进行处理后利用BP神经网络预测跨越障碍时输出角度,提出一种利用BP神经网络算法,根据不同大腿抬起高度,分析膝关节运动主动肌与被动肌发力程度,预测输出人体跨越障碍时膝关节角度的方法,能够有效帮助假肢膝关节或康复机器人实现跨越障碍的复杂动作。
In order to solve the problem of knee joint angle output when the human body crosses obstacles,a wearable signal acquisition test bench is designed.The motion analysis of the lower limb is carried out,and the myoelectrical signals and joint angle signals are used as motion data.After signal processing,BP neural network is used to predict the output angle when crossing obstacles.Herein a novel method based on BP neural network algorithm is proposed to analyze the forces of knee joint motion active muscle and passive muscle according to different thigh lift heights,and to predict the knee joint angle when the human body crosses obstacles.The proposed method can effectively help the prosthetic knee joint or rehabilitation robots implement the complex movement of obstacle crossing.
参考文献:
正在载入数据...