A novel pressure sensor calibration system based on a neural network  

作　　者：彭晓钧 杨坤涛 元秀华 

机构地区：[1]School of Optical and Electronic Information,Huazhong University of Science and Technology [2]Wuhan Second Ship Design Research Institute

出　　处：《Journal of Semiconductors》2015年第9期121-124,共4页半导体学报（英文版）

基　　金：Project supported by the National Natural Science Foundation of China(No.61275081)

摘　　要：According to the specific input-output characteristics of a pressure sensor, a novel calibration algorithm is presented and a calibration system is developed to correct the nonlinear error caused by temperature. In contrast to the routine BP and RBF, curve fitting based on RBF is first used to get the slope and intercept, and then the voltage-pressure curve is described. Test results show that the algorithm features fast convergence speed, strong robustness and minimum SSE （sum of squares for error）. It is proven by practical applications that this calibration system works well and the measurement precision is better than the design demands. Furthermore, this calibration system has a good real-time capability.According to the specific input-output characteristics of a pressure sensor, a novel calibration algorithm is presented and a calibration system is developed to correct the nonlinear error caused by temperature. In contrast to the routine BP and RBF, curve fitting based on RBF is first used to get the slope and intercept, and then the voltage-pressure curve is described. Test results show that the algorithm features fast convergence speed, strong robustness and minimum SSE （sum of squares for error）. It is proven by practical applications that this calibration system works well and the measurement precision is better than the design demands. Furthermore, this calibration system has a good real-time capability.

关 键 词：nonlinear error correction comprehensive compensation curve fitting neural network high precision 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置] TP18[自动化与计算机技术—控制科学与工程]