智能下肢假肢的多运动模式自适应控制
|
摘要
研制智能下肢假肢目的是为了改善残疾人生活质量及促进医疗福利事业的发展,同时智能下肢假肢也是近年来机器人学与生物医学工程领域广受关注的研究方向。目前国外已经出现智能化及其仿生度较高的智能下肢假肢,而国内在这一领域的研究状况则不容乐观,还没有成熟的智能下肢假肢产品出现。对智能下肢假肢的探索与研发,为肢体残疾人提供性能优良、价格低廉的智能假肢产品,对于缩短与发达国家的差距,促进我国康复医学工程技术和假肢产业的发展具有重要的意义。
智能下肢假肢的成功研制必须以下肢运动姿态的精确识别为前提,考虑到目前下肢运动姿态识别研究中遇到的单一膝关节角度无法辨识复杂多运动状态难题和因残肢肌肉缺损、肌肉疲劳、电极位置改变等因素带来的肌电信号干扰问题,有必要开发出一种获取多种运动力学信息的平台,以及寻找更有效的信号特征分析方法、下肢多运动模式的识别和下肢假肢的自适应控制方法。
本文紧扣国家自然科学基金资助项目“膝上假肢的运动力学信息获取与多运动模式控制方法研究(60705010)”的主题,主要完成了以下的研究工作:
(1)为获得足够的下肢运动信息,参考下肢运动的特点,并利用课题组现有设备,成功搭建了人体下肢多源运动信息获取系统,为智能下肢假肢的研究奠定了基础。该多源运动信息获取系统包含三个部分:MyoTrace 400肌电信号采集仪(获取大腿不同区域四块肌电的肌肉信号);附着PVDF力传感器的鞋(获取足跟和足趾区域的压力);MTx姿态仪(获取膝关节的屈伸角度)。
(2)通过实验方法获取大量多运动模式下的下肢表面肌电信号、足底压力信号和膝关节屈伸角度信号,并采用不同方法对各种信号进行了特征分析。本文对下肢表面肌电信号采用希尔伯特-黄变换的特征提取方法,对足底压力信号提出了一种积分电压比值法的特征提取方法,对膝关节屈伸角度信号提出了角度均值比的特征提取方法。
(3)在对下肢表面肌电信号的分析处理过程中,本文首次采用希尔伯特-黄变换(HHT)的方法做了两个方面的探索:
提出基于经验模态分解(EMD)的阈值消噪方法。该方法是基于信号和噪声经过EMD后在不同固有模态函数(IMF)上具有的不同特性,即首先对信号进行经验模态分解,然后对高频的IMF分别选用不同的滤波阈值,进行自适应滤波处理。
提出HHT边际谱特征提取方法。该方法是基于各层IMF的频率有效程度来选择合适的IMF,通过自适应边际谱的分段方法确定边际谱分段,求取边际谱各段的能量来获得边际谱形状特征。经由实验得到的一种优化的归一化处理方法,最终得到的HHT边际谱的形状特征。
(4)在多运动模式识别研究上,本文运用两种比较成熟的神经网络技术(基于L-M改进算法的BP与LVQ)对人体下肢运动姿态进行融合识别。实验结果表明:经过训练的两种网络分类器能正确识别下肢运动模式,基于L-M改进算法的BP网络识别正确率为75%,LVQ网络识别正确率为84%。对实验结果进行分析,发现LVQ具有识别准确率更高、重复性更好及网络训练更加稳定的优点。
(5)因为智能下肢假肢运动是复杂多变量、非线性且时变的过程,因此本文选用基于模型参考的神经网络自适应控制技术来对下肢运动进行仿真研究。仿真结果表明,该控制方法用于下肢假肢的控制取得了令人满意的效果。
To improve the living quality and welfare benefits of amputees, research has been made on the intellective artificial leg, which is also an attentive research project in the fields of robotics and biomedical engineering in these years. The high-level intelligentized bionic artificial legs have appeared in foreign countries, but research status in this field is not optimistic in China, there is no mature intellective artificial leg product. The exploration and development of intellective artificial leg is of great significance to provide high-performance, low-cost products, and it is also useful to shorten the gap with the developed countries and to promote rehabilitation engineering and prosthesis industry of China.
The success of the development of intellective artificial leg must be based on the accurate identification of moving posture, Considering the problems that single angle of knee joint is not enough for complex posture identification and the noise brought by the result of muscle defect, muscle fatigue, changes in the electrode location and other factors disturbs the EMG.. It is necessary to develop a terrace of getting multi-source kinetic mechanical information, seek some good methods of multi-locomotion mode recognition of lower limb and the adaptive control of lower limb prosthesis.
