搅拌摩擦焊焊缝缺陷的超声波检测及其信号识别
|
摘要
搅拌摩擦焊是一种新兴固相连接技术,其缺陷的无损检测技术也处于初始阶段。超声检测以其对缺陷良好的定位及定量能力成为搅拌摩擦焊焊缝缺陷检测的重要手段,而它在定性上的局限性使得对缺陷的定性问题成为研究的难点之一。
本文以铝合金搅拌摩擦焊焊缝的包铝层伸入、隧道孔、未焊透缺陷超声检测射频信号为对象,分析各类缺陷信号的时域和频域波形特征;利用小波变换理论对缺陷信号的进行特征量的提取,并对各特征量的类别可分性进行评价;以提取的特征量为网络输入,建立用于识别搅拌摩擦焊焊缝缺陷类型的人工神经网络。
结果表明,搅拌摩擦焊焊缝缺陷的超声波波形在时域和频域都有其自身特征,可用于超声检测时对缺陷的初步定性。隧道孔超声检测信号的时域静态波形在波宽范围内会有连续起伏的多个波峰,而另外两种缺陷信号在波宽范围内仅有一个明显的主峰;对于前后扫查动态波形,包铝层伸入与未焊透有近似的特征,即随着探头从焊缝边缘向远离焊缝的方向移动,缺陷波幅由低点上升到峰值,在峰值附近维持一段时间后又下降到最低点,而隧道孔缺陷的波形特征则是波幅先下降到最低点,随后又逐渐上升起来,利用隧道孔的时域静态及动态波形特征能够很好地将该缺陷识别出来;在频域上,缺陷信号的功率谱密度的平均主频率由高至低依次为包铝层伸入、未焊透、隧道孔缺陷,此外,隧道孔的功率谱密度图与另外两种缺陷的不同在于其主频率附近的频率点上会存在多个波峰。
应用小波变换理论可以很好地实现对缺陷检测信号的特征提取。本文分别采用了基于小波包分解重构信号的能量、小波包(4,1)和(4,3)节点系数、缺陷信号功率谱的小波分解这三种方法,对缺陷信号进行了特征量提取,并利用欧氏空间距离的类别可分性判据对以上三种方法进行了缺陷分类性的评估。结果表明,基于缺陷信号功率谱小波分解的特征提取方法具有最好的类别可分性。
以小波变换理论提取的缺陷信号特征量作为网络输入,人工神经网络可以很好地实现对搅拌摩擦焊焊缝缺陷的分类识别。本文建立并训练了以上述三种特征量为输入的BP网络,网络识别结果表明以基于缺陷信号功率谱的小波分解特征量作为网络输入的BP网络对缺陷的正确识别率最高,达到了85.71%,其中对隧道孔和未焊透的识别率达到100%,而包铝层伸入的识别率仅为33.33%。
Friction stir welding(FSW) is an emerging solid-phase welding technology,and the Nondestructive testing(NDT) technology of the defects of the FSW joints is also at its initial stage.Ultrasonic testing has become an important means to inspect defects in the FSW joints due to its profound quantitative and location capability.Since there is limit on qualitative capability for ultrasonic testing,this issue has become one of the research challenge of ultrasonic testing.
Taking the ultrasonic echo radio frequency(RF) signals of the aluminum clad penetration defect,channel defect and lack of penetration(LOP) in the FSW joints as research object in this paper,the time-domain and frequency-domain features of the defects echo signals in ultrasonic inspection were analysed.And then wavelet transformation was used to perform feature extraction and the defects classification performance was evaluated.At last,a artificial neural network(ANN) whose network inputs were the extracted feature vectors was created to recognize the defects type.
