本文選題：表面肌電信號(hào) + 特征提取��； 參考：《山西大學(xué)》2017年碩士論文

【摘要】：表面肌電信號(hào)作為一種重要的人體生理電信號(hào)可以應(yīng)用于智能系統(tǒng),實(shí)現(xiàn)對(duì)虛擬假肢或智能假肢的控制。目前,在智能仿生假肢研究中,利用肌電信號(hào)特征進(jìn)行動(dòng)作識(shí)別和運(yùn)動(dòng)控制是其研究的關(guān)鍵。論文主要圍繞表面肌電信號(hào)采集與預(yù)處理、肌電特征提取與識(shí)別、虛擬手臂3D模型設(shè)計(jì)以及虛擬假肢動(dòng)作仿真等方面進(jìn)行了相關(guān)研究,主要研究?jī)?nèi)容如下:1)表面肌電信號(hào)采集與預(yù)處理。設(shè)計(jì)了前臂外旋、前臂內(nèi)旋、握拳、展拳、上切、下切、內(nèi)翻和外翻8種動(dòng)作模式,分別采集指伸肌,尺側(cè)腕屈肌,掌長(zhǎng)肌,屈指淺肌4塊前臂肌肉群活動(dòng)的表面肌電信號(hào),利用小波變換結(jié)合自適應(yīng)濾波的方法,對(duì)實(shí)驗(yàn)采集的不同動(dòng)作對(duì)應(yīng)的表面肌電信號(hào)進(jìn)行預(yù)處理,獲得純凈的表面肌電信號(hào)。2)表面肌電信號(hào)特征提取。提取了表面肌電信號(hào)的絕對(duì)積分平均值、均方根值作為時(shí)域特征;提取平均功率頻率、中值頻率作為頻域特特征。采用db3小波進(jìn)行5層小波分解,分別計(jì)算第5層近似系數(shù)與第3、4、5層細(xì)節(jié)系數(shù)的均方根值與方差作為表面肌電信號(hào)的時(shí)頻特征,并對(duì)手臂不同動(dòng)作模式對(duì)應(yīng)的表面肌電信號(hào)特征的差異性進(jìn)行統(tǒng)計(jì)分析。3)基于表面肌電信號(hào)特征的動(dòng)作識(shí)別。首先利用BP神經(jīng)網(wǎng)絡(luò)算法,分別采用肌電信號(hào)的時(shí)域特征、頻域特征以及時(shí)頻特征,進(jìn)行8種手臂動(dòng)作的分類識(shí)別,獲得了89%、77%、91%的平均識(shí)別正確率。然后,設(shè)計(jì)棧式自編碼深度學(xué)習(xí)算法,分別利用表面肌電信號(hào)時(shí)域特征、頻域特征和時(shí)頻特征,進(jìn)行手臂動(dòng)作模式分類,平均分類正確率為95%、91%和96%。結(jié)果表明:肌電信號(hào)時(shí)頻特征能夠較好體現(xiàn)不同動(dòng)作模式之間的差異,同時(shí),棧式自編碼深度學(xué)習(xí)算法應(yīng)用于表面肌電信號(hào)特征分類與動(dòng)作識(shí)別要優(yōu)于BP神經(jīng)網(wǎng)絡(luò)算法。4)虛擬手臂3D假肢設(shè)計(jì)與動(dòng)作仿真。采用改進(jìn)的D-H方法建立了連桿機(jī)械手臂模型,并對(duì)其進(jìn)行了運(yùn)動(dòng)學(xué)分析和軌跡規(guī)劃,利用Matlab軟件仿真平臺(tái),實(shí)現(xiàn)連桿機(jī)械手臂執(zhí)行連續(xù)喝水動(dòng)作的模擬。使用SolidWorks軟件設(shè)計(jì)了虛擬3D假肢模型,并在虛擬現(xiàn)實(shí)環(huán)境中,通過計(jì)算機(jī)仿真驗(yàn)證了虛擬3D假肢模型的合理性。最后,將表面肌電特征的動(dòng)作識(shí)別結(jié)果,通過計(jì)算機(jī)網(wǎng)絡(luò),借助Java跨平臺(tái)傳輸給虛擬假肢,控制虛擬假肢連續(xù)執(zhí)行前臂內(nèi)旋、內(nèi)翻、外翻、前臂外旋與前臂內(nèi)旋90o五個(gè)動(dòng)作,模擬仿真結(jié)果表明了識(shí)別方法的有效性以及動(dòng)作執(zhí)行的完整性和精確性。論文的研究成果能夠應(yīng)用于人工智能、人機(jī)交互、仿生機(jī)器人、智能假肢等領(lǐng)域,具有科學(xué)和應(yīng)用雙重價(jià)值。
[Abstract]:As an important physiological signal of human body, surface electromyography (EMG) signal can be used in intelligent system to control virtual prosthesis or intelligent prosthesis. At present, in the research of intelligent biomimetic prosthesis, it is the key to use EMG signal to recognize and control the motion. This paper mainly focuses on the surface EMG signal acquisition and pretreatment, EMG feature extraction and recognition, virtual arm 3D model design and virtual artificial limb movement simulation. The main research contents are as follows: 1) Surface EMG signal acquisition and preprocessing. Eight modes of forearm external rotation, forearm internal rotation, fist grip, extended fist, upper cut, bottom cut, varus and valgus were designed. The surface EMG signals of four forearm muscles were collected, including extensor digitorum muscle, flexor Carpi ulnar muscle, palmar longus muscle and flexor superficial muscle. Wavelet transform combined with adaptive filtering is used to preprocess the surface EMG signal corresponding to different actions collected in the experiment, and the pure surface EMG signal (.2) surface EMG signal feature extraction is obtained. The absolute integral mean value of surface EMG signal is extracted, the root mean square value is taken as the time domain feature, and the average power frequency and median frequency are extracted as the special features in frequency domain. The db3 wavelet is used to decompose the five layer wavelet, and the root mean square value and variance of the fifth and the third layer detail coefficients are calculated respectively as the time-frequency characteristics of the surface EMG signal. The differences of EMG signal characteristics corresponding to different arm movements are analyzed statistically. 3) the action recognition based on SEMG features is presented. Firstly, the BP neural network algorithm is used to classify and recognize eight arm movements by using the time domain feature and frequency domain feature of EMG, respectively, and the average recognition accuracy of 89777% is obtained. Then, a stack self-coding depth learning algorithm is designed to classify the arm motion patterns using the time-domain, frequency-domain and time-frequency features of surface EMG signals, respectively. The average classification accuracy is 95% and 96% respectively. The results show that the time-frequency characteristics of EMG signals can well reflect the differences between different action modes, and at the same time, The self-coding depth learning algorithm based on stack is better than BP neural network algorithm in feature classification and motion recognition of surface EMG signal. 4) 3D artificial limb design and motion simulation of virtual arm. An improved D-H method is used to establish the model of the connecting rod manipulator, and the kinematics analysis and trajectory planning are carried out. The simulation of the continuous water movement of the connecting rod manipulator is realized by using Matlab software simulation platform. The virtual 3D prosthesis model is designed with SolidWorks software, and the rationality of the virtual 3D prosthesis model is verified by computer simulation in the virtual reality environment. Finally, the recognition results of the surface electromyoelectric features are transmitted to the virtual prosthesis by means of the Java platform through the computer network. The virtual prosthesis is controlled to perform the five actions of forearm internal rotation, varus, valgus, forearm external rotation and forearm internal rotation 90o continuously. Simulation results show the effectiveness of the method and the integrity and accuracy of the action execution. The research results can be applied to artificial intelligence, human-computer interaction, bionic robot, intelligent prosthesis and so on.
【學(xué)位授予單位】：山西大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R318;TN911.7

