Empirical Mode Decomposition and Rough Set Attribute Reduction for Ultrasonic Flaw Signal Classification

Empirical Mode Decomposition and Rough Set Attribute Reduction for Ultrasonic Flaw Signal Classification
复制标题

超声缺陷信号分类的经验模态分解和粗糙集属性约简

DOI:
10.1080/18756891.2014.889877
复制
发表时间:
2014-05
影响因子:
2.9
通讯作者:
Qintian Yang
Qintian Yang
中科院分区:
计算机科学4区
文献类型:
--
作者:
Peng Yang;Qintian Yang

文献摘要

参考文献

相似文献

摘要特征提取与选择是超声缺陷信号分类的重要技术。本研究采用经验模态分解(EMD)方法获得原始信号的固有模态函数(IMFs),并提取其对应的基于传统时频域的统计参数作为初始特征。然后利用谱聚类方法对特征值进行离散化,利用粗糙集属性约简(RSAR)实现特征选择。将最终的特征作为人工神经网络(ann)的输入,训练决策分类器进行缺陷识别。实验结果表明,与传统的基于小波变换和主成分分析的方法相比,EMD与RSAR相结合可以提高特征提取和选择的性能。采用该方案的人工神经网络能够有效地对不同的超声缺陷信号进行分类,具有较高的分类精度和较低的训练耗时。
AbstractFeature extraction and selection are the most important techniques for ultrasonic flaw signal classification. In this study, empirical mode decomposition (EMD) is used to obtain the intrinsic mode functions (IMFs) of original signal, and their corresponding traditional time and frequency domain based statistical parameters are extracted as the initial features. After that, spectral clustering method is used for feature value discretization so that rough set attribute reduction (RSAR) can be applied to implement feature selection. The final features are taken as input of artificial neural networks (ANNs) to train the decision classifier for flaw identification. Experimental results show that compared to conventional wavelet transform based schemes and principal components analysis, EMD combined with RSAR can improve the performance of feature extraction and selection. ANN by using such scheme can effectively classify different ultrasonic flaw signals with high accuracy and low training elapsed time.
DOI: 10.1109/iccit.2010.5711085
发表时间: 2010-11
期刊: 5th International Conference on Computer Sciences and Convergence Information Technology
影响因子: --
作者:
Kyungmi Lee
通讯作者: Kyungmi Lee
DOI: 10.21307/ijssis-2017-575
发表时间: 2013-01
影响因子: 1.2
作者:
Ye Hongxian;L. Wenchang;Huang Xiaoping
通讯作者: Ye Hongxian;L. Wenchang;Huang Xiaoping
DOI: 10.1109/imtc.1999.776987
发表时间: 1999-05
期刊: IMTC/99. Proceedings of the 16th IEEE Instrumentation and Measurement Technology Conference (Cat. No.99CH36309)
影响因子: --
作者:
S. Legendre;D. Massicotte;J. Goyette;T. Bose
通讯作者: S. Legendre;D. Massicotte;J. Goyette;T. Bose
DOI: 10.1080/713821795
发表时间: 1985-07
影响因子: 1.3
作者:
D. O. Thompson;D. Chimenti
通讯作者: D. O. Thompson;D. Chimenti
DOI: 10.21307/ijssis-2017-535
发表时间: 2013-01
影响因子: 1.2
作者:
Chihang Zhao;Zhong Xin;Dang Qian;Zhao Li-ye
通讯作者: Chihang Zhao;Zhong Xin;Dang Qian;Zhao Li-ye