摘要
介绍了硅压阻式压力传感器温度误差产生的原因及其特点,在比较了多种神经网络优缺点的基础上,提出了一种利用小波神经网络对压力传感器温度误差及非线性误差进行补偿的方法。该网络与BP神经网络相比,具有更快的收敛速度和更好的补偿精度。经过实验证明该网络能够有效地补偿压力传感器的温度非线性误差,在-40~60℃范围内,使温度误差从原来的5.4%降到了0.2%。
The characteristics of temperature error and non-linearity of silicon piezoresistive pressure sensor are introduced.After comparing characteristics of several neural network,a method for compensating temperature error and non-linearity of silicon piezoresistive pressure sensor is designed using wavelet neural network which has faster speed quality convergence and higher precision than BP meural network.The experimental results show that temperature error and non-linearity of silicon piezoresistive pressure sensor can be reduced markedly.In the range of-40~60℃,temperature error can be reduced from 5.4% to 0.2%.
出处
《传感器技术》
CSCD
北大核心
2005年第7期13-15,共3页
Journal of Transducer Technology
关键词
温度补偿
硅压阻式压力传感器
小波神经网络
temperature error compensation
silicon piezoresistive pressure sensor
wavelet neural network