基于SVMBP的下肢外骨骼步态检测及识别研究

doi:10.3901/JME.2022.12.029

机械工程学报 ›› 2022, Vol. 58 ›› Issue (12): 29-38.doi: 10.3901/JME.2022.12.029

扫码分享

基于SVMBP的下肢外骨骼步态检测及识别研究

曾德政, 吕继亮, 屈盛官, 尹鹏, 李小强

华南理工大学机械与汽车工程学院广州 510000

收稿日期:2021-09-06 修回日期:2022-01-23 出版日期:2022-06-20 发布日期:2022-09-14
通讯作者: 屈盛官(通信作者),男,1966年出生,教授,博士,博士研究生导师。主要从事新金属材料的先进制造技术、成形装备的集成和智能制造技术、人工智能外骨骼机器人技术的科研和教学工作。E-mail:qusg@scut.edu.cnsg@scut.edu.cn
作者简介:曾德政,女,1996年出生。主要从事人工智能外骨骼机器人及步态检测识别技术研究。E-mail:201821002525@mail.scut.edu.cn
基金资助:
特种车辆及驱动系统智能制造国家重点实验室开放资助项目（GZ2019KF001）

Research on Gait Detection and Recognition of Lower Limb Exoskeleton Based on SVMBP

ZENG Dezheng, Lü Jiliang, QU Shengguan, YIN Peng, LI Xiaoqiang

School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510000

Received:2021-09-06 Revised:2022-01-23 Online:2022-06-20 Published:2022-09-14

摘要/Abstract

摘要： 下肢外骨骼机器人是一种用于辅助人体下肢运动的智能化可穿戴装置，而人体步态识别是实现外骨骼机器人智能化最重要的技术之一。研制出一种适用于下肢外骨骼机器人的步态检测系统，并将硬件系统集成于智能传感鞋中，小巧而实用；在此基础上以下肢助力外骨骼样机为试验平台，完成了人体步态数据采集试验。另外，将支持向量机(Support vector machine,SVM)和逆传播神经网络(Back propagation neural network,BPNN)算法模型进行优化和整合，提出了基于SVMBP的运动识别算法，试验结果表明基于SVMBP的下肢外骨骼机器人步态检测系统能够完成6路足底压力信号的采集与实时显示，SVMBP算法对步行相位的平均分类识别准确率达99.39%，其平均识别准确率高于单一的SVM和BPNN算法，对于步行中各相位的识别更稳定，增强了算法的可靠性并且提高了算法的识别准确性。

关键词: 智能传感鞋, 步态检测识别, 支持向量机, 神经网络, SVMBP模型, 下肢外骨骼

Abstract: Lower limb exoskeleton (LLEXO) robot is a kind of intelligent wearable device used to assist human lower extremity to achieve power movement. And human gait recognition is one of the most important technologies to realize the intelligence of exoskeleton robot. A gait detection (HG) system was proposed for lower extremity exoskeleton robots, which realized the integration of the device into smart sensor shoes, and it was compact and practical. On this basis, the LLEXO experimental prototype was used to was used to conduct human gait data collection experiments. Meanwhile, the SVMBP motion recognition algorithm was proposed, which was based on the integration of the advantages of the support vector machine (SVM) and back propagation neural network (BPNN) algorithm models. The experimental results show that the SVMBP-based LLEXO HG system c an complete 6 channel plantar pressure signal acquisition and real-time display. And the proposed SVMBP model had an average classification and recognition accuracy of 99.39% for gait data, the average recognition accuracy was higher than the single SVM and BPNN algorithm, and the recognition of each phase during walking was more stable, which enhanced the reliability of the algorithm and improves the recognition accuracy of the algorithm.

Key words: smart sensor shoes, gait detection and recognition, support vector machine, neural network, SVMBP model, lower limb exoskeleton

中图分类号:

TP23

曾德政, 吕继亮, 屈盛官, 尹鹏, 李小强. 基于SVMBP的下肢外骨骼步态检测及识别研究[J]. 机械工程学报, 2022, 58(12): 29-38.

ZENG Dezheng, Lü Jiliang, QU Shengguan, YIN Peng, LI Xiaoqiang. Research on Gait Detection and Recognition of Lower Limb Exoskeleton Based on SVMBP[J]. Journal of Mechanical Engineering, 2022, 58(12): 29-38.

