基于足底压力传感器的不控制减重比例下步态相位识别
|
摘要
下肢外骨骼机器人是帮助下肢运动功能障碍患者步行训练的新手段,能够减轻医护人员的劳动强度,它常采用减重方式完成辅助训练。然而,对于地面行走减重外骨骼机器人系统而言,其减重比例随步态及穿戴方式变化而变化,因此不控制减重比例下的步态相位识别具有重要意义。通过搭建基于Arduino Mega2560板卡和单侧鞋内8个薄膜式压力传感器的足底压力采集系统,分别采集了正常行走、不控制减重比例减重带减重状态下行走时的足底压力信息,并采用神经网络算法进行步态相位识别。结果表明:在减重状态下行走与正常行走相比,左右脚压力值均出现明显下降且两侧具有对称性;足底每个压力传感器处的压力减小比例不同;采用神经网络算法对正常行走时步态相位总体识别率达到96.8%,对减重行走时步态相位总体识别率达到94.8%。研究结果表明该足底压力采集系统可以有效测量减重行走时的足底压力,为在地面不控制减重比例下减重带减重的外骨骼机器人控制策略的制定提供一定支持。
The lower extremity exoskeleton robot is a new means to help patients with lower extremity motor dysfunction,which can reduce the labor intensity of therapists.Body weight support is often used to complete the auxiliary training.However,for the ground walking weight-loss exoskeleton robot system,the ratio of body weight support would change with the gait and wearing situation,so it is important to recognize the gait phase under proportion-uncontrolled body weight support.A plantar pressure acquisition system based on the Arduino Mega2560 board and eight single-membrane pressure sensors in one side shoe was established,and the plantar pressure information of normal walking and body weight support walking with weight-loss belt under proportion-uncontrolled body weight support was collected.Then,the gait phase recognition was carried out using neural network algorithm.The results showed that the pressure values of left and right feet significantly decreased and two sides were symmetrical in body weight support walking compared with normal walking,but the pressure reduction ratio of each pressure sensor was different.The gait phase recognition rate of normal walking reached96.8% and the gait phase recognition rate of body weight support walking could still reach 94.8% by using neural network algorithm.The research results show that the plantar pressure acquisition system can effectively measure the plantar pressure under body weight support walking,and provide some support for the formulation of control strategy for body weight support exoskeleton robots with weightloss belt under proportion-uncontrolled body weight support on the ground.
The lower extremity exoskeleton robot is a new means to help patients with lower extremity motor dysfunction,which can reduce the labor intensity of therapists.Body weight support is often used to complete the auxiliary training.However,for the ground walking weight-loss exoskeleton robot system,the ratio of body weight support would change with the gait and wearing situation,so it is important to recognize the gait phase under proportion-uncontrolled body weight support.A plantar pressure acquisition system based on the Arduino Mega2560 board and eight single-membrane pressure sensors in one side shoe was established,and the plantar pressure information of normal walking and body weight support walking with weight-loss belt under proportion-uncontrolled body weight support was collected.Then,the gait phase recognition was carried out using neural network algorithm.The results showed that the pressure values of left and right feet significantly decreased and two sides were symmetrical in body weight support walking compared with normal walking,but the pressure reduction ratio of each pressure sensor was different.The gait phase recognition rate of normal walking reached96.8% and the gait phase recognition rate of body weight support walking could still reach 94.8% by using neural network algorithm.The research results show that the plantar pressure acquisition system can effectively measure the plantar pressure under body weight support walking,and provide some support for the formulation of control strategy for body weight support exoskeleton robots with weightloss belt under proportion-uncontrolled body weight support on the ground.
引文
[1]马青川,季林红,王人成,等.用于截瘫患者康复训练的足底轮式驱动外骨骼[J].清华大学学报(自然科学版),2017,57(6):597-603.doi:CNKI:SUN:QHXB.0.2017-06-007MA Qing-chuan,JI lin-hong,WANG Ren-cheng,et al.Foot-wheel driven exoskeleton for rehabilitation training of paraplegic patients[J].Journal of Tsinghua University(Science and Technology),2017,57(6):597-603.