This article closely around the National Natural Science Foundation on acquisition of kinetic mechanical information and control method of multi-motion model of AK prosthesis(60705010). In this paper the major research work are as follows:
(1) In order to obtain enough kinetic mechanical information, referring to the kinetic characteristics of the lower limb, the paper presents a set of multi-source kinetic mechanical information system by using the existing equipments which create essential conditions for intelligent control of lower limb prosthesis. This information system includes three parts: MyoTrace 400 (obtaining EMG of four different femoral muscles); PVDF force sensor attached to the shoe (obtaining heel and toe regional pressure); MTx sensor (obtaining the angle of knee joint).
(2) Through the experimental method, this paper gets much information about SEMG of four different femoral muscles, heel and toe regional pressure and the angle of knee joint, in this paper three feature extraction methods are proposed, the feature extraction based on HHT is used in SEMG, the feature extraction based on the ratio of integral voltage is used in plantar pressure signal and the feature extraction based on the ratio of angle meen is used in the angle signal of knee joint.
(3) In the analysis of SEMG, this paper contains two aspects’work through using HHT:
Bringing a method of threshold denoising based on empirical mode decomposition (EMD). This method based on different characteristics of signal with noise in different intrinsic mode function (IMFs), fistly the signal can be divided through EMD, finally the high-frequency IMFs are processed by adaptive filter through different threshold;
Bringing a feature extraction method based on HHT margin spectrum. This method contains three steps: fistly, the useful IMFs are selected and the self-adapting subsection for HHT margin spectrum is determined; secondly, the energy of each margin spectrum subsection is considered as the sharp feature of the margin spectrum for each SEMG; finally, each dimension of the feature vector is normalized by the method designed based on the experiment.
(4) In the research of multi-locomotion mode recognition of lower limb, the two mature neural networks (BP improved algorithm based on L-M & LVQ) are used in identification of moving posture. The experimental results show that the two methods are both suitable to recognize multi-locomotion mode of lower limb, the correct rate of BP neural networks based on L-M is 75%, and the correct rate of LVQ is 84%. Through the results, it shows that LVQ is more recognize rate, more repeatability and more robust.
(5) Considering the intellective artificial leg is a complicated system which is nonlinear, multilateral variable and parameters changed with time. In this paper, the neural network based model reference adaptive control technology to simulate research of the lower limb. Experimental result shows that the neural network based model reference adaptive control system is satisfied.
智能下肢假肢的成功研制必须以下肢运动姿态的精确识别为前提,考虑到目前下肢运动姿态识别研究中遇到的单一膝关节角度无法辨识复杂多运动状态难题和因残肢肌肉缺损、肌肉疲劳、电极位置改变等因素带来的肌电信号干扰问题,有必要开发出一种获取多种运动力学信息的平台,以及寻找更有效的信号特征分析方法、下肢多运动模式的识别和下肢假肢的自适应控制方法。
本文紧扣国家自然科学基金资助项目“膝上假肢的运动力学信息获取与多运动模式控制方法研究(60705010)”的主题,主要完成了以下的研究工作:
(1)为获得足够的下肢运动信息,参考下肢运动的特点,并利用课题组现有设备,成功搭建了人体下肢多源运动信息获取系统,为智能下肢假肢的研究奠定了基础。该多源运动信息获取系统包含三个部分:MyoTrace 400肌电信号采集仪(获取大腿不同区域四块肌电的肌肉信号);附着PVDF力传感器的鞋(获取足跟和足趾区域的压力);MTx姿态仪(获取膝关节的屈伸角度)。
(2)通过实验方法获取大量多运动模式下的下肢表面肌电信号、足底压力信号和膝关节屈伸角度信号,并采用不同方法对各种信号进行了特征分析。本文对下肢表面肌电信号采用希尔伯特-黄变换的特征提取方法,对足底压力信号提出了一种积分电压比值法的特征提取方法,对膝关节屈伸角度信号提出了角度均值比的特征提取方法。
(3)在对下肢表面肌电信号的分析处理过程中,本文首次采用希尔伯特-黄变换(HHT)的方法做了两个方面的探索:
提出基于经验模态分解(EMD)的阈值消噪方法。该方法是基于信号和噪声经过EMD后在不同固有模态函数(IMF)上具有的不同特性,即首先对信号进行经验模态分解,然后对高频的IMF分别选用不同的滤波阈值,进行自适应滤波处理。
提出HHT边际谱特征提取方法。该方法是基于各层IMF的频率有效程度来选择合适的IMF,通过自适应边际谱的分段方法确定边际谱分段,求取边际谱各段的能量来获得边际谱形状特征。经由实验得到的一种优化的归一化处理方法,最终得到的HHT边际谱的形状特征。
(4)在多运动模式识别研究上,本文运用两种比较成熟的神经网络技术(基于L-M改进算法的BP与LVQ)对人体下肢运动姿态进行融合识别。实验结果表明:经过训练的两种网络分类器能正确识别下肢运动模式,基于L-M改进算法的BP网络识别正确率为75%,LVQ网络识别正确率为84%。对实验结果进行分析,发现LVQ具有识别准确率更高、重复性更好及网络训练更加稳定的优点。
(5)因为智能下肢假肢运动是复杂多变量、非线性且时变的过程,因此本文选用基于模型参考的神经网络自适应控制技术来对下肢运动进行仿真研究。仿真结果表明,该控制方法用于下肢假肢的控制取得了令人满意的效果。
