بهبود کنترل بازوی رباتیک به کمک کنترل¬کننده تطبیقی مدل مرجع با استفاده از طبقهبندی سیگنال¬های EMG
محورهای موضوعی : مهندسی برق و کامپیوترمهسا برفی 1 , حمیدرضا کرمی 2 * , الهام فراهی 3 , فاطمه فریدی 4 , سید منوچهر حسینی پیلانگرگی 5
1 - دانشگاه بوعلی سینا،دانشکده فنی و مهندسی
2 - دانشگاه بوعلی سینا،دانشکده فنی و مهندسی
3 - دانشگاه بوعلی سینا،دانشکده فنی و مهندسی
4 - دانشگاه بوعلی سینا
5 - دانشگاه بوعلی سینا،دانشکده فنی و مهندسی
کلید واژه: الکترومیوگرافی, آنالیز تشخیصی خطی, ربات دو درجه آزادی, کنترلکننده تطبیقی مدل مرجع,
چکیده مقاله :
هدف این مقاله، بهبود کنترل بازوی رباتیک به کمک کنترلکننده تطبیقی مدل مرجع مبتنی بر نظریه لیاپانوف با استفاده از طبقهبندی سیگنالهای الکترومیوگرام (EMG) است. در این مقاله، بازوی انسان با یک ربات دو درجه آزادی مدلسازی شده است. روش کنترلی پیشنهادی، کنترلکننده تطبیقی مدل مرجع است. ماحصل این پژوهش، طراحی و شبیهسازی بازوی رباتیک به همراه کنترلکننده تطبیقی مدل مرجع است که با استفاده از طبقهبندی دادههای EMG ثبتشده از حرکات بازوی انسان، منتج به ردیابی مناسب سیگنال مرجع، فراجهش و خطای حالت ماندگار کمتر در مقایسه با کنترلکننده مرسوم PI شده است. بدین منظور ابتدا دادههای EMG با استفاده از دو الکترود از عضلات دلتوئید قدامی و دلتوئید میانی بازوی پنج دختر و با انجام دو حرکت دورشدن (ابداکشن) و خمشدن (فلکشن) بازو جمعآوری شده و پس از رفع نویز، ویژگیهای ریاضی انتگرال مقدار مطلق، گذر از صفر، واریانس و فرکانس میانه از آنها استخراج میشود. سپس کلاسبندی به روش آنالیز تشخیصی خطی به منظور تشخیص حرکات بر اساس ویژگیهای دادهها صورت میگیرد. در نهایت، مدل و سیستم کنترلکننده پیشنهادی با توجه به ویژگیهای سیگنال EMG، برای دستیابی به پاسخ کنترلی مناسب، طراحی میشوند و سیگنال فرمان مناسب جهت انجام حرکت مربوطه به کنترلکننده ارسال میشود. نتایج و مقادیر خطاهای حاصلشده نشان میدهند که انطباق رفتار مدل و کنترلکننده حاصل با الگوی از پیش تعریف شده حرکتی قابل توجه و مورد تأیید است.
The purpose of designing and manufacturing prosthetic organs is to create their maximum behavioral similarity to human organs. The aim of this paper is to improve the robotic arm control via Model Reference Adaptive System (MRAS) based on Lyapunov theory using EMG data classification. In this paper, human arm is modeled with a robot with two degrees of freedom. The proposed control method is MRAS. The outcome of this research is a robotic arm with MRAS, using the classification of electromyogram (EMG) data recorded from human arm movements, results in proper tracking of the reference signal, less overshoot and steady-state error compared to the conventional PI controller. For this purpose, using two electrodes, EMG data is collected from the anterior deltoid and middle deltoid muscles of the arm of five female athletes and by performing two movements of abduction and flexion of the arm. Then, after eliminating noise, integral of absolute value (IAV), zero crossing (ZC), variance (VAR) and median frequency (MF) are extracted. Then, classification is done by linear discriminant analysis (LDA) method to detect movements based on data characteristics. Finally, the proposed controller and model are designed according to the EMG characteristics to achieve the proper control response and the appropriate command signal is sent to the controller to perform the corresponding movement. The results and the values of the obtained errors show the conformity of the model and controller behavior with the predefined movement pattern.
[1] P. Konrad, The ABC of EMG A Practical Introduction to Kinesiological Electromyography, pp. 4-6, Noraxon Inc. USA, 2005.
[2] J. Hamill and K. M. Knutzen, Biomechanical Basis of Human Movement, Lippincott Williams & Wilkins, Oct. 2006.
[3] G. Robertson, G. Caldwell, J. Hamill, G. Kamen, and S. Whittlesey, Research Methods in Biomechanics Human Kinetics, 2013.
[4] F. Sadikoglu, C. Kavalcioglu, and B. Dagman, "Electromyogram (EMG) signal detection, classification of EMG signals and diagnosis of neuropathy muscle disease," Procedia Computer Science, vol. 120, pp. 422-429, 2017.
[5] N. Feng, et al., "A soft robotic hand: design, analysis, sEMG control, and experiment," The International J. of Advanced Manufacturing Technology, vol. 97, pp. 319-333, 2018.
[6] G. Lisi, P. Belluco, D. Cattaneo, and G. Gini, "From the classification of EMG signals to the development of a new lower arm prosthesis," IFAC Proceedings Volumes, vol. 44, no. 1, pp. 6493-6498, Jan. 2011.
[7] E. Raveh, S. Portnoy, and J. Friedman, "Adding vibrotactile feedback to a myoelectric controlled hand improves performance when online visual feedback is disturbed," Human Movement Science, vol. 58, pp. 32-40, Apr. 2018.