[2]YIN Y H,FAN Y J,XU L D.EMG and EPP-integrated human-machine interface between the paralyzed and rehabilitation exoskeleton[J].IEEE Transactions on Information Technology in Biomedicine,2012,16(4):542-549.doi:10.1109/titb.2011.2178034
[3]KIGUCHI K,TANAKA T,FUKUDA T,et al.Neurofuzzy control of a robotic exoskeleton with EMG signals[J].IEEE Transactions on Fuzzy Systems,2004,2(4):481-490.doi:10.1109/tfuzz.2004.832525
[4]MA J,ZHANG Y,CICHOCKI A,et al.A novel EOG/EEG hybrid human-machine interface adopting eye movements and ERPS:application to robot control[J].IEEE Transactions on Biomedical Engineering,2015,62(3):876-889.doi:10.1109/tbme.2014.2369483
[5]HORTAL E,PLANELLES D,COSTA A,et al.SVM-based brain-machine interface for controlling a robot arm through four mental tasks[J].Neurocomputing,2015,151:116-121.doi:10.1016/j.neucom.2014.09.078
[6]黄梓亮,方晨昊,欧阳小平,等.基于多信息融合的下肢外骨骼机器人感知系统研究[J].工程设计学报,2018,25(2):159-166.doi:10.3785/j.issn.1006-754X.2018.02.005HUANG Zi-liang,FANG Chen-hao,OUYANG Xiaoping,et al.Research on the sensing system of lower limb exoskeleton robot based on multi-information fusion[J].Chinese Journal of Engineering Design,2018,25(2):159-166.
[7]JUNG J Y,HEO W,YANG H,et al.A neural networkbased gait phase classification method using sensors equipped on lower limb exoskeleton robots[J].Sensors,2015,15(11):27738-27759.doi:10.3390/s151127738
[8]RAZAK A H A,ZAYEGH A,BEGG R K,et al.Foot plantar pressure measurement system:a review[J].Sensors,2012,12:9884-9912.doi:10.3390/s120709884
[9]HASSAN M,KADONE H,SUZUKI K,et al.Wearable gait measurement system with an instrumented cane for exoskeleton control[J].Sensors,2014,14(1):1705-1722.doi:10.3390/s140101705
[10]KIM J H,HAN J W,KIM D Y,et al.Design of a walking assistance lower limb exoskeleton for paraplegic patients and hardware validation using cop[J].International Journal of Advanced Robotic Systems,2013,10(2):11-13.doi:10.5772/55336
[11]GRAVANO S,IVANENKO Y P,MACCIONI G,et al.A novel approach to mechanical foot stimulation during human locomotion under body weight support[J].Human Movement Science,2011,30(2):352-367.doi:10.1016/j.humov.2010.01.002
[12]FLYNN T W,CANAVAN P K,CAVANAGH P R,et al.Plantar pressure reduction in an incremental weightbearing system[J].Physical Therapy,1997,77:410-416.doi:10.1093/ptj/77.4.410
[13]FANG J.Computer modelling and experimental design of a gait orthosis for early rehabilitation of walking[D].工程设path generation and simulation of dynamic cutting process for five-axis NC machining[J].Chinese Science Bulletin,2010,55(30):3408-3418.doi:10.1007/s11434-010-3247-7
[15]LARTIGUE C,DUC E,AFFOUARD A.Tool path deformation in 5-axis flank milling using envelope surface[J].Computer-Aided Design,2003,35(4):375-382.doi:10.1016/s0010-4485(02)00058-1
[16]CHU Chih-hsing,WU Ping-han,LEI Wei-tai.Tool path planning for 5-Axis flank milling of ruled surfaces considering CNC linear interpolation[J].Journal of Intelligent Manufacturing,2012,23(3):471-480.doi:10.1007/s10845-010-0386-3
[17]石国春.关于序列二次规划(SQP)算法求解非线性规划问题的研究[D].兰州:兰州大学数学与统计学院,2009:7-12.··196Glasgow,Scotland:University of Glasgow,College of Science and Engineering,2013:104-107.
