摘要
压力传感器的输出不仅随压力变化,而且易受环境温度的影响,因而限制了传感器的测量精度。为了克服压力传感器的上述缺陷,本文提出了一种基于最小二乘支持向量机的温度补偿方法,并用虚拟仪器技术予以实现。与常用的误差反传神经网络方法相比,最小二乘支持向量机可获得更好的泛化性能,不易发生局部最优及过拟合现象。因此该方法能有效地消除温度对传感器输出的影响。实例表明,补偿后的压力传感器具有更高的测量精度和温度稳定性。
The output of pressure sensor not only varies with the pressure in its input but also is easily affected by the environmental temperature, which will limit the measurement accuracy of the sensor. In order to overcome above shortcoming, in this investigation a temperature compensation method based on least squares support vector machine is presented and has been realized using virtual instrument technique. Compared with back-propagation neural network, least squares support vector machine can achieve higher generalization performance. Also, local minima and over fitting are unlikely to occur. So, the proposed method can eliminate the affection of the environmental temperature to the sensor more effectively. The application example indicates that the measurement accuracy and temperature stability of the compensated pressure sensor are both improved.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2007年第12期2235-2238,共4页
Chinese Journal of Scientific Instrument
基金
浙江省自然科学基金(Y106786
Y105281)资助项目
关键词
最小二乘支持向量机
压力传感器
温度补偿
虚拟仪器
least squares support vector machine
pressure sensor
temperature compensation
virtual instrument
