多维传感器标定的支持向量机复合式方法

马迎坤; 张希农

多维传感器标定的支持向量机复合式方法

西安交通大学航天航空学院强度与振动教育部重点实验室,西安 710049

基金项目: 国家自然科学基金(10772142)

计量
- 文章访问数: 1369
- HTML浏览量: 1
- PDF量: 18
- 被引次数: 0
出版历程
- 收稿日期: 2010-05-11
- 修回日期: 2010-09-07
- 刊出日期: 2011-06-28

Support vector machine complex method for multi-dimensional sensor calibration

The Key Laboratory of Strength and Vibration of Ministry of Education, School of Aerospace,Xi'an Jiaotong University,Xi'an 710049,China

摘要

摘要: 提出了多维传感器标定的支持向量机复合式标定方法,解决了多维传感器标定中的参数不确定性和耦合非线性因素.对一个多维传感器进行了支持向量机复合标定的仿真研究,将这一方法应用到六维力传感器测量系统的标定试验中.结果表明,与传统标定方法相比,支持向量机复合标定的方法在不增加数据样本的情况下,能够显著提高传感器标定的精度;同时也比纯支持向量机标定有更强的泛化能力,复合标定的模型还可以为传感器的设计提供依据.
- 支持向量机 /
- 复合标定 /
- 多维传感器 /
- 耦合 /
- 非线性
Abstract: A support vector machine(SVM) complex calibration approach was proposed to solve the parameters uncertainty and coupling nonlinearity.The simulation of the calibration of a multi-dimensional sensor was conducted by the SVM complex calibration method,which was then utilized to calibrate a six-dimensional force sensor system.It can be seen from the results that,as compared with other traditional calibration methods,the SVM complex calibration method can improve the calibration accuracy significantly,without increasing data samples;additionally,the complex calibration method also has better generalization performance in comparison with the SVM black box modeling,indicating that it can provide a basis for the design of sensors.
- support vector machine /
- complex calibration /
- multi-dimensional sensor /

HTML

参考文献(12)

[1]	郑红梅,刘正士,王勇.机器人六维腕传感器标定方法和标定装置的研究[J].计量学报,2005,26(1):43-45,85. ZHENG Hongmei,LIU Zhengshi,WANG Yong.Study on the method of dynamic characteristic calibration of the 6-axis wrist force sensor for robot[J].Acta Metrologica Sinica,2005,26(1):43-45,85.(in Chinese)
[2]	尹伟,李华星.压力传感器静态校准模型研究[J].测控技术,2006,25(4):20-25. YIN Wei,LI Huaxing.Research of static calibration models for pressure sensors[J].Measurement & Control Technology,2006,25(4):20-25.(in Chinese)
[3]	姚建涛,侯雨雷,牛建业,等.大量程预紧式六维力传感器及静态标定研究[J].仪器仪表学报,2009,30(6):1233-1239. YAO Jiantao,HOU Yulei,NIU Jianye,et al.Large range prestressed six-axis force sensor and study on static calibration[J].Chinese Journal of Scientific Instrument,2009,30(6):1233-1239.(in Chinese)
[4]	张立明.人工神经网络的模型及其应用[M].上海:复旦大学出版社,2003.
[5]	Cao M,Wang K W.A hybrid neural network approach for the development of friction component dynamic model[J].Journal of Dynamic Systems,Measurement,and Control,2004,126(3):144-153.
[6]	Dong Y F,Li Y M,Lai M,et al.Nonlinear structural response prediction based on support vector machines[J].Journal of Sound and Vibration,2008,311(3-5):886-897.
[7]	Vapnik V.Statistical learning theory[M].New York:John Wiley,1998.
[8]	张崇峰.空间对接六自由度半物理仿真的研究[J].航天控制,1999(1):70-74. Zhang C F.Study on six-degree-of-freedom simulation for docking[J].Aeropace Control,1999(1):70-74.(in Chinese)
[9]	Doebellin E O.Measurement system applications and design[M].New York:McGraw Hill,1985:25-28.
[10]	Diddens D,Reynaerts D,Brussel H V.Design of a ring-shaped three-axis micro force/torque sensor[J].Sensors and Actuators A:Physical,1995,46(1-3):255-231.
[11]	陈胜来.基于神经网络的多分力测试系统杂交建模分析方法研究 .西安:西安交通大学,2008. CHEN Shenglai.A study of hybrid modeling for multi-axis force measuring system based on artificial neural network .Xi'an:Xi'an Jiaotong University,2008.(in Chinese)
[12]	徐科军,李成.多维腕力传感器静态解耦的研究[J].合肥工业大学学报,1999,22(2):1-6. XU Kejun,LI Cheng.Research on static decoupling for multi-dimensional wrist force sensor[J].Journal of Hefei University of Technology,1999,22(2):1-6.(in Chinese)