基于表面肌电信号的人体步态事件快速识别方法

摘要/Abstract

摘要： 针对下肢康复训练机器人主动训练阶段患者运动检测实时性、准确性的需求，提出一种基于动态表面肌电信号的人体步态事件快速识别方法。首先，通过表面肌电信号产生过程数学建模及步态过程中肌肉活动规律分析，给出了基于表面肌电信号强度及其变化特征的步态事件感知原理；其次，以双腿股外侧肌动态表面肌电信号强度及其变化为特征，构建了用于识别支撑和摆动两个步态事件的自适应模糊神经网络模型。实验结果表明：该方法识别结果正确率达95.3%，对足跟触地和脚尖离地事件发生时刻进行识别的平均时间误差分别为21.4ms和24.5ms，同时证明，该方法对步态之间表面肌电信号的差异具有较强的鲁棒性。

关键词: 表面肌电信号, 步态事件, 自适应模糊神经网络, 康复机器人

Abstract: Real-time and accuracy detection of human motion during active training stage were required for lower limb rehabilitation robot. A dynamic surface EMG based human gait events fast recognition method was proposed. Firstly，the surface EMG generation model was established and the skeletal muscle activity during gait was analyzed，the gait event perception method with surface EMG intensity and its variation was put forward. Then，an ANFIS model was built to recognize the supporting phase and swing phase, which used the dynamic surface EMG signals of vastus lateralis lie in the both of left and right thigh as the signal source.The experimental results show that the average correct rate may reach 95.3% compared with results detected from force plate，the average time errors for heel strike (HS) and toe off (TO) timing detection are 21.4ms and 24.5ms respectively. Moreover，the method proposed also shows a strong robustness against the surface EMG difference between gaits.

Key words: surface electromyography(EMG), gait event, adaptive neuro fuzzy inference system(ANFIS), rehabilitation robot

中图分类号:

TP242

陈江城, 张小栋, 尹贵. 基于表面肌电信号的人体步态事件快速识别方法[J]. 中国机械工程.

Chen Jiangcheng, Zhang Xiaodong, Yin Gui. Human Gait Events Fast Recognition Method via Surface Electromyography[J]. China Mechanical Engineering.

参考文献

[1]胡进,侯增广,陈翼雄,等.下肢康复机器人及其交互控制方法[J]. 自动化学报，2014，40(11)：2377-2390.

Hu Jin，Hou Zeng guang，Chen Yixiong，et al. Lower Limb Rehabilitation Robots and Interactive Control Methods[J]. Acta Automatica Sinica，2014，40(11)：2377-2390.

[2]文忠,钱晋武,沈林勇,等.基于阻抗控制的步行康复训练机器人的轨迹自适应[J].机器人，2011，33(1)：142-149.

Wen Zhong，Qian Jinwu，Shen Linyong，et al. Trajectory Adaptation for Impedance Control Based Walking Rehabilitation Training Robot[J]. Robot，2011,33(1):142-149.

[3]Marchal-Crespo L，Reinkensmeyer D J. Review of Control Strategies for Robotic Movement Training after Neurologic Injury[J]. Journal of Neuroengineering and Rehabilitation，2009，6(1)：20.

[4]Riener R，Lunenburger L，Jezernik S，et al.Patient-cooperative Strategies for Robot-aided Treadmill Training：First Experimental Results[J]. Neural Systems and Rehabilitation Engineering，IEEE Transactions on，2005，13(3)：380-394.

[5]Sankai Y. Hal：Hybrid Assistive Limb Based on Cybernics. Robotics Research[J]. Berlin Heidelberg:Springer，2011.

[6]Bernhardt M，Frey M，Colombo G，et al. Hybrid Force-position Control Yields Cooperative Behaviour of the Rehabilitation Robot LOKOMAT[C]//Proceedings of the 9th International Conference on the Rehabilitation Robotics. Chicago，IL，USA：IEEE，2005:536-539.

[7]Giroux M，Moissenet F,Dumas R.EMG-based Validation of Musculo-skeletal Models for Gait Analysis[J]. Computer Methods in Biomechanics and Biomedical Engineering,2013,16（S1）：152-154.

[8]Huang B，Chen M，Shi X，et al.Gait Event Detection with Intelligent Shoes[C]// Proceedings of The International Conference on Information Acquisition. Jeju City，Korea：IEEE，2007：579-584.

[9]Catalfamo P，Moser D，Ghoussayni S，et al.Detection of Gait Events Using an F-Scan in-shoe Pressure Measurement System[J]. Gait & posture，2008，28(3)：420-426.

[10]Heliot R，Pissard-GiboIIet R，Espiau B，et al. Continuous Identification of Gait Phase for Robotics and Rehabilitation Using Microsensors[C]//Proceedings of the 12th International Conference on Advanced Robotics. Seattle，USA：IEEE，2005：686-691.

[11]Williamson R，Andrews B J. Gait Event Detection for FES using Accelerometers and Supervised Machine Learning[J]. Rehabilitation Engineering，IEEE Transactions on，2000，8(3)：312-319.

[12]Hanlon M，Anderson R. Real-time Gait Event Detection Using Wearable Sensors[J]. Gait & Posture，2009，30(4)：523-527.

[13]Wang W，De Stefano A，Allen R. A Simulation Model of the Surface EMG Signal for Analysis of Muscle Activity During the Gait Cycle[J]. Computers in Biology and Medicine，2006，36：601-618.

[14]Roy S H，Cheng M S，Chang S S，et al. A Combined sEMG and Accelerometer System for Monitoring Functional Activity in Stroke[J]. Neural Systems and Rehabilitation Engineering，IEEE Transactions on，2009，17(6)：585-594.

[15]Güler I，beyli E D. Adaptive Neuro-fuzzy Inference System for Classification of EEG Signals Using Wavelet Coefficients[J]. Journal of Neuroscience Methods，2005，148(2)：113-121.