Please wait a minute...
浙江大学学报(工学版)
J4  2010, Vol. 44 Issue (7): 1373-1376    DOI: 10.3785/j.issn.1008973X.2010.07.025
自动化技术     
基于神经网络的智能下肢假肢自适应控制
马玉良1, 徐文良1, 孟明1, 罗志增1, 杨家强2
1. 杭州电子科技大学 自动化学院, 浙江 杭州 310018; 2. 浙江大学 电气工程学院, 浙江 杭州 310027
Adaptive control for intelligent lower limb prosthesis based on
neural network
MA Yu-liang1, XU Wen-liang1, MENG Ming1, LUO Zhi-zeng1, YANG Jia-qiang2
1. School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China; 2. College of Electrical Engineering,
Zhejiang University, Hangzhou 310027, China
 全文: PDF  HTML
摘要：

下肢假肢的膝关节是一种具有高度非线性、时变、强耦合的阻尼系统，传统控制方法很难达到良好控制效果.针对这一问题,提出将神经网络(NN)应用于下肢假肢控制.以学习矢量量化（LVQ）神经网络为基础,提出神经网络模型参考自适应控制方法.该方法通过选择适当的参考模型和自适应算法,利用参考模型输出与实际系统输出之间的误差信号,由自适应算法计算当前的控制量以控制智能下肢假肢,达到自适应控制的目的.该方法不需要进行性能指标的变换,容易实现且自适应速度快,仿真结果表明了该方法的有效性.
Abstract:

The knee joint of lower limb prosthesis is a damp system with high nonlinearity, timevarying and strong coupling, and the traditional control method can hardly achieve good performance. Aimed at the problem, a neural network (NN)based model reference adaptive control method was proposed based on the learning vector quantization (LVQ) neural network. Based on an appropriate reference model and an adaptive algorithm, the current control variable was calculated by using the error between the reference model output and the actual system output in order to control the intelligent lowerlimb prosthesis and achieve the adaptive control. The method does not require the transformation of performance criteria, and is fast and easy to implement. Simulation results showed the validity of the method.
出版日期: 2010-07-01
:  TP 13  
基金资助:

国家“863”高技术研究发展计划资助项目(2008AA04Z212); 国家自然科学基金资助项目 (60874102，60705010); 浙江省自然科学基金资助项目(Y1080854，Y1090761); 浙江省教育厅基金资助项目(Y200907366，Y200805157).
通讯作者: 杨家强, 男, 副教授.     E-mail: yjq1998@163.com
作者简介: 马玉良(1976—), 男, 河北石家庄人, 副研究员, 从事智能控制﹑机器人控制和鲁棒控制等研究. Email: mayuliang@hdu.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

马玉良, 徐文良, 孟明, 罗志增, 杨家强. 基于神经网络的智能下肢假肢自适应控制[J]. J4, 2010, 44(7): 1373-1376.

MA Yu-Liang, XU Wen-Liang, MENG Meng, LUO Zhi-Ceng, YANG Jia-Jiang. Adaptive control for intelligent lower limb prosthesis based on
neural network. J4, 2010, 44(7): 1373-1376.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008973X.2010.07.025    或    http://www.zjujournals.com/eng/CN/Y2010/V44/I7/1373

