基于信息熵与信息融合的供输弹系统故障诊断研究

针对供输弹系统早期故障微弱特征难以提取等问题,提出了信息熵与信息融合的故障诊断方法。将经过降噪预处理后的信号提取样本熵作为特征参量,经Elman神经网络初步诊断,将其输出值归一化后作为证据体的基本概率分配,采用一种基于证据关联系数加权平均融合模型,最终得到决策级融合的诊断结果。结果表明:该方法能有效对供输弹系统故障进行诊断,诊断正确率高达93.71%。

Research on Fault Diagnosis of Ammunition Supply System Based on Information Entropy and Information Fusion

Aiming at the problem that it is difficult to extract the weak features of the early fault of the ammunition feeding and transporting system,a fault diagnosis method based on information entropy and information fusion is proposed in this paper.Sample entropy of signal extracted after denoising pretreatment is used as feature parameter,and Elman neural network is used to diagnose it.The output value is normalized and used as the basic probability distribution of evidence body.A weighted average fusion model based on correlation coefficient of evidence is used to obtain the final diagnosis result of decision-level fusion.The results show that the method can effectively diagnose the fault of the ammunition feeding system,and the diagnostic accuracy is as high as 93.71%.