[14]CHAU T.A review of analytical techniques for gait data.Part 1:Fuzzy,statistical and fractal methods[J].Gait and Posture,2001,13(1):49-66.doi:10.1016/s0966-6362(00)00094-1
[15]CHAU T.A Review of analytical techniques for gait data.Part 2:Neural network and wavelet methods[J].Gait and Posture,2001,13(2):102-120.doi:10.1016/s0966-6362(00)00095-3
[16]马玉良,马云鹏,张启忠,等.GA-BP神经网络在下肢运动步态相位识别中的应用研究[J].传感技术学报,2013,26(9):1183-1187.doi:10.3969/j.issn.1004-1699.2013.09.001MA Yu-liang,MA Yun-peng,ZHANG Qi-zhong,et al.Gait phase recognition of lower limb based on GA opti‐mized BP neural network[J].Chinese Journal of Sensors and Actuators,2013,26(9):1183-1187.
[17]MIJAILOVI N,GAVRILOVI M,RAFAJLOVI S.Gait phases recognition from accelerations and ground reaction forces:application of neural networks[J].Telfor Journal,2009,1(1):34-37.学报第26卷SHI Guo-chun.Research on solving nonlinear program‐ming problems by sequential quadratic programming(SQP)algorithm[D].Lanzhou:Lanzhou University,School of Mathematics and Statistics,2009:7-12.
[18]JORGE N,STEPHEN W.Numerical optimization[M].Berlin:Springer,2006:121-180.
[19]黄鑫.“S”形试件几何质量测评及不确定度研究[D].天津:天津大学机械工程学院,2016:69-85.HUANG Xin.Research on geometry quality evaluation and uncertainty for S-shaped test part[D].Tianjin:Tianjin University,School of Mechanical Engineering,2016:69-85.
[2]YIN Y H,FAN Y J,XU L D.EMG and EPP-integrated human-machine interface between the paralyzed and rehabilitation exoskeleton[J].IEEE Transactions on Information Technology in Biomedicine,2012,16(4):542-549.doi:10.1109/titb.2011.2178034
[3]KIGUCHI K,TANAKA T,FUKUDA T,et al.Neurofuzzy control of a robotic exoskeleton with EMG signals[J].IEEE Transactions on Fuzzy Systems,2004,2(4):481-490.doi:10.1109/tfuzz.2004.832525
[4]MA J,ZHANG Y,CICHOCKI A,et al.A novel EOG/EEG hybrid human-machine interface adopting eye movements and ERPS:application to robot control[J].IEEE Transactions on Biomedical Engineering,2015,62(3):876-889.doi:10.1109/tbme.2014.2369483
[5]HORTAL E,PLANELLES D,COSTA A,et al.SVM-based brain-machine interface for controlling a robot arm through four mental tasks[J].Neurocomputing,2015,151:116-121.doi:10.1016/j.neucom.2014.09.078
[6]黄梓亮,方晨昊,欧阳小平,等.基于多信息融合的下肢外骨骼机器人感知系统研究[J].工程设计学报,2018,25(2):159-166.doi:10.3785/j.issn.1006-754X.2018.02.005HUANG Zi-liang,FANG Chen-hao,OUYANG Xiaoping,et al.Research on the sensing system of lower limb exoskeleton robot based on multi-information fusion[J].Chinese Journal of Engineering Design,2018,25(2):159-166.