The research result showed that the time-domain and frequency-domain waveform of the defects echo signals present obvious characteristics,which can be used for qualitative analysis of the defects.For the echo static waveform of the channel defect signal in ultrasonic testing,there are several consecutive wave peaks fluctuation within the wave width range.But for the other two kinds of the defects,there is only a obvious main wave peak within the wave width range. For the dynamic echo waveform of the defect by travering scan that is perpendicular to the weld line,aluminum clad penetration defect and LOP defect have similar characteristic, that is,as transducer moves away from the weld line,the amplitude of the defect echo wave goes up to a peak and remains unchanged at the peak for a while,then drops down into the valley.But the situation of the channel defect is different,the amplitude drops down first into the valley and then goes up gradually.These charactersitcs can be used to recognize channel defect. The average values of the principal frequency of the defect echo signal rank from high to low as follows: aluminum clad penetration defect defect,LOP,channel defect. Additionally, the difference between the figures of the power spectral density(PSD) of channel defect and the others is that there are several obvious wave peaks around the principal frequency.
It's benefical to achieve the feature extraction of the defects signals with wavelet transform theory.Three feature extraction methods based on wavelet packet(WP) signal component node energy,WP node coefficients,wavelet decomposition of the PSD of the defects echo signal were used to extract the features of the three types of defects.To evaluate the classification performance of the feature extraction methods above by classification criteria based on Euclidean's distance,and the result showed that the feature extraction method based on wavelet decomposition of the PSD of the defects echo signal has the best classification performance.
It's effective to achieve the defects of FSW joints recognition by ANN with extracted feature input vectors.A back propagation(BP) neural network whose inputs vectors were the features above was created and trained in this paper.The result of networks recognition experiments showed that the network whose input vector is the feature base on wavelet decomposition of the PSD of the defects echo signal has the best classification capability.The BP network’s rate of the defects recognition is 85.71%,and rate of the LOP and channel defects recognition are both 100%,but the rate of the aluminum clad penetration defects recognition is just only 33.33%.
本文以铝合金搅拌摩擦焊焊缝的包铝层伸入、隧道孔、未焊透缺陷超声检测射频信号为对象,分析各类缺陷信号的时域和频域波形特征;利用小波变换理论对缺陷信号的进行特征量的提取,并对各特征量的类别可分性进行评价;以提取的特征量为网络输入,建立用于识别搅拌摩擦焊焊缝缺陷类型的人工神经网络。
结果表明,搅拌摩擦焊焊缝缺陷的超声波波形在时域和频域都有其自身特征,可用于超声检测时对缺陷的初步定性。隧道孔超声检测信号的时域静态波形在波宽范围内会有连续起伏的多个波峰,而另外两种缺陷信号在波宽范围内仅有一个明显的主峰;对于前后扫查动态波形,包铝层伸入与未焊透有近似的特征,即随着探头从焊缝边缘向远离焊缝的方向移动,缺陷波幅由低点上升到峰值,在峰值附近维持一段时间后又下降到最低点,而隧道孔缺陷的波形特征则是波幅先下降到最低点,随后又逐渐上升起来,利用隧道孔的时域静态及动态波形特征能够很好地将该缺陷识别出来;在频域上,缺陷信号的功率谱密度的平均主频率由高至低依次为包铝层伸入、未焊透、隧道孔缺陷,此外,隧道孔的功率谱密度图与另外两种缺陷的不同在于其主频率附近的频率点上会存在多个波峰。
应用小波变换理论可以很好地实现对缺陷检测信号的特征提取。本文分别采用了基于小波包分解重构信号的能量、小波包(4,1)和(4,3)节点系数、缺陷信号功率谱的小波分解这三种方法,对缺陷信号进行了特征量提取,并利用欧氏空间距离的类别可分性判据对以上三种方法进行了缺陷分类性的评估。结果表明,基于缺陷信号功率谱小波分解的特征提取方法具有最好的类别可分性。
以小波变换理论提取的缺陷信号特征量作为网络输入,人工神经网络可以很好地实现对搅拌摩擦焊焊缝缺陷的分类识别。本文建立并训练了以上述三种特征量为输入的BP网络,网络识别结果表明以基于缺陷信号功率谱的小波分解特征量作为网络输入的BP网络对缺陷的正确识别率最高,达到了85.71%,其中对隧道孔和未焊透的识别率达到100%,而包铝层伸入的识别率仅为33.33%。
Friction stir welding(FSW) is an emerging solid-phase welding technology,and the Nondestructive testing(NDT) technology of the defects of the FSW joints is also at its initial stage.Ultrasonic testing has become an important means to inspect defects in the FSW joints due to its profound quantitative and location capability.Since there is limit on qualitative capability for ultrasonic testing,this issue has become one of the research challenge of ultrasonic testing.
