首页> 外文期刊>Journal of Residuals Science & Technology >Temperature Compensation Methodology based on Artificial Neural Network in a MEMS Electro- Thermal Excitation Resonant Pressure Sensor
【24h】

Temperature Compensation Methodology based on Artificial Neural Network in a MEMS Electro- Thermal Excitation Resonant Pressure Sensor

机译:基于人工神经网络的MEMS电热激励谐振压力传感器温度补偿方法

获取原文
           

摘要

For an electro-thermal excitation MEMS resonant pressure sensor, temperature compensation method based on artificial neural network (ANN) is proposed to eliminate the additional temperature drift of the resonant frequency caused by electro-thermal excitation and change of ambient temperature. Two ANN compensation model are established after the effects of learning rate, number of hidden neurons, and goal error on training of ANN are analyzed. After trained by experimental data obtained by calibration experiment on the sensor sample, the compensation results of proposed ANN compensation model are compared to the results of dual beams compensation technique, and comparison results show proposed ANN compensation model can effectively eliminate the influence of additional temperature and accurately give the value of measured pressure.
机译:对于电热激励MEMS谐振压力传感器,提出了一种基于人工神经网络的温度补偿方法,以消除电热激励和环境温度变化引起的谐振频率的附加温度漂移。在分析了学习率,隐神经元数量和目标误差对神经网络训练的影响后,建立了两种神经网络补偿模型。经过校准实验获得的实验数据对传感器样本进行训练,将所提出的人工神经网络补偿模型的补偿结果与双光束补偿技术的结果进行比较,比较结果表明所提出的人工神经网络补偿模型可以有效消除附加温度和温度的影响。准确给出测得的压力值。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号