基于峰值误差约束的传感器线性化方法研究  

Sensor linearization study based on peak error restriction

作　　者：胡学海[1,2] 王厚军[1] 古天祥[1] 

机构地区：[1]电子科技大学自动化学院 [2]成都飞机设计研究所计量研究室成都610041

出　　处：《仪器仪表学报》2007年第2期342-346,共5页Chinese Journal of Scientific Instrument

摘　　要：基于加权最小二乘算法和模糊数学的基本性质,本文提出一种新算法用于智能传感器的非线性补偿。算法既考虑了峰值误差也考虑了积分测度误差,可在峰值误差和积分测度误差间进行折衷,分析及实验结果表明在付出较小积分测度误差的代价上,可大幅减小峰值误差,从而在总体上提高传感器线性化后的性能。This paper develops a new method for the nonlinear compensation of intelligent sensor based on reweighed least square and fuzzy mathematics. Considered about peak error and integral measure error, the method can compromise between both of them. Theoretical analysis and test result show that the method can reduce a great deal of peak error on the cost of a little integral measure error degradation. So it can enhance sensor＇ s performance after linearization in general.

关 键 词：峰值误差 积分测度误差 模糊加权最小二乘法 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置] TP212.6[自动化与计算机技术—控制科学与工程]