神经网络用于电热响应曲线的分析  

Analysis of Electric Thermal Response Curve Using Neural Network Technique

作　　者：周彬[1] 秦志春[1] 田桂蓉[1] 徐振相[1] 

机构地区：[1]南京理工大学化工学院,江苏南京210094

出　　处：《爆破器材》2008年第1期25-28,共4页Explosive Materials

摘　　要：瞬态脉冲试验是一种对桥丝式电火工品进行无损检测的方法。通过瞬态脉冲试验得到火工品的电热响应曲线,正常的电热响应曲线是光滑的,而非正常的电热响应曲线往往有较大的波动,出现非正常电热响应曲线的火工品一般都存在某种疵病。该文将神经网络技术用于对电热响应曲线的分析,以区分正常的电热响应曲线和非正常的电热响应曲线。研究结果表明,该方法可以比较准确地区分这两种电热响应曲线,实现自动判断。Transient pulse test is one kind of nondestructive test method employed to test bridge wire electric explosive device （EED）. The normal electric thermal response curve obtained from transient pulse test is smooth, but the abnormal one has obvious fluctuation. In general, the EED having abnormal curve has some shortcomings. In this paper , the neural network technique is used to analyze the response curve to distinguish the abnormal from the normal ones. The result shows the method is rather effective.

关 键 词：瞬态脉冲试验 无损检测 火工品 电热响应 神经网络 

分 类 号：TQ560.72[化学工程—炸药化工]