基于BP神经网络的压力传感器数据融合研究

摘要

压力传感器由于输出电压值易受环境温度、电压扰动等非目标参量的影响而导致精度大大降低.该文采用BP神经网络对压力和温度2个目标参量进行数据融合处理,减小了两者相互交叉干扰敏感度.结果表明,采用BP神经网络进行数据融合,能够提高传感器的稳定性及其精度,仿真验证了该方法的有效性和可行性.%The output of pressure sensor is easily affected by non-objection parameters, such as environment temperatures, voltage fluctuation and so on, which results to the reducement of the accuracy. By using BP neural network, two target parameters, pressure and temperature, are made to do the data combination to reduce the sensitivity of cross-interference. The simulation result shows that the fusion of BP neural network improves the accuracy and stability of sensor, and verifies the validity and feasibility of this method.