计算机应用 ›› 2015, Vol. 35 ›› Issue (7): 2109-2112.DOI: 10.11772/j.issn.1001-9081.2015.07.2109

• 行业与领域应用 • 上一篇    

基于肌电信号的多模式抓握力估计

张冰珂1,2, 段小刚1,2, 邓华1,2   

  1. 1. 中南大学 高性能复杂制造国家重点实验室, 长沙 410083;
    2. 中南大学 机电工程学院, 长沙 410083
  • 收稿日期:2015-01-26 修回日期:2015-03-31 出版日期:2015-07-10 发布日期:2015-07-17
  • 通讯作者: 段小刚(1972-),男,湖南湘潭人,讲师,博士,主要研究方向:智能控制、机器人动力学,xgduan@csu.edu.cn
  • 作者简介:张冰珂(1991-),女,湖南岳阳人,硕士研究生,主要研究方向:生物机电一体化、智能控制; 邓华(1961-),男,湖南岳阳人,教授,博士,主要研究方向:机器人、机电液智能控制。
  • 基金资助:

    国家973计划项目(2011CB013302)。

Force estimation in different grasping mode from electromyography

ZHANG Bingke1,2, DUAN Xiaogang1,2, DENG Hua1,2   

  1. 1. State Key Laboratory of High Performance Complex Manufacturing, Central South University, Changsha Hunan 410083, China;
    2. College of Mechanical and Electrical Engineering, Central South University, Changsha Hunan 410083, China
  • Received:2015-01-26 Revised:2015-03-31 Online:2015-07-10 Published:2015-07-17

摘要:

针对大多肌电控制的假肢只研究模式识别而没有对抓握力和抓握模式同步解码的问题,提出一种同时分析抓握模式和抓取力的方法。首先,采用4通道表面电极采集人体手臂肌电信号(EMG),采用力敏电阻(FSR)采集抓取力信号;然后,分别利用线性判别分析(LDA)方法和人工神经网络(ANN)进行抓握模式识别和力估计。在4种抓握模式下分别建立4个肌电信号-力关系,一旦判别出抓取模式,则调用相应模式下肌电信号-力模型估计抓握力大小以实现模式识别和力估计的结合。实验结果表明,当进行模式和力的同步解码时,模式平均分类精度约为77.8%,力估计的准确率约为90%。该方法可以用于假肢的肌电控制,不仅可以解码使用者的抓取动作的意图,还可以解码使用者期望的抓取力,辅助假肢实现稳定抓取。

关键词: 肌电信号, 假肢手, 人工神经网络, 模式识别, 指尖力

Abstract:

A method to analyze the grasping and pattern force of Electromyography (EMG) simultaneously was proposed, in order to solve the problem that most myoelectric survey focused only on pattern recognition regardless of the combination of grasping pattern and force. First, surface EMG signals were collected through 4 EMG electrodes. Force data was obtained by Force Sensor Resistor (FSR). Then, the Linear Discriminant Analysis (LDA) method was used to realize pattern recognition and Artificial Neural Networks (ANN) was applied to estimate force. 4 types of EMG-force relationship were built in 4 different grasping modes. Once the grasping pattern identified, the program called the corresponding force model to estimate force value and achieved the combination force decoding and pattern recognition. The experimental results illustrate that when pattern and force are analyzed simultaneously, the average classification accuracy is about 77.8%; meanwhile the force prediction accuracy rate is about 90%. The proposed method can be applied to myoelectric control of the prosthetic hand, not only the user's intension of grasping mode can be decoded, but also the desired force can also be estimated. The stable grasping can be assisted by this approach.

Key words: Electromyography (EMG), prosthetic hand, Artificial Neural Network (ANN), pattern recognition, fingertip force

中图分类号: