Title :
A research of multi-axis force sensor static decoupling method based on neural network
Author :
Huibin Cao;Yong Yu;Yunjian Ge
Author_Institution :
Institute of Intelligent Machine Chinese Academy of Science Hefei, Anhui Province, China
Abstract :
The static coupling of multi-axis force sensor is a major influencing factor to its measuring precision. Aiming at resolving the disadvantages such as low decoupling precision of the traditional method, we put forward a linear decoupling method based on neural network. Firstly, this paper analyzes the reasons why coupling exists in the multi-axis force sensor, and then according to this phenomenon, this method gains a weight matrix by using the associational function of the linear model of the neural networks and the matrix can reflect the coupling force of different dimensions correctly. Comparing to the traditional static decoupling method, this method improves the precision of decoupling greatly. In the end of this paper, experiments and traditional decoupling method are used to compare and prove the effectiveness of this method.
Keywords :
"Force sensors","Neural networks","Intelligent sensors","Force measurement","Capacitive sensors","Fingers","Calibration","Intelligent networks","Machine intelligence","Robot sensing systems"
Conference_Titel :
Automation and Logistics, 2009. ICAL ´09. IEEE International Conference on
Print_ISBN :
978-1-4244-4794-7
Electronic_ISBN :
2161-816X
DOI :
10.1109/ICAL.2009.5262800