基于神经网络的气体目标识别方法

研究神经网络在战场气体特征目标识别应用中的有效算法.通过建立战场目标气体特性探测与分析系统,针对战场上不确定背景条件下气体目标的自动识别问题,在总结目标特性规律,分析BP算法的基础上,采用BP算法对分类器进行训练,改善系统对信号的探测能力.典型战场目标信号样本检验表明:利用基于神经网络的分类器来实现对战场气体目标的识别分类是可行的.

Passive Sensing with Gaseous Objects on the Battlefield Using Neural Network

According to the characteristics of gas signals, the effectiveness of battlefield targets classification and identification used by neural network is explored. A system of gas test and analysis for typical battlefield targets is set up. BP algorithm is adopted to deal with the on base of the characteristic regulation of targets and the analysis of BP algorithm target recognition under undefined background in battlefield. The ability of detecting signal will be improved effectively. It is demonstrated that the modified BP algorithm has higher correct identification rates for gas signals of battlefield targets according to signal sample experiments of typical targets, and the neural network classifier is suitable for the classification of battlefield targets.