[8] M. Tavakoli, C. Benussi, and J. L. Lourenco, "Single channel surface EMG control of advanced prosthetic hands: a simple, low cost and efficient approach," Expert Systems with Applications, vol. 79, pp. 322-332, 15 Aug. 2017.
[9] I. I. Borisov, O. V. Borisova, S. V. Krivosheev, R. V. Oleynik, and S. S. Reznikov, "Prototyping of EMG-controlled prosthetic hand with sensory system," IFAC-PapersOnLine, vol. 50, no. 1, pp. 16027-16031, Jul. 2017.
[10] P. K. Artemiadis and K. J. Kyriakopoulos, "EMG-based control of a robot arm using low-dimensional embedding," IEEE Trans. on Robotics, vol. 26, no. 2, pp. 393-398, Apr. 2010.
[11] S. Javier Patricio Collahuazo and M. Esteban Fernando Ordoñez, "Design and construction of a robot hand activated by electromyographic signals," in Proc. IEEE Int. Symp. on Robotic and Sensors Environments Proceedings, pp. 25-30, Magdeburg, Germany, 16-18 Nov. 2012.
[12] M. Qingyun, Q. Meng, H. Yu, and X. Wei, "A survey on sEMG control strategies of wearable hand exoskeleton for rehabilitation," in Proc.2nd IEEE Asia-Pacific Conf. on Intelligent Robot Systems, ACIRS’17, pp. 165-169, Wuhan, China, 16-18 Jun. 2017.
[13] Z. Lu, K. Y. Tong, X. Zhang, S. Li, and P. Zhou, "Myoelectric pattern recognition for controlling a robotic hand: a feasibility study in stroke," IEEE Trans. on Biomedical Engineering, vol. 66, no. 2, pp. 365-372, Feb. 2018.
[14] M. Rossi, et al., "Preliminary results toward a naturally controlled multi-synergistic prosthetic hand," in Proc. IEEE Int. Conf. on Rehabilitation Robotics, ICORR’17, pp. 1356-1363, London, UK, 17-20 Jul. 2017.
[15] https://myndfitlife.com/big-shoulders-now-killing-exercises/
[16] MA-300 EMG System User Guide, Motion Lab Systems, Baton Rouge, LA, 2004.
[17] R. T. Floyd, Manual of Structural Kinesiology, 19th Ed., McGraw-Hill Education, New York, 2015.
[18] P. K. Artemiadis and K. J. Kyriakopoulos, "A switching regime model for the EMG-based control of a robot arm," IEEE Trans. on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 41, no. 1, pp. 53-63, Feb. 2010.
[19] X. Sheng, B. Lv, W. Guo, and X. Zhu, "Common spatial-spectral analysis of EMG signals for multiday and multiuser myoelectric interface," Biomedical Signal Processing and Control, vol. 53, Article ID: 101572, Aug. 2019.
[20] K. Englehart and B. Hudgins, "A robust, real-time control scheme for multifunction myoelectric control," IEEE Trans. on Biomedical Engineering, vol. 50, no. 7, pp. 848-854, Jul. 2003.
[21] A. Nazemi and A. Maleki, "Artificial neural network classifier in comparison with LDA and LS-SVM classifiers to recognize 52 hand postures and movements," in Proc. 4th IEEE Int.l Conf. on Computer and Knowledge Engineering, ICCKE’14, pp. 18-22, Mashhad, Iran, 29-30 Oct. 2014.
[22] D. P. Yang, et al., "An anthropomorphic robot hand developed based on underactuated mechanism and controlled by EMG signals," J. of Bionic Engineering, vol. 6, no. 3, pp. 255-263, Sept. 2009.
[23] I. I. Kuzborskij, A. Gijsberts, and B. Caputo, "On the challenge of classifying 52 hand movements from surface electromyography," in Proc. of Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society, pp. 4931-4937, San Diego, CA, USA, 28 Aug.-1 Sept. 2012.
[24] S. Saud, B. Jamil, Y. Upadhyay, and K. Irshad, "Performance improvement of empirical models for estimation of global solar radiation in India: a k-fold cross-validation approach," Sustainable Energy Technologies and Assessments, vol. 40, Article ID: 100768, Aug. 2020.
[25] M. A. Khan, et al., "Geopolymer concrete compressive strength via artificial neural network, adaptive neuro fuzzy interface system, and gene expression programming with K-fold cross validation," Front. Mater., vol. 8, Article ID: 62116, 3 May 2021.
[26] Y. Tang, Y. Q. Zhang, N. V. Chawla, and S. Krasser, "SVMs modeling for highly imbalanced classification," IEEE Trans. on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 39, no. 1, pp. 281-288, Feb. 2008.
[27] A. Prakash, A. K. Sahi, N. Sharma, and S. Sharma, "Force myography controlled multifunctional hand prosthesis for upper-limb amputees," Biomedical Signal Processing and Control, vol. 62, Article ID: 102122, Sept. 2020.
[28] P. K. Artemiadis and K. J. Kyriakopoulos, "EMG-based control of a robot arm using low-dimensional embeddings," IEEE Trans. on Robotics, vol. 26, no. 2, pp. 393-398, Apr. 2010.
[29] S. Sastry and M. Bodson, Adaptive Control: Stability, Convergence and Robustness, Courier Corporation, 2011.
[30] N. Wang, K. Lao, and X. Zhang, "Design and myoelectric control of an anthropomorphic prosthetic hand," J. of Bionic Engineering, vol. 14, no. 1, pp. 47-59, Jan. 2017.