基于BP网络的压力传感器信息融合

压力传感器输出特性容易受环境温度、电压扰动等各种非目标参量的影响，从而大大降低了其性能。BP算法是一种最速下降的静态寻优算法，而对其改进的算法LMBP算法克服了标准BP算法的固有缺点，不但学习速度快，而且精度高。利用LMBP算法对压力传感器的输出进行融合，有效地消除了非目标参量特别是温度对压力传感器输出的影响，最后利用MATLAB软件对样本数据进行训练和仿真，通过对融合结果分析可知：BP网络的LMBP算法不仅提高了压力传感器的精度，而且提高了压力传感器的稳定性和可靠性。

Information Fusion of Pressure Sensor Based on BP Network

The output of pressure sensor is easily affected by no n|objection parameters, such as environment temperatures, voltage fluctuation a nd so on, in the applications. BP algorithm is the steepest descent algorithm an d an algorithm to improve its performance, LMBP algorithm overcomes the disadvan tage of the standard BP algorithm and it has not only fast learning velocity, bu t also high accuracy. Using LMBP algorithm to fuse the output data of pressure s ensor, it eliminates the affection of the non|objection parameters, especially, such as temperatures, to the pressure sensor. Then the MATLAB software is used to train and simulate the example data. Finally, the analyzed fusion results sho w that not only the accuracy of the pressure sensor is improved, but also the st ability and liability of the pressure sensors are improved.