Information Engineering |
|
|
|
|
Application of DTCWPT and NCA-LSSVM to inspect internal defects of magnetic tile |
XIE Luo feng, XU Hui ning, HUANG Qin yuan, ZHAO Yue, YIN Guo fu |
School of Manufacturing Science and Technology, Sichuan University, Chengdu 610065, China |
|
|
Abstract A novel method was proposed to detect magnetic tile internal defects based on dual-tree complex wavelet packet transform (DTCWPT), neighborhood component analysis (NCA), least squares support vector machines (LSSVM). The impact sound was decomposed up to 6 levels, resulting in 64 sub-signals. Then four statistical features: energy, skewness, kurtosis and fuzzy entropy were calculated to construct feature set. The dimension of feature set was reduced and optimized by NCA. The new feature set was input to LSSVM to judge whether the magnetic tile is with internal defects. The reliability of the proposed method was verified by the experimental results. The classification results showed that the accuracy rates of three kinds of magnetic tiles could reach 99%, higher than the bispectrum method. The experimental results demonstrate that the proposed method is fast, adaptable, efficient and reliable, providing a technical support to detect the internal defects of magnetic tile.
|
Published: 01 January 2017
|
|
|
Cite this article:
XIE Luo feng, XU Hui ning, HUANG Qin yuan, ZHAO Yue, YIN Guo fu. Application of DTCWPT and NCA-LSSVM to inspect internal defects of magnetic tile. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(1): 184-191.
|
应用双树复小波包和NCA-LSSVM检测磁瓦内部缺陷
提出结合双树复小波包变换(DTCWPT)、邻域成分分析法(NCA)、最小二乘支持向量机(LSSVM)的磁瓦内部缺陷检测方法.通过双树复小波包将采集的声音信号分解为6层,得到64个不同频带的子信号;求取特定频带信号的能量、偏度、峭度、模糊熵,并将能量、偏度、峭度、模糊熵作为分类特征|利用邻域成分分析法对分类特征降维|将降维构造的新特征集输入到最小二乘支持向量机,判断磁瓦是否含有内部缺陷.通过实验验证,对提出的检测方法进行可行性分析.3种不同类型磁瓦的内部缺陷识别率均可以达到99%,与以往双谱切片方法相比,提高了检测识别率.试验结果表明,提出的方法具有检测速度快、可靠性高、适应性强等特点,为高效、准确地进行磁瓦内部缺陷检测提供了有效的技术手段.
|
|
[1] LI X, JIANG H, YIN G. Detection of surface crack defects on ferrite magnetic tile [J]. NDT&E International, 2014, 62(2): 6-13.
[2] WAGNER R, GONCALVES O, DEMMA A, et al. Guided wave testing performance studies: comparison with ultrasonic and magnetic flux leakage pigs [J]. Insight, 2013, 55(4): 187-196.
[3] MOHAMMAD R, AFZALNIA MR, HAMED F. Heat residual stress measurement of welded areas in steel pipes via magnetic particle testing [J]. Materials Evaluation, 2012, 70(6): 624-630.
[4] SHKATOV P. Combining eddycurrent and magnetic methods for the defectoscopy of ferromagnetic materials [J]. Nondestructive Testing and Evaluation, 2013,28: 155-165.
[5] BAKNOV A S, KUROZAEV V P, KUDRYAVTSEV D A, et al. Increasing the reliability of magneticparticle testing by means of a YMJIK10 automated unit for magnetic fluorescentpenetrant inspection of pipe end faces [J]. Russian Journal of Nondestructive Testing, 2014, 40(5): 311-316.
[6] 黄沁元,殷鹰,赵越,等.基于双谱分析的磁瓦内部缺陷音频检测方法[J].四川大学学报:工程科学版,2014,46(5): 188-194.
HUANG Qinyuan, YIN Ying, ZHAO Yue, et al.Acoustic inspection of internal defect in magnetic tile based on bispectrum analysis [J]. Journal of SichuanUniversity: Engineering Science, 2014, 46(5):188-194.