参考文献

[1] ZHU J Y, ZHOU H. Realization of key technology for intelligent exoskeleton load system[C]//Advances in Information Technology and Industry Applications, Lecture Notes in Electrical Engineering, November, 2012, Springer Verlag, Berlin, 2011(136):77-82.
[2] 史小华, 王洪波, 孙利, 等. 外骨骼型下肢康复机器人结构设计与动力学分析[J]. 机械工程学报, 2014, 50(3):41-48. SHI Xiaohua, WANG Hongbo, SUN Li, et al. Design and dynamic analysis of an exoskeletal lower limbs rehabilitation robot[J]. Journal of Mechanical Engineering, 2014, 50(3):41-48.
[3] ZHOU L B, CHEN W H, CHEN W J, et al. Design of a passive lower limb exoskeleton for walking assistance with gravity compensation[J]. Mechanism and Machine Theory, 2020, 150(103840):211-230.
[4] 申京玉, 张仕民, 陈冲, 等. 无动力外骨骼助力机器人研究进展[J]. 机械传动, 2020, 44(2):166-176. SHEN Jingyu, ZHANG Shimin, CHEN Chong, et al. Research progress of unpowered exoskeleton assist robot[J]. Mechanical Transmission, 2020, 44(2):166-176.
[5] 汪步云, 王月朋, 梁艺, 等. 下肢外骨骼助力机器人关节驱动设计及试验分析[J]. 机械工程学报, 2019, 55(23):55-66. WANG Buyun, WANG Yuepeng, LIANG Yi, et al. Design on articular motion&servo driving with experimental analysisfor lower limb exoskeleton robot[J]. Journal of Mechanical Engineering, 2019, 55(23):55-66.
[6] SHI D, ZHANG W X, ZHANG W, et al. A review on lower limb rehabilitation exoskeleton robots[J]. Chinese Journal of Mechanical Engineering, 2019, 32(4):12-22.
[7] LI Z Q, XIE H X, LI W L, YAO Z. Proceeding of human exoskeleton technology and discussions on future research[J]. Chinese Journal of Mechanical Engineering, 2014, 27(3):437-447.
[8] JANG J, KIM K, LEE J, et al, Online gait task recognition algorithm for hip exoskeleton[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems, September 28-October 02, 2015, Hambrg, Germany, IEEE, 2015:5327-5332.
[9] YEUNG L F, OCKENFELD C, PANG M K. Design of an exoskeleton ankle robot for robot-assisted gait training of stroke patients[C]//International Conference on Rehabilitation Robotics (ICORR). International Conference on Rehabilitation Robotics ICORR, July 17-20, 2017, London, England, 2017:211-215.
[10] TAO W J, LIU T, ZHENG R C, et al. Gait analysis using wearable sensors[J]. Sensors, 2015, 12(2):2255-2283.
[11] GORSIC M, KAMNIK M, AMBROZIC L, et al. Online phase detection using wearable sensors for walking with a robotic prosthesis[J]. Sensors, 2014, 14(2):2776-2794.
[12] CHERELLE P, JUNIUS K, GROSU V, et al. The AMP-Foot 2.1:actuator design, control and experiments with an amputee[J]. Robotica, 2014, 32(8):1347-1361.
[13] GUO Q, JIANG D. Method for walking gait identification in a lower extremity exoskeleton based on c4.5 decision tree algorithm[J]. International Journal of Advanced Robotic Systems, 2015, 12(30):1-11.
[14] 石欣, 熊庆宇, 雷璐宁. 基于压力传感器的跌倒检测系统研究[J]. 仪器仪表学报, 2010, 31(3):715-720. SHI Xin, Xiong Qingyu, LEI Luning. Research on fall detection system based on pressure sensor[J]. Chinese Journal of Scientific Instrument, 2010, 31(3):715-720.
[15] GYLLENSTEN I C, BONOMI A G. Identifying types of physical activity with a single accelerometer:evaluating laboratory-trained algorithms in daily life[J]. IEEE transactions on biomedical engineering, 2011, 58(9):2656-2663.
[16] 蔡聪. 基于视频的动物运动跟踪分析系统及应用研究[D]. 武汉:华中科技大学, 2011. CAI Cong. Development and application research on a video-based motion tracking and analysis system for animals[D]. Wuhan:Huazhong University of Science and Technology, 2011.
[17] VAN GESTEL T, SUYKENS J A K, Baesens B, et al.Benchmarking least squares support vector machine classifiers[J]. Machine Learn, 2004, 54(1):5-32.
[18] PAN L Z, SONG A G, XU G Z, et al. Prescription diagnosis for upper-limb rehabilitation training robot based on SVM-GDFNN[J]. Chinese Journal of Mechanical Engineering, 2013, 49(13):17-23.
[19] CHEN Z L, GUO Q, XIONG H Y, et al. Control and implementation of 2-DOF lower limb exoskeleton experiment platform[J]. Chinese Journal of Mechanical Engineering, 2021, 34(1):22.
[20] WEI F, GUO R. Deterministic convergence of an online gradient method for BP-neural networks[J]. IEEE Transactions on Neural Networks, 2005, 16(3):533-540.