To improve the living quality and welfare benefits of amputees, research has been made on the intellective artificial leg, which is also an attentive research project in the fields of robotics and biomedical engineering in these years. The high-level intelligentized bionic artificial legs have appeared in foreign countries, but research status in this field is not optimistic in China, there is no mature intellective artificial leg product. The exploration and development of intellective artificial leg is of great significance to provide high-performance, low-cost products, and it is also useful to shorten the gap with the developed countries and to promote rehabilitation engineering and prosthesis industry of China.
The success of the development of intellective artificial leg must be based on the accurate identification of moving posture, Considering the problems that single angle of knee joint is not enough for complex posture identification and the noise brought by the result of muscle defect, muscle fatigue, changes in the electrode location and other factors disturbs the EMG.. It is necessary to develop a terrace of getting multi-source kinetic mechanical information, seek some good methods of multi-locomotion mode recognition of lower limb and the adaptive control of lower limb prosthesis.
This article closely around the National Natural Science Foundation on acquisition of kinetic mechanical information and control method of multi-motion model of AK prosthesis(60705010). In this paper the major research work are as follows:
(1) In order to obtain enough kinetic mechanical information, referring to the kinetic characteristics of the lower limb, the paper presents a set of multi-source kinetic mechanical information system by using the existing equipments which create essential conditions for intelligent control of lower limb prosthesis. This information system includes three parts: MyoTrace 400 (obtaining EMG of four different femoral muscles); PVDF force sensor attached to the shoe (obtaining heel and toe regional pressure); MTx sensor (obtaining the angle of knee joint).
(2) Through the experimental method, this paper gets much information about SEMG of four different femoral muscles, heel and toe regional pressure and the angle of knee joint, in this paper three feature extraction methods are proposed, the feature extraction based on HHT is used in SEMG, the feature extraction based on the ratio of integral voltage is used in plantar pressure signal and the feature extraction based on the ratio of angle meen is used in the angle signal of knee joint.
(3) In the analysis of SEMG, this paper contains two aspects’work through using HHT:
Bringing a method of threshold denoising based on empirical mode decomposition (EMD). This method based on different characteristics of signal with noise in different intrinsic mode function (IMFs), fistly the signal can be divided through EMD, finally the high-frequency IMFs are processed by adaptive filter through different threshold;
Bringing a feature extraction method based on HHT margin spectrum. This method contains three steps: fistly, the useful IMFs are selected and the self-adapting subsection for HHT margin spectrum is determined; secondly, the energy of each margin spectrum subsection is considered as the sharp feature of the margin spectrum for each SEMG; finally, each dimension of the feature vector is normalized by the method designed based on the experiment.
(4) In the research of multi-locomotion mode recognition of lower limb, the two mature neural networks (BP improved algorithm based on L-M & LVQ) are used in identification of moving posture. The experimental results show that the two methods are both suitable to recognize multi-locomotion mode of lower limb, the correct rate of BP neural networks based on L-M is 75%, and the correct rate of LVQ is 84%. Through the results, it shows that LVQ is more recognize rate, more repeatability and more robust.
(5) Considering the intellective artificial leg is a complicated system which is nonlinear, multilateral variable and parameters changed with time. In this paper, the neural network based model reference adaptive control technology to simulate research of the lower limb. Experimental result shows that the neural network based model reference adaptive control system is satisfied.