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 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

2 明東;王欣;徐瑞;邱爽;趙欣;綦宏志;周鵬;張力新;萬柏坤;;sEMG Feature Analysis on Forearm Muscle Fatigue During Isometric Contractions[J];Transactions of Tianjin University;2014年02期

3 程秀芳;侯偉民;徐文墨;;用于生物模型的表面肌電信號(hào)處理[J];河北聯(lián)合大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年01期

4 張啟忠;席旭剛;羅志增;;基于非線性特征的表面肌電信號(hào)模式識(shí)別方法[J];電子與信息學(xué)報(bào);2013年09期

5 鄒曉陽;雷敏;;基于多尺度最大李雅普諾夫指數(shù)的表面肌電信號(hào)模式識(shí)別[J];中國(guó)生物醫(yī)學(xué)工程學(xué)報(bào);2012年01期

6 王智興;樊文欣;張保成;史源源;;基于Matlab的工業(yè)機(jī)器人運(yùn)動(dòng)學(xué)分析與仿真[J];機(jī)電工程;2012年01期

7 邢廣成;張洛花;;基于MATLAB的PUMA機(jī)器人運(yùn)動(dòng)仿真研究[J];科技資訊;2011年30期

8 劉萍;陳瑩;;五自由度關(guān)節(jié)式機(jī)械手運(yùn)動(dòng)學(xué)分析及仿真[J];制造業(yè)自動(dòng)化;2011年19期

9 程立艷;費(fèi)凌;蘇澤郎;;基于MATLAB五自由度機(jī)械手運(yùn)動(dòng)學(xué)仿真分析[J];機(jī)械研究與應(yīng)用;2011年04期

10 樊紹巍;劉伊威;金明河;蘭天;陳兆們;劉宏;趙大威;;HIT/DLR HandⅡ類人形五指靈巧手機(jī)構(gòu)的研究[J];哈爾濱工程大學(xué)學(xué)報(bào);2009年02期

相關(guān)博士學(xué)位論文 前3條

1 李陽;智能仿生手臂肌電信號(hào)—運(yùn)動(dòng)模型化與模式識(shí)別理論方法研究[D];吉林大學(xué);2012年

2 趙章琰;表面肌電信號(hào)檢測(cè)和處理中若干關(guān)鍵技術(shù)研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2010年

3 趙衍運(yùn);圖像對(duì)象特征提取與識(shí)別[D];北京郵電大學(xué);2009年

相關(guān)碩士學(xué)位論文 前7條

1 師宏慧;語音情感識(shí)別方法研究[D];山西大學(xué);2016年

2 鄭世鈺;基于支持向量機(jī)的手臂動(dòng)作表面肌電信號(hào)模式分類方法研究[D];吉林大學(xué);2014年

3 周科;六軸工業(yè)機(jī)器人設(shè)計(jì)與軌跡規(guī)劃方法研究[D];哈爾濱工業(yè)大學(xué);2013年

4 孫保峰;基于神經(jīng)網(wǎng)絡(luò)的表面肌電信號(hào)分類方法研究[D];吉林大學(xué);2013年

5 張志勇;肌電信號(hào)采集與肌電假肢控制的研究[D];哈爾濱工業(yè)大學(xué);2010年

6 邱青菊;表面肌電信號(hào)的特征提取與模式分類研究[D];上海交通大學(xué);2009年

7 張勇;基于Simulink的機(jī)器人虛擬現(xiàn)實(shí)仿真研究[D];哈爾濱工程大學(xué);2007年

，

本文編號(hào)：2105019