基于神经网络的假肢无线控制系统的设计Design of prosthesis wireless control system based on neural network
彭子韬,许鹏,沈晓燕,吴芳
摘要(Abstract)：
为了改善残疾人生活水平和促进医疗事业发展,提出一种基于神经网络的假肢无线控制系统设计方案。该系统以STM32为核心芯片,通过采集上肢肱二头肌、肱三头肌、指浅屈肌、指伸肌4块肌肉的肌电信号,使用BP神经网络与SOFM神经网络相结合对肌电信号进行模式识别,实时控制肌电假肢的完成伸臂、屈臂、腕内旋、腕外旋、握拳、张手6种动作行为。实验结果表明,该系统对6种动作的整体识别率可达97%,并且采用无线实时的控制方式,能够更方便地帮助部分肢体残疾患者完成这些基本的操作行为。
关键词(KeyWords)： 神经网络;肌电信号;模式识别;STM32;无线控制;肌电假肢
基金项目(Foundation): 国家自然科学基金重大项目(61534003);国家自然科学基金面上项目(81371663);; 江苏高校品牌专业建设工程资助项目(PPZY2015B135)资助~~
作者(Author): 彭子韬,许鹏,沈晓燕,吴芳
DOI: 10.16652/j.issn.1004-373x.2018.02.016
参考文献(References)：
- [1]中国残疾人联合会.2010年末全国残疾人总数及各类、不同残疾等级人数[EB/OL].[2013-01-29].http://www.cdpf.org.cn/sjzx/cjrgk/201206/t20120626_387581.shtml.China Disabled Persons′Federation.The total number of the disabled and the number of each level of the disabled in China at the end of 2010[EB/OL].[2013-01-29].http://www.cdpf.org.cn/sjzx/cjrgk/201206/t20120626_387581.shtml.
- [2]LI G,SCHULTZ A E,KUIKEN T A.Quantifying pattern recognition-based myoelectric control of multifunctional transradial prostheses[J].IEEE transactions on neural system and rehabilitation engineering,2010,18(2):185-192.
- [3]丁其川,熊安斌,赵新刚,等.基于表面肌电的运动意图识别方法研究及应用综述[J].自动化学报,2016,42(1):13-25.DING Qichuan,XIONG Anbin,ZHAO Xingang,et al.Research and application of motion intention recognition method based on surface electromyography[J].Journal of automation,2016,42(1):13-25.
- [4]田岚,姜乃夫,李光林.基于微处理器的多功能肌电假肢控制系统[J].集成技术,2013,2(4):14-19.TIAN Lan,JIANG Naifu,LI Guanglin.Multifunctional myoelectric prosthetic control system based on microprocessor[J].Integration technology,2013,2(4):14-19.
- [5]孙保峰.基于神经网络的表面肌电信号分类方法研究[D].长春:吉林大学,2013.SUN Baofeng.Classification of surface EMG signals based on neural network[D].Changchun:Jilin University,2013.
- [6]ZHANG Q H,MENG X H,GUO H C,et al.Obstacles based on BP neural network pattern recognition[C]//Proceedings of2012 International Conference on Mechatronics and Automation(ICMA).Chengdu:IEEE,2012:2574-2581.
- [7]LI Y,TIAN Y,CHEN W.Multi-pattern recognition of s EMG based on improved BP neural network algorithm[C]//Proceedings of Chinese Control Conference.Beijing:Chinese Academy of Science,2010(7):2867-2872.
- [8]朱福珍,吴斌.SOFM网络及其在Matlab中的实现[J].微计算机信息,2005,21(12):163-165.ZHU Fuzhen,WU Bin.SOFM network and its implementation in MATLAB[J].Microcomputer information,2005,21(12):163-165.
- [9]李萍,曾令可,税安泽,等.基于MATLAB的BP神经网络预测系统的设计[J].计算机应用与软件,2008,25(4):149-150.LI Ping,ZENG Lingke,SHUI Anze,et al.Design of BP neural network prediction system based on MATLAB[J].Computer application and software,2008,25(4):149-150.
- [10]喻洪流,胡加华.基于动态阈值的肌电假手动作控制方法研究[J].现代科学仪器,2011(3):43-45.YU Hongliu,HU Jiahua.Research on control method of dynamic threshold based on the action of prosthetic hand[J].Modern scientific instruments,2011(3):43-45.