[7] BAYRAM I, SELESNICK I W. On the dualTree complex wavelet packet and MBand transforms [J]. IEEE Transactions on Signal Processing, 2008, 56(6):22982310.
[8] LO E H S, PICKERING M R, FRATER M R, et al. Image segmentation from scale and rotation invariant texture features from the double dyadic dual-tree complex wavelet transform [J]. Image and Vision Computing, 2011, 9(1): 15-28.
[9] 李辉,郑海起,唐力伟.基于双树复小波包峭度图的轴承故障诊断研究[J].振动与冲击,2012, 31(10): 13-18.
LI Hui, ZHANG Haiqi, TANG Liwei. Bearing fault diagnosis based on kurtogram of dualtree complex wavelet packet transform [J]. Journal of Vibration and Shock, 2012, 31(10): 13-18.
[10] 王娜,郑德忠,刘永红.双树复小波包变换语音增强新算法[J].传感技术学报,2009,22(7):983-987.
WANG Na, ZHENG Dezhong, LIU Yonghong. New method for speech enhancement based on dual tree complex wavelet packet transform [J]. Journal of Sensors and Actuators, 2009, 22(7): 983-987.
[11] ZHOU H, CHEN J, DONG G, et al. Bearing fault recognition method based on neighbourhood component analysis and coupled hidden Markov model [J].Mechanical Systems and Signal Processing, 2016, 6667: 568-581.
[12] XU Q, WONG PK. Hysteresis modeling and compensation of a piezostage using least squares support vector machines [J]. Mechatronics, 2011, 21(7): 12391251.
[13] 杨先勇,周晓军,张文斌,等.基于局域波法和KPCALSSVM的滚动轴承故障诊断[J].浙江大学学报:工学版,2010,44(8): 1519-1524.
YANG Xianyong, ZHOU Xiaojun, ZHANG Wen bin, et al. Rolling bearing fault diagnosis based on local wave method and KPCALSSVM [J]. Journal of Zhejiang University: Engineering Science, 2010, 44(8): 1519-1524.
[14] SELESNICK I W, BARANIUK R G, KINGSBURY N G. The dualtree complex wavelet transform [J]. IEEE Digital Signal Processing Magazine, 2005, 22(6): 123-151.
[15] 胥永刚,孟志鹏,陆明.基于双树复小波包变换的滚动轴承故障诊断[J].农业工程学报,2013, 29(10): 49-56.
XU Yonggang, MENG Zhipeng, LU Ming. Fault diagnosis of rolling bearing based on dualtree complex wavelet packet transform [J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(10): 49-56.
[16] 胥永刚,孟志鹏,赵国亮,等.双树复小波包和谱峭度在齿轮故障诊断中的应用[J].北京工业大学学报,2014, 40(4): 488-494.
XU Yonggang, MENG Zhipeng, ZHAO Guoliang, et al. Application of gear fault diagnosis based on dualtree complex wavelet packet transform and spectral kurtosis [J]. Journal of Beijing University of Technology, 2014, 40(4): 488-494.
[17] 郑近德,程军圣,杨宇.基于改进的ITD和模糊熵的滚动轴承故障诊断方法[J].中国机械工程,2012,23(19): 2372-2377.
ZHENG Jinde, CHENG Junsheng, YANG Yu. A rolling bearing fault diagnosis method based on improved ITD and fuzzy entropy [J]. Chinese Mechanical Engineering, 2012,23(19): 2372-2377.
[18] XAVIERDESOUZA S, SUYKENS J A, VANDEWALLE J, et al. Coupled simulated annealing [J]. IEEE Transactions on Systems, Man and Cybernetics: Part B, 2010, 40(2): 320-335.
[19] FAWCETT T. An introduction to ROC analysis [J]. Pattern Recognition Letters, 2006, 27(8): 861-874. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|