基于SVMBP的下肢外骨骼步态检测及识别研究

Research on Gait Detection and Recognition of Lower Limb Exoskeleton Based on SVMBP

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李建乐, 张佳奇, 黄念, 李腾腾, 徐浩, 夏梓旭, 武湛君. 基于深度学习的分布式光纤损伤识别方法[J]. 机械工程学报, 2022, 58(8): 88-95.
[2]	贾寒冰, 刘鹏, 张雷, 王震坡. 基于规则与机器学习融合的换道决策建模方法研究[J]. 机械工程学报, 2022, 58(4): 212-221.
[3]	余晓霞, 邓蕾, 汤宝平, 夏乙, 李琪康. 小样本条件下元学习门控神经网络的齿轮退化趋势预测研究[J]. 机械工程学报, 2022, 58(3): 149-156.
[4]	王闰南, 谢帆, 张波. 基于神经网络方法的峰值电流控制Boost变换器数据驱动建模^*[J]. 电气工程学报, 2022, 17(2): 142-150.
[5]	高翱, 王帅, 韩兴臣, 张智晟. 基于GRU神经网络的WGAN短期负荷预测模型^*[J]. 电气工程学报, 2022, 17(2): 168-175.
[6]	陈灵, 陈郑平, 李军良, 米为民, 刘铭洋. 基于深度卷积神经网络和合作博弈的多微网实时能量管理策略[J]. 电气工程学报, 2022, 17(2): 215-225.
[7]	邸红采, 彭芳瑜, 唐小卫, 闫蓉. 机器人铣削加工误差视觉跟踪测量与补偿研究[J]. 机械工程学报, 2022, 58(14): 35-43.
[8]	丁军, 古愉川, 黄霞, 宋鹍, 路世青, 王路生. 基于改进遗传算法优化人工神经网络的304不锈钢流变应力预测准确性研究[J]. 机械工程学报, 2022, 58(10): 78-86.
[9]	张朝龙, 赵筛筛, 何怡刚. 基于信息熵与PSO-LSTM的锂电池组健康状态估计方法[J]. 机械工程学报, 2022, 58(10): 180-190.
[10]	程真英, 江文姝, 方旭, 李瑞君, 黄强先. 基于遗传算法和Elman神经网络的接触式探头动态特性补偿[J]. 机械工程学报, 2022, 58(10): 24-30.
[11]	刘茜, 程靖, 梁建勋. 混合碰撞建模方法及其试验验证[J]. 机械工程学报, 2022, 58(1): 116-123.
[12]	张立, 陈江涛, 熊芬芬, 任成坤, 李超. 基于元学习的多可信度深度神经网络代理模型[J]. 机械工程学报, 2022, 58(1): 190-200.
[13]	蔡鑫祥, 撖奥洋, 周生奇, 菅学辉, 张智晟. 基于改进Bagging算法与模糊MP-LSTM融合的短期负荷预测模型^*[J]. 电气工程学报, 2022, 17(1): 164-170.
[14]	陈诚, 皮志勇, 赵英龙, 廖玄, 张明敏, 李勇. 基于自适应灾变遗传-循环神经网络的锂离子电池SOC估计^*[J]. 电气工程学报, 2022, 17(1): 86-94.
[15]	宋立业, 范抑伶, 王燚增. 基于KPCA与IHHO-LSSVM的电力变压器故障诊断方法研究^*[J]. 电气工程学报, 2022, 17(1): 95-103.