小波包分析在乏燃料剪切机故障诊断中的应用  

Application of Wavelet Packet Analysis in Fault Diagnosis of Spent Nuclear Fuel Shears

作　　者：张小志[1] 赵立宏[1] 邓骞[2] 宋超[3] 

机构地区：[1]南华大学电气工程学院,湖南衡阳421001 [2]南华大学机械工程学院,湖南衡阳421001 [3]衡阳技师学院机械工程系,湖南衡阳421001

出　　处：《南华大学学报（自然科学版）》2014年第1期69-73,共5页Journal of University of South China：Science and Technology

基　　金：国防基础科研计划基金资助项目(B3720110001)

摘　　要：针对乏燃料剪切机剪切声音信号特征提取的难题,利用小波包分析方法,对不同磨损状况刀具的剪切声音信号进行小波包变换,提取变换信号的各频段归一化能量特征向量,根据声音信号的能量特征向量可辨识不同状况的乏燃料剪切机剪切声音,从而实现乏燃料剪切机故障诊断.实验表明,该特征向量能有效识别刀具的正常磨损、一级磨损、二级磨损三种状况,有效解决了基于隐马尔可夫模型的故障模式识别中特征提取的问题.Aiming at the voice signal feature extraction problem of spent nuclear fuel shears,the wavelet packet analysis method was proposed. The wavelet packet transform was used to the cutting sound signal of the different status tool,extracting the normalized energy eigenvector of each frequency band signal,the energy eigenvector can distinguish different status cutting sound signal,and then diagnose the fault of spent nuclear fuel shears. Experi-mental results show that it can effectively distinguish three conditions of the shears：the lev-el of normal,the first or the second wear and tear,which effectively solved the feature ex-traction problem based on the Hidden Markov Model in shearing machine fault pattern rec-ognition.

关 键 词：小波包分析 特征提取 故障诊断 乏燃料剪切机 

分 类 号：TL248[核科学技术—核燃料循环与材料]