引文
[1]刘志泉.我国肢体残疾人概况[J].中国康复医学杂志,2003,18(8):493-494.
[2]国际先进机器人技术计划(IARP)第二十次联合协调讨论会报告译文集:64.
[3]张更林,金宝士,张宇光.人体下肢假肢发展概况[J].佳木斯大学学报,2002,20(3):336-339.
[4]谭冠政,吴立明.国内外人工腿(假肢)研究的进展及发展趋势[J].机器人,2001,23(1):91-96.
[5] D. Datta, B. Heller, J. Howitt. A comparative evaluation of oxygen consumption and gait pattern in amputees using Intelligent Prostheses and conventionally damped knee swing-phase control[J].Clinical Rehabilitation, 2008, 19(4):398-403.
[6] S. Zahedi, A. Sykes, S. Lang, I. Cullington. Adaptive prosthesis–a new concept in prosthetic knee control[J].Robotic, 2005, 23(3):337-344.
[7] M. S. Orendurff, A. D. Segal, G. K. Klute, M. L. McDowell, J. A. Pecoraro, J. M. Czerniecki. Gait efficiency using the C-Leg[J].Journal of Rehabilitation Research and Development, 2006, 43(2):239-246.
[8]杨建坤,季林红,王人成,金德闻,张济川.四杆机构膝关节控制力矩分析[J].中国康复理论与实践,2004,10(5):264-265.
[9] D. Jin, J. Yang, R. Zhang, R. Wang, J. Zhang. Terrain identification for prosthetic knees based on electromyography signal features[J].Tsinghua Science and Technology, 2006,11(1):74-79.
[10]杨义勇,王人成,郝智秀,金德闻,张涵.自然步态摆动期动力学协调模式的研究[J].生物医学工程杂志,2006,23(1):69-73.
[11]蒋翌军,袁正华.储能式复合材料运动假肢(腿和足弓)成型工艺研究[J].纤维复合材料,1997,2:13-16.
[12]谭冠政,何胜军,曾庆冬,闫炳雷,蔡光超.CIP-I智能仿生人工腿步速测量系统研究与设计[J].计算机测量与控制,2005,13(11):1164-1166.
[13]丛德宏,徐心和.磁流变液智能假腿的摆动相控制[J].系统仿真学报,2006,18(s2):916-918.
[14]郭欣,杨鹏,王志宇.肌电信号控制下肢假肢的机理[J].中南工业大学学报,2003,34(2):31-33.
[15]Xin Guo, Peng Yang, Ying Li, Wei-Li Yan. The SEMG Analysis For the Lower Limb Prosthesis Using Wavelet Transformation[C]. Proceedings of the 26th Annual International Conference of the IEEE EMBS. San Francisco, CA, USA* September 1-5, 2004: 341-344.
[16]Peng Yang, Lingling Chen, Xin Guo, Xitai Wang, Lifeng Li. Artificial Lower Limb with Myoelectrical Control Based on Support Vector Machine[C]. Proceedings of the 6th World Congress on Intelligent Control and Automation, June 21-23, Dalian, China, 2007: 9486-9489.计
[17]王斌锐,徐心和.智能仿生腿的研究[J].控制与决策,2004,19(2):122-127.
[18]Graupe. Control of Electrically-simulated walking of paraplegics via above- and below-lesion EMG Signature identification[C]. IEEE Trans. Automatic Control , 1989,34(2):130-138.
[19]Merletti, R and LoConte, L. Modeling of Surface Myoelectric Signals [C]. IEEE Trans Biomedical Engineering, 1999,46(7):810-820.
[20]胡天培.肌电特征发现与肌电康复研究[J].上海交通大学学报,1994, 28(3):151-153.
[21]雷敏,王志中.肌电假肢控制中的表面肌电信号的研究进展与展望[J].中国医疗器械杂志,2001, 25(3):156-160.
[22]Katsutoshi, Kuribayashi, et al. A discrimination system using neural network for EMG-controlled prostheses-Integral type of EMG signal processing[C], Proc. Of the 1993 IEEE/RSJ Int. Conference on Intelligent Robots and Systems’93 [Yokohama], 1993,1750-1755.
[23]李耀宇,郭凌菱等.肌电信号的波幅直方图统计处理[J].生物医学工程学杂志, 1995,12(3):237-240.
[24]Ronager. Power spectrum analysis of EMG pattern in normal and diseased muscles[J]. Neurol. Sci, 1989,94(1-3):283-294.
