本文選題：肌電信號(hào) + 連續(xù)估計(jì)��； 參考：《杭州電子科技大學(xué)》2017年碩士論文

【摘要】：表面肌電信號(hào)(Surface Electromyography,sEMG)是肌肉收縮時(shí)所產(chǎn)生的動(dòng)作電位在皮膚表面疊加而成,與肢體的運(yùn)動(dòng)直接相關(guān),可以用來(lái)反應(yīng)人的運(yùn)動(dòng)意圖。由于sEMG具有蘊(yùn)含信息豐富、采集方便等特點(diǎn),在運(yùn)動(dòng)控制、康復(fù)醫(yī)療等領(lǐng)域具有重要應(yīng)用價(jià)值。本文以肌電假肢多自由度比例同步控制為立足點(diǎn),設(shè)計(jì)實(shí)驗(yàn)采集上肢關(guān)節(jié)肌肉動(dòng)作所產(chǎn)生的肌電信號(hào)和運(yùn)動(dòng)參數(shù),結(jié)合肌肉協(xié)同理論從中樞神經(jīng)系統(tǒng)協(xié)同控制人體運(yùn)動(dòng)的角度出發(fā),著重分析協(xié)同元、激活系數(shù)和角度之間的關(guān)系,并應(yīng)用肌肉協(xié)同的模型解決肌電假肢的比例同步控制問(wèn)題。首先,相比模式分類控制方法,連續(xù)估計(jì)控制方法更符合人體運(yùn)動(dòng)規(guī)律,可以類人實(shí)現(xiàn)關(guān)節(jié)的比例同步控制。本文結(jié)合人體前臂常用動(dòng)作模式,設(shè)計(jì)了上肢三個(gè)自由度的獨(dú)立和組合動(dòng)作實(shí)驗(yàn),通過(guò)運(yùn)用三維運(yùn)動(dòng)捕捉系統(tǒng)同步采集前臂肌電信號(hào)和對(duì)應(yīng)動(dòng)作的關(guān)節(jié)角度,為后續(xù)研究打下數(shù)據(jù)基礎(chǔ)。其次,引入肌肉協(xié)同理論來(lái)進(jìn)一步解釋和解決人體運(yùn)動(dòng)過(guò)程中多自由度運(yùn)動(dòng)協(xié)調(diào)問(wèn)題。通過(guò)分而治之的方法確定對(duì)應(yīng)前臂六個(gè)獨(dú)立動(dòng)作的六個(gè)協(xié)同元,利用非負(fù)矩陣分解(Non-negative Matrix Factorization,NMF)算法對(duì)肌電信號(hào)的均方根特征分解提取出表示中樞神經(jīng)系統(tǒng)低維控制參數(shù)的肌肉協(xié)同元;利用非負(fù)最小二乘算法提取出表示對(duì)協(xié)同元刺激程度的激活系數(shù)。通過(guò)對(duì)比激活系數(shù)和關(guān)節(jié)真實(shí)運(yùn)動(dòng)軌跡,發(fā)現(xiàn)激活系數(shù)可以反映出動(dòng)作類別和肌肉激活程度,但是激活系數(shù)并不能完全反映出上肢的實(shí)際運(yùn)動(dòng)軌跡,動(dòng)作之間的激活系數(shù)也沒(méi)有充分解耦。然后,為了進(jìn)一步解決激活系數(shù)和運(yùn)動(dòng)軌跡之間的偏差問(wèn)題,分解各個(gè)動(dòng)作激活系數(shù)之間的耦合性。通過(guò)人工蜂群算法優(yōu)化的支持向量回歸(Support Vector Regression,SVR)算法和BP神經(jīng)網(wǎng)絡(luò)回歸算法分別構(gòu)建了映射激活系數(shù)到關(guān)節(jié)角度的SVR激活模型和BP激活模型,利用建立的激活模型從采集的表面肌電信號(hào)得到關(guān)節(jié)運(yùn)動(dòng)的連續(xù)估計(jì)。對(duì)兩個(gè)關(guān)節(jié)獨(dú)立和組合運(yùn)動(dòng)的估計(jì)實(shí)驗(yàn)表明,SVR和BP激活模型均能獲得較好的估計(jì)精度,但是SVR激活模型可以獲得更穩(wěn)定和更精確的估計(jì)效果。接著,為了分析關(guān)節(jié)動(dòng)作的快慢程度對(duì)SVR激活模型估計(jì)效果的影響,設(shè)計(jì)了掌關(guān)節(jié)和腕關(guān)節(jié)三個(gè)自由度動(dòng)作分別在高速、中速、低速運(yùn)動(dòng)模式下的動(dòng)作實(shí)驗(yàn)。根據(jù)相關(guān)系數(shù)、均方根誤差和t檢驗(yàn)分析估計(jì)結(jié)果,指出SVR激活模型在高速和中速狀態(tài)下可以獲得良好的估計(jì)效果。最后,設(shè)計(jì)了肌電假肢比例同步控制的在線仿真實(shí)驗(yàn)。通過(guò)獨(dú)立和組合動(dòng)作的在線控制任務(wù),測(cè)試SVR激活模型對(duì)單自由度和多自由度動(dòng)作的比例同步控制效果。本文研究成果給肌電假肢的控制方法提供了一種新的方案。
[Abstract]:Surface electromyography (EMG) is a superposition of action potential produced by muscle contraction on the skin surface, which is directly related to the movement of the limbs and can be used to reflect the intention of human motion. Because of its rich information and convenient collection, sEMG has important application value in the field of movement control, rehabilitation and medical treatment. In this paper, the multi-degree-of-freedom proportional synchronous control of EMG prosthesis is taken as the foothold, and the EMG signals and motion parameters produced by the muscle movement of the upper limb joint are collected experimentally. Based on the theory of muscle coordination, the relationship among synergetic elements, activation coefficients and angles is analyzed from the point of view of central nervous system coordinated control of human body movement. The model of muscle coordination is applied to solve the problem of proportional synchronous control of myoelectric prosthesis. Firstly, compared with the pattern classification control method, the