基于RF-GA的六维力传感器解耦方法  

Decoupling Method of Six-Axis Force Sensor Based on RF-GA

作　　者：徐家琪 龙建勇 孙炜[1,2,3] 王耀南 梁桥康[1,2,3] XU Jia-qi;LONG Jian-yong;SUN Wei;WANG Yao-nan;LIANG Qiao-kang(College of Electrical and Information Engineering,Hunan University,Changsha 410082,China;National Engineering Laboratory for Robot Vision Perception and Control Technologies,Changsha 410082,China;Hunan Key Laboratory of Intelligent Robot Technology in Electronic Manufacturing,Changsha 410082,China)

机构地区：[1]湖南大学电气与信息工程学院,湖南长沙410082 [2]机器人视觉感知与控制技术国家工程实验室,湖南长沙410082 [3]电子制造业智能机器人湖南省重点实验室,湖南长沙410082

出　　处：《测控技术》2020年第5期28-35,68,共9页Measurement & Control Technology

基　　金：国家自然科学基金项目(61673163);湖南省科技计划项目(2017XK2102);湖南省重点实验室开放基金(IRT2018003)。

摘　　要：多维力传感器的维间耦合问题严重影响了检测精度的提高。通过设计新型RF-GA(基于遗传算法的改进随机森林算法)解耦方法解决多维力信息的解耦问题,实现提高力传感器检测精度的目标。针对随机森林算法中含有大量子树,但每个子树的预测准度无法保证的问题,利用遗传算法对随机森林的子树进行筛选,保留优质子树,从而提高预测精度。以基于应变检测的六维力传感器为实验对象,将RF-GA算法运用到实际力信息解耦中,并通过解耦实验对RF-GA算法进行验证。与现有解耦算法相比,RF-GA解耦方法具有精度高、解耦时间短的优点,实验结果表明该算法能有效提高多维力传感器的解耦精度。The inter-dimension coupling of multi-axis force sensor seriously affects the improvement of detection precision. A novel random forest algorithm based on genetic algorithm( RF-GA) is proposed to decouple the multi-axis force sensor and improve the measurement performance. The normal random forest contains a large number of subtrees,but the accuracy of each subtree cannot be guaranteed. Therefore,the genetic algorithm( GA) was used to select high-quality subtrees of the random forest to improve prediction accuracy. Taking the six-axis force sensor based on strain detection as the experimental object,the RF-GA was applied to the actual force information decoupling,and was verified by the decoupling experiment. Compared with other traditional decoupling algorithms,RF-GA based on decoupling method has the advantages of high precision and short decoupling time. Experimental results show that this method can improve the decoupling performance.

关 键 词：多维力传感器 静态解耦 随机森林 遗传算法 

分 类 号：TP212.12[自动化与计算机技术—检测技术与自动化装置]