[25]Kang, W, Shiu, J, Cheng, C, et al. The application of cepstral coefficient and maximum likelihood method in EMG pattern recognition[C]. IEEE Transactions on Biomedical Engineering, 1995,42(8): 777-785.
[26]Merletti, R. Estimation of shape characteristics of surface muscle signal spectra from time domain data[C]. IEEE Trans. Biomed. Eng, 1995,42(2):769-776.
[27]蔡立羽,王志中,张还虹.基于短时傅立叶变换的肌电信号识别方法[J].中国医疗器械杂志, 2000,24(3):133-136.
[28]Morlet, J. Geophysics, 1982,47(2):222-236.
[29]Constable, R. and Thornhill, T. J. et al. Time-frequency analysis of the surface EMG duringmacimum height jumps under altered-G conditions[J]. Biomed Sci Inst rum, 1994,30:69-74.
[30]蔡立羽,王志中,张还虹.基于小波变换的肌电信号识别方法研究[J].数据采集与处理, 2000,15(2):255-258.
[31]Costantino, D, Morabito, F. C, and Versaci, M. A. Wavelet approach for classifying filtered SEMG experimental data[C]. Proceedings of the IASTED International Conference on Modelling, Identification and Control, 2008,23:540-545.
[32]Huang, N. E. The Empirical Mode Composition And The Hilbert Spectrum For Nonlinear And Non-stationary Time Series Analysis[J]. Proc R Soc Lond A, 1998,454(4):903-995.
[33]Yang, J.N, Lei, Y, Pan, S. et al. System identification of linear structures based on Hilbert-huang spectral analysis[J]. Earthquake Engineering and Structural Dynamics, 2003,32(9):1443-1467.
[34]Veltcheva, A. D. Wave and Group Transformation by a Hilbert Spectrum[J]. Coastal Engineering Journal, 2002,44(4):283-300.
[35]Zadeh, L. A. Fuzzy sets. Information and Control[M], 1965,8:338-353.
[36]杨广映.带触觉仿生假手研究.[硕士学位论文].杭州:杭州电子科技大学, 2005.
[37]J.J.Luh, G.C.Chang, C.K.Cheng, J.S.Lai, and T.S.Kuo, Isokinetic Elbow Joint Torques Estimation from SEMG and Joint Kinematics Data: Using an Artificial Neural Network Model[J], Electromyography Kinesiology, 1999,9:173-183.
[38]夏世芬,黄天民.一种神经网络自适应PID控制器[J].西南交通大学学报, 1998,33(6):710-715.
[39]张明君.基于遗传算法优化的神经网络PID控制器[J].北华大学学报, 2004,5(5):462-465.
[40]徐湘元,毛宗源.基于径向基函数神经网络的内模控制[J].电路与系统学报, 1999,4(2):86-91.
[41]燕铁斌,窦祖林.实用瘫痪康复[M].北京:人民卫生出版社, 1999:262-265.
[42]Whittl eM.W.Gait. analysis:an introduction(second edition) [M]. U.K.:Reed Educational and professional publishing, 1997.
[43]卢祖能,曾庆杏,李承晏,余绍祖.实用肌电图学[M].北京:人民卫生出版社,2000:58-69.
[44]Muzumdar, Ashok. Powered Upper Limb Prostheses-Control[J]. Implementation and Clinical Application, 2008(9):56-75.
[45]刘磊,岳文浩.神经肌电图原理[M].北京:科学出版社, 1983:6-8.
[46]赵东升.PVDF压电薄膜传感器的研制[J].传感器与微系统,2007,26(3):51-55.
[47]罗志增,蒋静坪.机器人感觉与多信息融合[M].北京:机械工业出版社,2002:28-29.
[48]刘刚,王立香,张连俊.LabVIEW 8.20中文版编程及应用[M].北京:电子工业出版社,2008:315-318.
[49]李强.关节机构的结构设计与分析.[硕士学位论文].西安:西北工业大学, 2007.
[50]Huang N E. et al. The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-Stationary Time Series Analysis [C]// Proc R Soc Lond A, 1998, 454(A): 417-457,903-995, 1834-1839.
[51]徐士良.计算机常用算法[M].北京:清华大学出版社,1995:191-196.
[52]钟佑明,金涛,秦树人.希尔伯特-黄变换中的一种新包络线算法[J].数据采集与处理,2005,1(20): 13-17.
[53]马文杰.基于HHT的肌电信号处理和SVM的手部多运动模式识别方法研究.[硕士学位论文].杭州:杭州电子科技大学, 2007.