continuous estimation control method is more consistent with the human motion law, and it can realize the proportional synchronous control of joints. In this paper, combined with the common action mode of human forearm, the experiment of three degrees of freedom of upper limb is designed. The electromyography signal of forearm and the joint angle of corresponding action are collected synchronously by using three-dimensional motion capture system. To lay the data foundation for the follow-up research. Secondly, the theory of muscle coordination is introduced to further explain and solve the problem of multi-degree-of-freedom motion coordination. Using the divide-and-conquer method to determine the six synergetic elements corresponding to the six independent actions of the forearm, Non-negative Matrix factorization (NMF) algorithm is used to extract muscle synergists representing the low dimensional control parameters of central nervous system (CNS). The non-negative least squares algorithm is used to extract the activation coefficients representing the stimulus degree of the synergists. By comparing the activation coefficient with the real motion trajectory of the joint, it was found that the activation coefficient could reflect the type of movement and the degree of muscle activation, but the activation coefficient could not completely reflect the actual movement track of the upper limb. The activation coefficients between actions are also not fully decoupled. Then, in order to solve the problem of the deviation between the activation coefficient and the motion trajectory, the coupling between the activation coefficients of each action is decomposed. The SVR activation model and BP activation model of mapping activation coefficient to joint angle are constructed by the support vector regression support Vector regression algorithm and BP neural network regression algorithm optimized by artificial bee colony algorithm, respectively. The continuous estimation of joint motion is obtained from the collected surface EMG signals using the established activation model. The experiments of joint independent and combined motion estimation show that both SVR and BP activation model can obtain better estimation accuracy, but SVR activation model can obtain more stable and accurate estimation results. Then, in order to analyze the influence of the speed and slowness of joint action on the estimation effect of SVR activation model, three degrees of freedom (DOF) motions of metacarpal joint and wrist joint were designed in high speed, middle speed and low speed motion mode respectively. According to the correlation coefficient, root mean square error and t test, it is pointed out that the SVR activation model can obtain good estimation results at high and medium speed. Finally, the online simulation experiment of proportion synchronous control of myoelectric prosthesis is designed. Through the on-line control task of independent and combined actions, the proportional synchronization control effect of SVR activation model for single and multi-degree-of-freedom actions is tested. The results of this paper provide a new scheme for the control of myoelectric prosthesis.
【學(xué)位授予單位】：杭州電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R318.17;TN911.7

