摘要
表面肌电信号作为人的生理电信号,能够准确、实时地反映肌肉的活动状态和功能状态,可预测人体的运动意图等。采集人体下肢相关肌肉束的表面肌电信号,利用神经网络预测下肢髋关节、膝关节和踝关节的运动信息,建立表面肌电信号和下肢各关节的映射关系。然后利用MATLAB联合ADAMS仿真系统验证表面肌电信号作为外骨骼机器人输入控制信号的动态性能和可行性。最后通过离线功能性实验测试平台,验证机械腿的基本功能,为后续人机交互实时控制奠定了基础。
EMG signals of the muscle bundles on human lower limbs are collected in this paper.The neural network is used to predict the motion information of the lower limbs of the hip joint,knee joint and ankle joint,and to establish the mapping relationship between the EMG signals and the joints on lower limbs.Then,the simulation system of MATLAB and ADAMS is used to verify the dynamic performance and feasibility of the surface EMG signals as the input control signal of the exoskeleton robot.Finally,through the off-line functional test platform,the basic function of the mechanical leg is verified.
出处
《工业控制计算机》
2018年第6期56-58,共3页
Industrial Control Computer
关键词
肌电信号
神经网络
映射控制
联合仿真
EMG signals
neural network
mapping control
joint simulation