[54]罗志增,加玉涛.基于表面EMG功率谱和BP网络的多运动模式识别[J].华中科技大学学报,2006,34(7): 63-66.
[55]朱大奇,史慧.人工神经网络原理及其应用[M].北京:科学出版社,2006:164-178.
[56]董长虹. Matlab神经网络与应用(第二版)[M].北京:国防工业出版社, 2007:65-91.
[57]T Kohonen. Self-Organization and Associative Memory [M]. Berlin:Springer-Verlag,1995.
[58]王永骥,涂健.神经元网络控制[M].北京:机械工业出版社,1998:10-12.
[59]Miller W T,Glanz F H&Kraft L G. Application of a general learning algorithm to the control of robotic manipulators[J].The International Journal of Robotics Research, 1987,6(2):84-98.
[60]Miller W T,Glanz F H&Kraft L G. Real-time dynamic control of an industrial manipulator using a neural-network-based learning controller[C].IEEE Transactions on Robotics and Automation, 1990,6(1):1-9.
[61]Sanner R M&Slotine J J E. Stable adaptive control and recursive identification using radial Gaussian networks[C].In:Proceedings of IEEE Conference on Decision and Control,Brighton, , 1991,2116-2123.
[62]Popovic D B,Oguztoreli M N,Stein R B. Optimal control for an active above-knee prosthesis with two degrees of freedom[J].J Biomech, 1995,28:89-98.
[63]Daniel Zlatnik,Beatrice Steiner,Gerhard Schweitzer. Finite-State control of a Trans-Femoral (TF) [J].IEEE Transactions on Control Systems Technology, 2002, 10(3):408-420.
[64]Popovic D B,Tomovic R,Tepavac D. Control aspects an active A/K prosthesis [J]. Int.J. Man-Machine Studyies, 1991,35:751-767.
[65]Vojislav D. Kalanovic,Dejan Popovic,et al. Feedback Error Learning Neural Network for Trans-Femoral Prosthesis[J].IEEETransactions on Rehabilitation Engineering, 2000,8(1):71-80.
[66]Kostov A,Andrews B J,Popovic D B,et al. Machine Learning in Control of Functional Electrical Stimulation(FES) for Locomotion[J].IEEE Trans.Biomed.En., 1995,2:541-551.
[67]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,2008:440-448.
[2]国际先进机器人技术计划(IARP)第二十次联合协调讨论会报告译文集:64.
[3]张更林,金宝士,张宇光.人体下肢假肢发展概况[J].佳木斯大学学报,2002,20(3):336-339.
[4]谭冠政,吴立明.国内外人工腿(假肢)研究的进展及发展趋势[J].机器人,2001,23(1):91-96.
[5] D. Datta, B. Heller, J. Howitt. A comparative evaluation of oxygen consumption and gait pattern in amputees using Intelligent Prostheses and conventionally damped knee swing-phase control[J].Clinical Rehabilitation, 2008, 19(4):398-403.
[6] S. Zahedi, A. Sykes, S. Lang, I. Cullington. Adaptive prosthesis–a new concept in prosthetic knee control[J].Robotic, 2005, 23(3):337-344.
[7] M. S. Orendurff, A. D. Segal, G. K. Klute, M. L. McDowell, J. A. Pecoraro, J. M. Czerniecki. Gait efficiency using the C-Leg[J].Journal of Rehabilitation Research and Development, 2006, 43(2):239-246.
[8]杨建坤,季林红,王人成,金德闻,张济川.四杆机构膝关节控制力矩分析[J].中国康复理论与实践,2004,10(5):264-265.
[9] D. Jin, J. Yang, R. Zhang, R. Wang, J. Zhang. Terrain identification for prosthetic knees based on electromyography signal features[J].Tsinghua Science and Technology, 2006,11(1):74-79.
[10]杨义勇,王人成,郝智秀,金德闻,张涵.自然步态摆动期动力学协调模式的研究[J].生物医学工程杂志,2006,23(1):69-73.
[11]蒋翌军,袁正华.储能式复合材料运动假肢(腿和足弓)成型工艺研究[J].纤维复合材料,1997,2:13-16.
[12]谭冠政,何胜军,曾庆冬,闫炳雷,蔡光超.CIP-I智能仿生人工腿步速测量系统研究与设计[J].计算机测量与控制,2005,13(11):1164-1166.
[13]丛德宏,徐心和.磁流变液智能假腿的摆动相控制[J].系统仿真学报,2006,18(s2):916-918.