[7]JUNG J Y,HEO W,YANG H,et al.A neural networkbased gait phase classification method using sensors equipped on lower limb exoskeleton robots[J].Sensors,2015,15(11):27738-27759.doi:10.3390/s151127738
[8]RAZAK A H A,ZAYEGH A,BEGG R K,et al.Foot plantar pressure measurement system:a review[J].Sensors,2012,12:9884-9912.doi:10.3390/s120709884
[9]HASSAN M,KADONE H,SUZUKI K,et al.Wearable gait measurement system with an instrumented cane for exoskeleton control[J].Sensors,2014,14(1):1705-1722.doi:10.3390/s140101705
[10]KIM J H,HAN J W,KIM D Y,et al.Design of a walking assistance lower limb exoskeleton for paraplegic patients and hardware validation using cop[J].International Journal of Advanced Robotic Systems,2013,10(2):11-13.doi:10.5772/55336
[11]GRAVANO S,IVANENKO Y P,MACCIONI G,et al.A novel approach to mechanical foot stimulation during human locomotion under body weight support[J].Human Movement Science,2011,30(2):352-367.doi:10.1016/j.humov.2010.01.002
[12]FLYNN T W,CANAVAN P K,CAVANAGH P R,et al.Plantar pressure reduction in an incremental weightbearing system[J].Physical Therapy,1997,77:410-416.doi:10.1093/ptj/77.4.410
[13]FANG J.Computer modelling and experimental design of a gait orthosis for early rehabilitation of walking[D].工程设path generation and simulation of dynamic cutting process for five-axis NC machining[J].Chinese Science Bulletin,2010,55(30):3408-3418.doi:10.1007/s11434-010-3247-7
[15]LARTIGUE C,DUC E,AFFOUARD A.Tool path deformation in 5-axis flank milling using envelope surface[J].Computer-Aided Design,2003,35(4):375-382.doi:10.1016/s0010-4485(02)00058-1
[16]CHU Chih-hsing,WU Ping-han,LEI Wei-tai.Tool path planning for 5-Axis flank milling of ruled surfaces considering CNC linear interpolation[J].Journal of Intelligent Manufacturing,2012,23(3):471-480.doi:10.1007/s10845-010-0386-3
[17]石国春.关于序列二次规划(SQP)算法求解非线性规划问题的研究[D].兰州:兰州大学数学与统计学院,2009:7-12.··196Glasgow,Scotland:University of Glasgow,College of Science and Engineering,2013:104-107.
[14]CHAU T.A review of analytical techniques for gait data.Part 1:Fuzzy,statistical and fractal methods[J].Gait and Posture,2001,13(1):49-66.doi:10.1016/s0966-6362(00)00094-1
[15]CHAU T.A Review of analytical techniques for gait data.Part 2:Neural network and wavelet methods[J].Gait and Posture,2001,13(2):102-120.doi:10.1016/s0966-6362(00)00095-3
[16]马玉良,马云鹏,张启忠,等.GA-BP神经网络在下肢运动步态相位识别中的应用研究[J].传感技术学报,2013,26(9):1183-1187.doi:10.3969/j.issn.1004-1699.2013.09.001MA Yu-liang,MA Yun-peng,ZHANG Qi-zhong,et al.Gait phase recognition of lower limb based on GA opti‐mized BP neural network[J].Chinese Journal of Sensors and Actuators,2013,26(9):1183-1187.
[17]MIJAILOVI N,GAVRILOVI M,RAFAJLOVI S.Gait phases recognition from accelerations and ground reaction forces:application of neural networks[J].Telfor Journal,2009,1(1):34-37.学报第26卷SHI Guo-chun.Research on solving nonlinear program‐ming problems by sequential quadratic programming(SQP)algorithm[D].Lanzhou:Lanzhou University,School of Mathematics and Statistics,2009:7-12.
[18]JORGE N,STEPHEN W.Numerical optimization[M].Berlin:Springer,2006:121-180.
[19]黄鑫.“S”形试件几何质量测评及不确定度研究[D].天津:天津大学机械工程学院,2016:69-85.HUANG Xin.Research on geometry quality evaluation and uncertainty for S-shaped test part[D].Tianjin:Tianjin University,School of Mechanical Engineering,2016:69-85.