BP网络是应用最广的一种人工神经网络,将BP神经网络应用到压力检测领域的温度等非线性补偿,具有重要的实用价值,对压力检测精度的改进效果显著;从传感器信息融合的角度看,神经网络就是一个融合系统;通过对神经网络基本理论的阐述,针对研究对象将BP神经网络原理与多传感器信息融合技术有机集合起来,提出了基于BP神经网络的二传感器信息融合模型及改进算法,建立了BP神经网络训练标准样本库,并对该网络模型进行主要技术指标的测试和仿真工作,测试结果表明构建的模型及其改进算法能很好地满足了高精度压力检测仪的指标要求.
BP network is a kind of the most widely used artificial neural network, it is applied to temperature nonlinear compensation of pressure detecting, has important practical value, and significantly on the improvement of detection accuracy. From the point of view of the sensor information fusion, neural network is a fusion system. Through the exposition of the basic theory of neural network, and based on the principle of BP neural network and multi sensor information fusion technology, the model and the improved algorithm of two sensor informa- tion fusion based on BP neural network have been proposed, and training sample database of BP neural network has been established. The main technical parameters of the network model have been tested and simulated, and the results show that the constructed model and its im- proved algorithm can well meet the requirement of high accuracy pressure detector index.