[14]郭欣,杨鹏,王志宇.肌电信号控制下肢假肢的机理[J].中南工业大学学报,2003,34(2):31-33.
[15]Xin Guo, Peng Yang, Ying Li, Wei-Li Yan. The SEMG Analysis For the Lower Limb Prosthesis Using Wavelet Transformation[C]. Proceedings of the 26th Annual International Conference of the IEEE EMBS. San Francisco, CA, USA* September 1-5, 2004: 341-344.
[16]Peng Yang, Lingling Chen, Xin Guo, Xitai Wang, Lifeng Li. Artificial Lower Limb with Myoelectrical Control Based on Support Vector Machine[C]. Proceedings of the 6th World Congress on Intelligent Control and Automation, June 21-23, Dalian, China, 2007: 9486-9489.计
[17]王斌锐,徐心和.智能仿生腿的研究[J].控制与决策,2004,19(2):122-127.
[18]Graupe. Control of Electrically-simulated walking of paraplegics via above- and below-lesion EMG Signature identification[C]. IEEE Trans. Automatic Control , 1989,34(2):130-138.
[19]Merletti, R and LoConte, L. Modeling of Surface Myoelectric Signals [C]. IEEE Trans Biomedical Engineering, 1999,46(7):810-820.
[20]胡天培.肌电特征发现与肌电康复研究[J].上海交通大学学报,1994, 28(3):151-153.
[21]雷敏,王志中.肌电假肢控制中的表面肌电信号的研究进展与展望[J].中国医疗器械杂志,2001, 25(3):156-160.
[22]Katsutoshi, Kuribayashi, et al. A discrimination system using neural network for EMG-controlled prostheses-Integral type of EMG signal processing[C], Proc. Of the 1993 IEEE/RSJ Int. Conference on Intelligent Robots and Systems’93 [Yokohama], 1993,1750-1755.
[23]李耀宇,郭凌菱等.肌电信号的波幅直方图统计处理[J].生物医学工程学杂志, 1995,12(3):237-240.
[24]Ronager. Power spectrum analysis of EMG pattern in normal and diseased muscles[J]. Neurol. Sci, 1989,94(1-3):283-294.
[25]Kang, W, Shiu, J, Cheng, C, et al. The application of cepstral coefficient and maximum likelihood method in EMG pattern recognition[C]. IEEE Transactions on Biomedical Engineering, 1995,42(8): 777-785.
[26]Merletti, R. Estimation of shape characteristics of surface muscle signal spectra from time domain data[C]. IEEE Trans. Biomed. Eng, 1995,42(2):769-776.
[27]蔡立羽,王志中,张还虹.基于短时傅立叶变换的肌电信号识别方法[J].中国医疗器械杂志, 2000,24(3):133-136.
[28]Morlet, J. Geophysics, 1982,47(2):222-236.
[29]Constable, R. and Thornhill, T. J. et al. Time-frequency analysis of the surface EMG duringmacimum height jumps under altered-G conditions[J]. Biomed Sci Inst rum, 1994,30:69-74.
[30]蔡立羽,王志中,张还虹.基于小波变换的肌电信号识别方法研究[J].数据采集与处理, 2000,15(2):255-258.
[31]Costantino, D, Morabito, F. C, and Versaci, M. A. Wavelet approach for classifying filtered SEMG experimental data[C]. Proceedings of the IASTED International Conference on Modelling, Identification and Control, 2008,23:540-545.
[32]Huang, N. E. The Empirical Mode Composition And The Hilbert Spectrum For Nonlinear And Non-stationary Time Series Analysis[J]. Proc R Soc Lond A, 1998,454(4):903-995.
[33]Yang, J.N, Lei, Y, Pan, S. et al. System identification of linear structures based on Hilbert-huang spectral analysis[J]. Earthquake Engineering and Structural Dynamics, 2003,32(9):1443-1467.
[34]Veltcheva, A. D. Wave and Group Transformation by a Hilbert Spectrum[J]. Coastal Engineering Journal, 2002,44(4):283-300.
[35]Zadeh, L. A. Fuzzy sets. Information and Control[M], 1965,8:338-353.
[36]杨广映.带触觉仿生假手研究.[硕士学位论文].杭州:杭州电子科技大学, 2005.
[37]J.J.Luh, G.C.Chang, C.K.Cheng, J.S.Lai, and T.S.Kuo, Isokinetic Elbow Joint Torques Estimation from SEMG and Joint Kinematics Data: Using an Artificial Neural Network Model[J], Electromyography Kinesiology, 1999,9:173-183.
