中文摘要：

提出了一种面向偏瘫患者,可实现单关节和多关节运动的5自由度穿戴式上肢康复机器人的控制新方法.根据偏瘫患者上肢单侧受损的特点,该机器人利用偏瘫患者的健肢运动的表面肌电信号（sEMG）驱动康复机械臂辅助患者患肢实现康复训练.利用肌电绝对值积分（IAV）和自回归参数模型法（AR model）对选定的上肢四块肌肉运动产生的sEMG信号进行分析,所提取的特征分别作为基于Levenberg-Marquardt算法的反向传播神经网络的输入,6个上肢运动作为输出建立表面肌电信号与上肢康复动作之间的关系.试验结果表明该方法利用sEMG准确地完成了对上肢康复动作的识别.这一方法有利于提高患者运动积极性,保持正确运动的感觉,并为研究患者受损上肢表面肌电信号与肌肉运动的关系打下了基础.

英文摘要：

A 5 DOF wearable rehabilitation robot which can implement single joint and multi-joint multiple motions for hemiplegic patients was presented. The method of driving rehabilitation robot to help patients＇ impaired limb to carry out rehabilitation exercises by surface Electromyogram（sEMG） from healthy limb of their own is presented. Features extracted from sEMG signals of four upper limb muscles by IAV and AR parameter model method are sent into Levenberg-Marquardt （LM） based back propagation neural network （BPN） as the input, whose output is six upper limb rehabilitation exercise motions, to establish relationship of sEMG signal and motions. Experiments describe the effective result of this method, which is useful for patient to keep the sense of proper motion and active of motion. It lays the groundwork for studying relationship of sEMG signal and motions of patients＇ impaired upper limb.