基于LS-SVR的压力传感器温度自补偿策略  

Temperature Self-Compensation Strategy for Pressure Sensor Based on LS-SVR

作　　者：胡启阳[1] 龙军[1] 陈君[1] 

机构地区：[1]北京控制工程研究所,北京100190

出　　处：《传感技术学报》2017年第7期1057-1061,共5页Chinese Journal of Sensors and Actuators

基　　金：十二五民用航天项目(E020415)

摘　　要：硅压阻式压力传感器在实际使用过程中受环境温度影响易发生温度漂移,同时传感器本身又存在一定的非线性,这使得传感器测量精度大幅度降低。针对传统的温度补偿方法中需引入温度传感器的情况,提出一种基于最小二乘支持向量回归(LS-SVR)的压力传感器温度自补偿策略,通过定义并测量传感器桥路自身参数获取温度信息实现温度补偿,而无需配置额外的温度传感器。通过粒子群算法和交叉验证对LS-SVR的参数进行了优化。实验结果表明:这种利用传感器自身桥路进行温度补偿的方法能够有效地消除压力传感器的温度漂移。补偿后测量精度达到0.1%FS。Temperature drift exists in Silicon piezo-resistive pressure sensor as the result of its susceptibility to tem- perature, which decreases the measurement precision of the sensor. Aiming at the problem that a temperature sensor is needed in traditional temperature compensation method, a temperature self-compensation strategy for pressure sen- sor based on LS-SVR is proposed,which acquires temperature information by definition and measurement of parame- ters in the measurement bridge of sensor. PSO algorithm and Cross Validate are applied to optimize the parameters of LS-SVR. The experimental results show that this method can eliminate the temperature drift effectively without an additional temperature sensor. The measurement accuracy can be improved to 0.1%FS.

关 键 词：压力传感器 温度补偿 最小二乘支持向量回归 粒子群优化 K-折交叉验证 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]