Taking the ultrasonic echo radio frequency(RF) signals of the aluminum clad penetration defect,channel defect and lack of penetration(LOP) in the FSW joints as research object in this paper,the time-domain and frequency-domain features of the defects echo signals in ultrasonic inspection were analysed.And then wavelet transformation was used to perform feature extraction and the defects classification performance was evaluated.At last,a artificial neural network(ANN) whose network inputs were the extracted feature vectors was created to recognize the defects type.
The research result showed that the time-domain and frequency-domain waveform of the defects echo signals present obvious characteristics,which can be used for qualitative analysis of the defects.For the echo static waveform of the channel defect signal in ultrasonic testing,there are several consecutive wave peaks fluctuation within the wave width range.But for the other two kinds of the defects,there is only a obvious main wave peak within the wave width range. For the dynamic echo waveform of the defect by travering scan that is perpendicular to the weld line,aluminum clad penetration defect and LOP defect have similar characteristic, that is,as transducer moves away from the weld line,the amplitude of the defect echo wave goes up to a peak and remains unchanged at the peak for a while,then drops down into the valley.But the situation of the channel defect is different,the amplitude drops down first into the valley and then goes up gradually.These charactersitcs can be used to recognize channel defect. The average values of the principal frequency of the defect echo signal rank from high to low as follows: aluminum clad penetration defect defect,LOP,channel defect. Additionally, the difference between the figures of the power spectral density(PSD) of channel defect and the others is that there are several obvious wave peaks around the principal frequency.
It's benefical to achieve the feature extraction of the defects signals with wavelet transform theory.Three feature extraction methods based on wavelet packet(WP) signal component node energy,WP node coefficients,wavelet decomposition of the PSD of the defects echo signal were used to extract the features of the three types of defects.To evaluate the classification performance of the feature extraction methods above by classification criteria based on Euclidean's distance,and the result showed that the feature extraction method based on wavelet decomposition of the PSD of the defects echo signal has the best classification performance.
It's effective to achieve the defects of FSW joints recognition by ANN with extracted feature input vectors.A back propagation(BP) neural network whose inputs vectors were the features above was created and trained in this paper.The result of networks recognition experiments showed that the network whose input vector is the feature base on wavelet decomposition of the PSD of the defects echo signal has the best classification capability.The BP network’s rate of the defects recognition is 85.71%,and rate of the LOP and channel defects recognition are both 100%,but the rate of the aluminum clad penetration defects recognition is just only 33.33%.
引文
[1] Kinchen David G,Aldahir Esma. NDE of Friction Stir Welds in Aerospace Applications [R].New Orleans:Lockheed Martin Michoud Space Systems, 2002:1～7.
[2]柯黎明,邢丽,刘鸽平.搅拌摩擦焊工艺及其应用[J].南昌航空工业学院学报,1999,13(3):1-4.
[3]王大勇,冯吉才,王攀峰.搅拌摩擦焊用搅拌头研究现状与发展趋势[J].焊接,2004,(6):6～10.
[4]刘松平,刘菲菲,李乐刚,等.铝合金搅拌摩擦焊缝的无损检测方法[J].航空制造技术,2006,(3):81～84.
[5] Bird C.Quality control of friction stir welds by the application of non-destructive testing[A].4th International Symposium on Friction Stir Welding,Part City,Utah,USA,2003.
[6]柯黎明.搅拌摩擦焊接头成形规律研究[D].北京:清华大学,2007.
[7] Ghidinif T,Vugrin T,Dalle Donne C.Residual stresses,defects and non-destructive evaluation of FSW joints [J]. Welding International, 2005, 19(10): 783～790.
[8]周万盛,姚君山.铝及铝合金的焊接[M].北京:机械工业出版社,2006.
[9]柯黎明.搅拌摩擦焊接头典型缺陷检测及表征技术[Z].航空科学基金项目申请书,2006.
[10]刘松平,刘菲菲,李乐刚,等.搅拌摩擦焊缝变入射角超声检测方法研究[J].无损检测,2006,28(5):225～228.