［1］ GONG Siyuan, YANG Peng, SONG Liang, et al. Study on development platform of active lowerlimb prosthesis based on MATLAB ［C］∥ Proceedings of the 20th Chinese Control and Decision Conference. Yantai, China: IEEE, 2008: 35423545.
［2］ 贺光辉,谭冠政,曾庆东,等.智能仿生人工腿位置伺服控制系统的设计［J］.计算机测量与控制,2007,15(1): 5255.
HE Guanghui, TAN Guanzheng, ZENG Qingdong, et al. Study and design of position servo control system of intelligent bionic artificial leg ［J］. Computer Measurement and Control, 2007, 15(1): 5255.
［3］ 王人成,沈强,金德闻.假肢智能膝关节研究进展［J］.康复医学工程,2007,22(12): 10931094.
WANG Rencheng, SHEN Qiang, JIN Dewen. Research development of intelligent knee prosthesis ［J］. Chinese Journal of Rehabilitation Medicine, 2007, 22(12): 10931094.
［4］ 杨义勇,王人成,王延利,等.新型仿生膝关节的机构设计与仿真研究［J］.中国机械工程,2008, 19(1): 7274.
YANG Yiyong, WANG Rencheng, WANG Yanli, et al. Humanoid design and movement and simulation of a new knee prosthesis ［J］. China Mechanical Engineering, 2008, 19(1): 7274.
［5］ ATSUO O, GORO O, KAZUNORI H, et al. Design of lower limb prosthesis with contact pressure adjustment by MR fluid ［C］∥ Proceedings of the 30th Annual International IEEE EMBS Conference. Vancouver, Canada: IEEE, 2008: 330333.
［6］ POPOVIC D B, OGUZTORELI M N, STEIN R B. Optimal control for an active aboveknee prosthesis with two degrees of freedom ［J］. Journal of Biomech, 1995, 28(1): 8998.
［7］ DANIEL Z, BEATRICE S, GERHARD S. Finitestate control of a transfemoral (TF) ［J］. IEEE Transactions on Control Systems Technology, 2002, 10(3): 408420.
［8］ POPOVIC D B, TOMOVIC R, TEPAVAC D. Control aspects of active aboveknee prosthesis ［J］. International Journal of ManMachine Studies, 1991, 35(6): 751767.
［9］ VOJISLAV D K, DEJAN P. Feedback error learning neural network for transfemoral prosthesis ［J］.IEEE Transactions on Rehabilitation Engineering, 2000, 8(1): 7180.
［10］ KOSTOV A, ANDREWS B J, POPOVIC D B, et al. Machine learning in control of functional electrical stimulation systems for locomotion［J］. IEEE Transactions on Biomedical Engineering, 1995, 42(6): 541551.
［11］ SANNER R M, SLOTINE J E. Stable adaptive control and recursive identification using radial Gaussian networks ［C］∥ Proceedings of IEEE Conference on Decision and Control. Brighton: IEEE, 1991: 21162123.
［12］ KOHONEN T. Selforganization and associative memory ［M］. Berlin: SpringerVerlag, 1995: 8896.
［13］ 黄永安,李文成,高小科.Matlab7.0/Simulink6.0应用实例仿真与高效算法开发［M］.北京:清华大学出版社,2008: 440448.
［14］ 徐文良.智能下肢假肢的多运动模式自适应控制［D］.杭州:杭州电子科技大学,2010: 5559.
XU Wenliang. Multimotion model adaptive control of intelligent lower limb prosthesis ［D］. Hangzhou: Hangzhou Dianzi University, 2010: 5559.
[1] 李丽娟, 熊路, 刘君, 徐欧官. 基于AP-LSSVM的多模型预测控制[J]. J4, 2013, 47(10): 1741-1746.
[2] 娄柯, 齐斌, 穆文英, 崔宝同. 基于反馈控制策略的多智能体蜂拥控制[J]. J4, 2013, 47(10): 1758-1763.
[3] 毛维杰,张媛媛. 具有区间时变时滞的中立型系统稳定性分析[J]. J4, 2012, 46(5): 848-852.
[4] 崔黎黎, 张化光,罗艳红. 控制方向未知的非线性系统的自适应评价设计[J]. J4, 2012, 46(5): 853-857.
[5] 倪何, 肖航, 程刚, 孙丰瑞. 基于混沌演化的蒸汽动力装置负荷控制优化[J]. J4, 2011, 45(12): 2202-2207.
[6] 王丽娟, 章辉. 通讯访问约束下的线性系统参数可辨识性[J]. J4, 2011, 45(12): 2103-2108.
[7] 赵黎丽, 李平, 李修亮. 带遗忘因子的线性系统自适应观测器设计[J]. J4, 2011, 45(10): 1704-1709.
[8] 王俊宏, 薛安克. 测量值量化的时滞系统的输出反馈控制[J]. J4, 2010, 44(7): 1418-1422.
[9] 潘海鹏, 吕勇松. 时滞系统的模糊神经网络补偿控制[J]. J4, 2010, 44(7): 1343-1347.
[10] 邹洪波, 房善华, 鲁仁全, 薛安克. 基于2级控制系统的量化状态观测器设计[J]. J4, 2010, 44(7): 1428-1432.
[11] 谢斌, 张开石, 潘华东, 等. 未知环境中无人机适航地图构建与地面目标跟踪[J]. J4, 2010, 44(1): 118-123.