压力容器2016，Vol.33Issue(3)：51-55,5.DOI:10.3969/j.issn.1001-4837.2016.03.008
基于 BP 神经网络的焊接冷裂纹声发射信号特征识别
Recognition for Acoustic Emission Signal Characteristics of Welding Cold Crack Based on BP Neural Network
摘要
Abstract
Acoustic emission technique is capable to monitor cold cracks.But in the long-time cooling process after welding,there exist a host of interference signals which make it harder to analysis and evalu-ate the signals.Thus,a BP neural network which can recognize welding cold crack signals was estab-lished.Its input unit was constituted by 5 typical parameters of the acoustic emission signals,as well as output unit was constituted by characteristics of crack signals and interference signals.Through training and testing the data from the experiment of SPV490Q steel plate with rigid restraint,the feasibility of the neural network was confirmed.关键词
焊接冷裂纹/声发射技术/SPV490Q/BP神经网络Key words
welding cold crack/acoustic emission technique/SPV490Q/BP neural network分类
机械制造引用本文复制引用
张颖,孔德慧,张盛蠫,周俊鹏..基于 BP 神经网络的焊接冷裂纹声发射信号特征识别[J].压力容器,2016,33(3):51-55,5.基金项目
黑龙江省博士后科研启动项目 （）