[11] AndréLamarre,Olivier Dupuis,Michael Moles.Complete.Inspection of Friction Stir Welds in Aluminum using Ultrasonic and Eddy Current Arrays[J].CINDE Journal,2006,27(4): 14-16,18～22.
[12] Colin R Bird.Ultrasonic phased array inspection technology for the evaluation of friction sitr welds[J].Insight,2004,46(1):31～36.
[13] Bird C R,Kleiner D.The phased array inspection of friction stir welded aluminium plant[A]. Proceedings of 23rd International Conference on Offshore Mechanics and Arctic Engineering2004 vol.2[C].Vancouver:OMAE,2004:959～966.
[14]任吉林,林俊明,高春法.电磁检测[M].北京:机械工业出版社,2000.
[15]美国无损检测学会编,美国无损检测手册译审委员会译.美国无损检测手册(电磁卷)[M].上海:世界图书出版社,1999.
[16] Smith R A.The potential for friction stir weld inspection using transient eddy currents[J].Insight-The Journal of The British Institute of NDT ,2005,47(3):133～143.
[17] Smith R A,G R Hugo.Transient eddy-current NDE for ageing aircraft-Capabilities and limitations[J].Insight-The Journal of The British Institute of NDT,2001,43(1):14～25.
[18] Neil J.Goldfine,et al.High Resolution Inductive Sensor Arrays For Material And Defect Characterization Of Welds[P].美国专利: US6995557 B2,2006-02-07.
[19] Neil J.Goldfine,et al.Method For Characterizing Coating And Substrates[P].美国专利: US6377039 B1,2002-04-23
[20] Neil J.Goldfine,et al.Friction Stir Weld Inspection Through Conductivity Imaging Using Shaped Field MWM?-Arrays[A].6th International Trends in Welding Research ConferenceProceedings[C].Pine Mountain: ASM International,2003:318～323.
[21]李功,黄民.基于小波包变换的超声回波信号特征提取[J].合肥工业大学学报(自然科学版),2006,29(2):246～249.
[22]吴婷,颜国正,杨帮华.基于小波包分解的脑电信号特征提取[J].仪器仪表学报,2007,28(12):2230～2234.
[23] Sad?k Kara,Fatma Dirgenali.A system to diagnose atherosclerosis via wavelet transforms,principal component analysis and artificial neural networks.Expert Systems with Applications,2007,32(2):632～640.
[24]张静远,张冰,蒋兴舟.基于小波变换的特征提取方法分析[J].信号处理,2000,16(2):156～162.
[25]李家伟,陈积懋.无损检测手册[M].机械工业出版社,2002.
[26]全国锅炉压力容器无损检测人员资格考核委员会.超声波探伤(Ⅱ、Ⅲ级教材)[M].北京:中国锅炉压力容器安全杂志社,1995.
[27]史立丰.铜-钢惯性摩擦焊接头超声波无损检测特性的研究[D].北京:北京工业大学,2003.
[28]《超声波探伤技术及探伤仪》编写组.超声波探伤技术及探伤仪[M].北京:国防工业出版社,1977.
[29]国家发展和改革委员会.JB/T 4730.3-2005,承压设备无损检测第3部分:超声检测[S].北京:[出版者不详],2005.
[30] Boggess Albert ,Narcowich Francis J.小波与傅里叶分析基础[M].北京:电子工业出版社,2004.
[31]夏纪真.超声检测中的缺陷定性方法[EB/OL].http://www.ndtinfo.net/hichina/wenxian/xjz-wenku/xjz-ut-dingxing.htm,2000-10-10/2008-3-20.
[32]蒋志峰.超声检测频域分析及对缺陷识别应用研究[D].杭州:浙江大学,2004.
[33]郑祥明,顾向华,史立丰,等.超声兰姆波的时频分析[J].声学学报.2003,28(4):368～374.
[34] Rodríguez M A,San Emeterio J L,Lázaro J C,et al.Ultrasonic flaw detection in NDE of higly scattering materials using wavelet and Wigner-Ville transform processing[J].Ultrasonics,2004,42(1-9):847～851.
[35]毛捷,简晓明,李明轩,等.信号处理在超声检测中的应用[J].应用声学,2000,19(3):45～47.