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 黃寶瑩;周臣清;黃玲玲;蘇妙儀;;配對(duì)t檢驗(yàn)法比較3種方法檢測(cè)奶粉中金黃色葡萄球菌計(jì)數(shù)結(jié)果[J];中國(guó)乳品工業(yè);2016年08期

2 劉銘;劉精精;何禹德;;基于GA-SVR算法的淀粉價(jià)格預(yù)測(cè)研究[J];數(shù)學(xué)的實(shí)踐與認(rèn)識(shí);2016年08期

3 丁其川;熊安斌;趙新剛;韓建達(dá);;基于表面肌電的運(yùn)動(dòng)意圖識(shí)別方法研究及應(yīng)用綜述[J];自動(dòng)化學(xué)報(bào);2016年01期

4 劉建;鄒任玲;張東衡;徐秀林;胡秀枋;;表面肌電信號(hào)特征提取方法研究發(fā)展趨勢(shì)[J];生物醫(yī)學(xué)工程學(xué)進(jìn)展;2015年03期

5 倪自強(qiáng);王田苗;劉達(dá);;醫(yī)療機(jī)器人技術(shù)發(fā)展綜述[J];機(jī)械工程學(xué)報(bào);2015年13期

6 丁帥;王亮;;基于塊稀疏貝葉斯學(xué)習(xí)的肌電信號(hào)特征提取[J];儀器儀表學(xué)報(bào);2014年12期

7 丁其川;趙新剛;韓建達(dá);;基于肌電信號(hào)的上肢多關(guān)節(jié)連續(xù)運(yùn)動(dòng)估計(jì)[J];機(jī)器人;2014年04期

8 王琳;張峗;彭文輝;徐波;王前程;;基于人工蜂群優(yōu)化的支持向量回歸預(yù)測(cè)方法[J];系統(tǒng)工程與電子技術(shù);2014年02期

9 林輝杰;嚴(yán)波濤;許崇高;梁海丹;;基于函數(shù)型數(shù)據(jù)分析技術(shù)的運(yùn)動(dòng)協(xié)調(diào)量化方法應(yīng)用研究[J];體育科學(xué);2012年09期

10 林輝杰;嚴(yán)波濤;劉占鋒;許崇高;梁海丹;;運(yùn)動(dòng)協(xié)調(diào)的定量方法以及在專項(xiàng)技術(shù)分析領(lǐng)域的研究進(jìn)展[J];體育科學(xué);2012年03期

相關(guān)博士學(xué)位論文 前1條

1 林輝杰;擲鐵餅動(dòng)作中人體運(yùn)動(dòng)協(xié)調(diào)特征研究[D];上海體育學(xué)院;2013年

相關(guān)碩士學(xué)位論文 前4條

1 楊帥;基于AdaBoost算法的手部動(dòng)作表面肌電信號(hào)分類方法研究[D];吉林大學(xué);2015年

2 李飛;基于表面肌電信號(hào)的小兒腦癱步態(tài)肌肉協(xié)同分析[D];中國(guó)科學(xué)技術(shù)大學(xué);2014年

3 趙鵬;基于肌電反饋的下肢康復(fù)機(jī)器人控制策略研究[D];燕山大學(xué);2014年

4 游淼;基于肌動(dòng)圖（MMG）與肌電圖（EMG）信號(hào)的假肢控制系統(tǒng)研究[D];中南大學(xué);2011年

，

本文編號(hào)：1895273