基于BP神经网络的压力传感器温度补偿方法研究

Research on Temperature Compensation Method of Pressure Sensor Based on BP Neural Network

硅压阻式压力传感器在工作时受温度的影响较大,随着温度的升高或降低,传感器的实际测量值会出现一定的误差,出现温度漂移的现象,为了抑制温度漂移对传感器的影响,采用人工神经网络中的BP神经网络的方法对温度漂移现象进行补偿,通过对补偿前后数据的对比,使传感器的灵敏度温度系数和满量程误差分别提升了两个数量级,得到了较为理想的效果,提升了传感器的性能和可靠性。

Silicon piezoresistive pressure sensors are greatly affected by temperature during operation.As the temperature increases or decreases,the actual measurement of the sensor will have a certain error and the phenomenon of temperature drift.In order to suppress the influence of temperature drift on the sensor,the BP neural network in artificial neural network is used to compensate the temperature drift.By comparing the data before and after compensation,The sensor’s sensitivity temperature coefficient and full-scale error have been increased by two orders of magnitude respectively.The ideal result is obtained,which improves the performance and reliability of the sensor.