[36]张?.LY12铝合金细小夹杂物超声频谱分析法检测试验研究[D].西安:西北工业大学,2003.
[37]飞思科技产品研发中心.MATLAB7辅助信号处理技术与应用[M].北京:电子工业出版社,2005.
[38]岳钊,牛文成.小波分析在超声传感器系统特征信号预处理中的应用[J].南开大学学报(自然科学版),2005,38(2):5～9.
[39]焦卫东.基于互信息的小波特征提取方法及其在机械故障诊断中的应用[J].中国机械工程,2004,15(21):1946～1947.
[40]曾浩,周祖德,陈幼平,等.激光焊接质量实时检测和控制的进展[J].激光杂志,2000,21(1):2～5.
[41]飞思科技产品研发中心.小波分析理论与MATLAB7实现[M].北京:电子工业出版社,2005.
[42]罗莉.小波分析在焊缝缺陷识别中的应用[D].兰州:兰州理工大学,2004.
[43]许丹,刘强.基于小波多分辨率分析的高性能XY工作台故障诊断[J].中国机械工程,2007,18(5):573～576.
[44] Mallats H W.Singularity Detection and Processing with Wavelets[J].IEEE Trans.on Information Theory,1992,38(2):617～643.
[45] Chen Changming,Kovacevic Radovan,Jandgric Dragana.Wavelet transform analysis of acoustic emission in monitoring friction stir welding of 6061 aluminum[J].International Journal of Machine Tools and Manufacture,2003,43(13):1383～1390.
[46]程龙跃,李功.小波包分解在超声检测缺陷回波信号处理中的应用[J].安徽冶金,2006,(1):43～48.
[47] Chen Y J,Shi Y W,Zhang X P.Detection of weak bonding in friction welds by ultrasound[J].Ultrasonics,1998,36(1-5):141～146.
[48]郭建平.小波与分形在摩擦焊超声检测信号处理中的应用研究(D).西安:西北工业大学,2006.
[49]张淑艳.摩擦焊超声检测信号的小波分形分析[D].西安:西北工业大学,2005.
[50]张广明,赵明涛,王裕文,等.超声缺陷检测中小波变换信号处理的参数确定[J].声学学报,2000,25(5):450～454.
[51]刘素美,李书光.超声检测信号处理的小波基选择[J].新疆石油学院学报,2004,16(4):75～78.
[52]袁英民,孙金立,万钧,等.某航空发动机压气机叶片超声检测信号处理-四种典型小波基的应用比较[J].无损检测,2004,26(7):332～335.
[53]边肇祺.模式识别(第二版)[M].北京:清华大学出版社,2007.
[54]蔡元龙.模式识别[M].西安:西北电讯工程学院出版社,1986.
[55]苏金明,阮沈勇.MATLAB6.1实用指南(下册)[M].北京:电子工业出版社,2002.
[56]李建文,徐彦霖,王增勇.应用模式识别技术识别超声检测的缺陷类型[J].仪器仪表学报,2004,25(4):585～586.
[57]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].北京:电子工业出版社,2007.
[58]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005.
[59] Martínóscar,López Manuel,Martín Fernando.Artificial neural networks for quality control by ultrasonic testing in resistance spot welding[J].Journal of Materials Processing Technology,2007,183(2-3):226～233.
[60] Mathworks Inc.Neural network toolbox User's Guide[EB/OL].http://www.mathworks.com.
[61] Mirapeix J.García-Allende P B.Cobo A,et al.Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks[J].NDT&E International,2007,40(4):315～323.
[62]杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社,2002.
[63]何方国,齐欢.基于主成分分析与神经网络的非线性评价模型[J].武汉理工大学学报,2007,29(8):183-186.
[64]高惠璇.应用多元统计分析[M].北京:北京大学出版社,2005.
[65]于秀林.多元统计分析[M].北京:中国统计出版社,1999.
[66]何晓群.现代统计分析方法与应用(第二版)[M].北京:中国人民大学出版社,2007.
[2]柯黎明,邢丽,刘鸽平.搅拌摩擦焊工艺及其应用[J].南昌航空工业学院学报,1999,13(3):1-4.