[38]夏世芬,黄天民.一种神经网络自适应PID控制器[J].西南交通大学学报, 1998,33(6):710-715.
[39]张明君.基于遗传算法优化的神经网络PID控制器[J].北华大学学报, 2004,5(5):462-465.
[40]徐湘元,毛宗源.基于径向基函数神经网络的内模控制[J].电路与系统学报, 1999,4(2):86-91.
[41]燕铁斌,窦祖林.实用瘫痪康复[M].北京:人民卫生出版社, 1999:262-265.
[42]Whittl eM.W.Gait. analysis:an introduction(second edition) [M]. U.K.:Reed Educational and professional publishing, 1997.
[43]卢祖能,曾庆杏,李承晏,余绍祖.实用肌电图学[M].北京:人民卫生出版社,2000:58-69.
[44]Muzumdar, Ashok. Powered Upper Limb Prostheses-Control[J]. Implementation and Clinical Application, 2008(9):56-75.
[45]刘磊,岳文浩.神经肌电图原理[M].北京:科学出版社, 1983:6-8.
[46]赵东升.PVDF压电薄膜传感器的研制[J].传感器与微系统,2007,26(3):51-55.
[47]罗志增,蒋静坪.机器人感觉与多信息融合[M].北京:机械工业出版社,2002:28-29.
[48]刘刚,王立香,张连俊.LabVIEW 8.20中文版编程及应用[M].北京:电子工业出版社,2008:315-318.
[49]李强.关节机构的结构设计与分析.[硕士学位论文].西安:西北工业大学, 2007.
[50]Huang N E. et al. The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-Stationary Time Series Analysis [C]// Proc R Soc Lond A, 1998, 454(A): 417-457,903-995, 1834-1839.
[51]徐士良.计算机常用算法[M].北京:清华大学出版社,1995:191-196.
[52]钟佑明,金涛,秦树人.希尔伯特-黄变换中的一种新包络线算法[J].数据采集与处理,2005,1(20): 13-17.
[53]马文杰.基于HHT的肌电信号处理和SVM的手部多运动模式识别方法研究.[硕士学位论文].杭州:杭州电子科技大学, 2007.
[54]罗志增,加玉涛.基于表面EMG功率谱和BP网络的多运动模式识别[J].华中科技大学学报,2006,34(7): 63-66.
[55]朱大奇,史慧.人工神经网络原理及其应用[M].北京:科学出版社,2006:164-178.
[56]董长虹. Matlab神经网络与应用(第二版)[M].北京:国防工业出版社, 2007:65-91.
[57]T Kohonen. Self-Organization and Associative Memory [M]. Berlin:Springer-Verlag,1995.
[58]王永骥,涂健.神经元网络控制[M].北京:机械工业出版社,1998:10-12.
[59]Miller W T,Glanz F H&Kraft L G. Application of a general learning algorithm to the control of robotic manipulators[J].The International Journal of Robotics Research, 1987,6(2):84-98.
[60]Miller W T,Glanz F H&Kraft L G. Real-time dynamic control of an industrial manipulator using a neural-network-based learning controller[C].IEEE Transactions on Robotics and Automation, 1990,6(1):1-9.
[61]Sanner R M&Slotine J J E. Stable adaptive control and recursive identification using radial Gaussian networks[C].In:Proceedings of IEEE Conference on Decision and Control,Brighton, , 1991,2116-2123.
[62]Popovic D B,Oguztoreli M N,Stein R B. Optimal control for an active above-knee prosthesis with two degrees of freedom[J].J Biomech, 1995,28:89-98.
[63]Daniel Zlatnik,Beatrice Steiner,Gerhard Schweitzer. Finite-State control of a Trans-Femoral (TF) [J].IEEE Transactions on Control Systems Technology, 2002, 10(3):408-420.
[64]Popovic D B,Tomovic R,Tepavac D. Control aspects an active A/K prosthesis [J]. Int.J. Man-Machine Studyies, 1991,35:751-767.
[65]Vojislav D. Kalanovic,Dejan Popovic,et al. Feedback Error Learning Neural Network for Trans-Femoral Prosthesis[J].IEEETransactions on Rehabilitation Engineering, 2000,8(1):71-80.
[66]Kostov A,Andrews B J,Popovic D B,et al. Machine Learning in Control of Functional Electrical Stimulation(FES) for Locomotion[J].IEEE Trans.Biomed.En., 1995,2:541-551.
[67]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,2008:440-448.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |