Adaboost集成BP神经网络在传感器阵列检测系统中的应用

针对目前常见的多元有害气体检测问题，设计并搭建了一种基于传感器阵列和集成 BP神经网络相结合的传感器阵列检测系统。在该系统中采用集成BP神经网络对传感器阵列的三种混合有害气体的响应信号进行回归分析。为了提高集成BP神经网络的预测准确性，又利用Adaboost算法对集成BP神经网络进行了优化。结果显示：该系统能够准确地检测气体组分，通过Adaboost算法对集成BP神经网络优化后，预测的平均相对误差小于2%，能够有效解决气体传感器的交叉敏感问题，提高传感器的选择性。

Application of Adaboost integrated BP neural network in detecting system of sensor array

Aiming at problem of harmful gas mixture detection,a kind of gas detecting system is developed by combining sensor array with integrated BP neural network. The purpose of this test system is regression analysis on response signal of three harmful gas mixture measured by sensor array using BP neural network algorithm. In order to improve the prediction accuracy of the BP neural network,adopt the Adaboost algorithm to optimize integrated neural network. The results show that the system can accurately detect gas component,after integrated neural network is optimized by Adaboost algorithm,predicted average relative error is less than 2%,it can significantly solve problem of cross sensitivity and improve selectivity of sensor.