[3]王大勇,冯吉才,王攀峰.搅拌摩擦焊用搅拌头研究现状与发展趋势[J].焊接,2004,(6):6～10.
[4]刘松平,刘菲菲,李乐刚,等.铝合金搅拌摩擦焊缝的无损检测方法[J].航空制造技术,2006,(3):81～84.
[5] Bird C.Quality control of friction stir welds by the application of non-destructive testing[A].4th International Symposium on Friction Stir Welding,Part City,Utah,USA,2003.
[6]柯黎明.搅拌摩擦焊接头成形规律研究[D].北京:清华大学,2007.
[7] Ghidinif T,Vugrin T,Dalle Donne C.Residual stresses,defects and non-destructive evaluation of FSW joints [J]. Welding International, 2005, 19(10): 783～790.
[8]周万盛,姚君山.铝及铝合金的焊接[M].北京:机械工业出版社,2006.
[9]柯黎明.搅拌摩擦焊接头典型缺陷检测及表征技术[Z].航空科学基金项目申请书,2006.
[10]刘松平,刘菲菲,李乐刚,等.搅拌摩擦焊缝变入射角超声检测方法研究[J].无损检测,2006,28(5):225～228.
[11] AndréLamarre,Olivier Dupuis,Michael Moles.Complete.Inspection of Friction Stir Welds in Aluminum using Ultrasonic and Eddy Current Arrays[J].CINDE Journal,2006,27(4): 14-16,18～22.
[12] Colin R Bird.Ultrasonic phased array inspection technology for the evaluation of friction sitr welds[J].Insight,2004,46(1):31～36.
[13] Bird C R,Kleiner D.The phased array inspection of friction stir welded aluminium plant[A]. Proceedings of 23rd International Conference on Offshore Mechanics and Arctic Engineering2004 vol.2[C].Vancouver:OMAE,2004:959～966.
[14]任吉林,林俊明,高春法.电磁检测[M].北京:机械工业出版社,2000.
[15]美国无损检测学会编,美国无损检测手册译审委员会译.美国无损检测手册(电磁卷)[M].上海:世界图书出版社,1999.
[16] Smith R A.The potential for friction stir weld inspection using transient eddy currents[J].Insight-The Journal of The British Institute of NDT ,2005,47(3):133～143.
[17] Smith R A,G R Hugo.Transient eddy-current NDE for ageing aircraft-Capabilities and limitations[J].Insight-The Journal of The British Institute of NDT,2001,43(1):14～25.
[18] Neil J.Goldfine,et al.High Resolution Inductive Sensor Arrays For Material And Defect Characterization Of Welds[P].美国专利: US6995557 B2,2006-02-07.
[19] Neil J.Goldfine,et al.Method For Characterizing Coating And Substrates[P].美国专利: US6377039 B1,2002-04-23
[20] Neil J.Goldfine,et al.Friction Stir Weld Inspection Through Conductivity Imaging Using Shaped Field MWM?-Arrays[A].6th International Trends in Welding Research ConferenceProceedings[C].Pine Mountain: ASM International,2003:318～323.
[21]李功,黄民.基于小波包变换的超声回波信号特征提取[J].合肥工业大学学报(自然科学版),2006,29(2):246～249.
[22]吴婷,颜国正,杨帮华.基于小波包分解的脑电信号特征提取[J].仪器仪表学报,2007,28(12):2230～2234.
[23] Sad?k Kara,Fatma Dirgenali.A system to diagnose atherosclerosis via wavelet transforms,principal component analysis and artificial neural networks.Expert Systems with Applications,2007,32(2):632～640.
[24]张静远,张冰,蒋兴舟.基于小波变换的特征提取方法分析[J].信号处理,2000,16(2):156～162.
[25]李家伟,陈积懋.无损检测手册[M].机械工业出版社,2002.
[26]全国锅炉压力容器无损检测人员资格考核委员会.超声波探伤(Ⅱ、Ⅲ级教材)[M].北京:中国锅炉压力容器安全杂志社,1995.
[27]史立丰.铜-钢惯性摩擦焊接头超声波无损检测特性的研究[D].北京:北京工业大学,2003.
[28]《超声波探伤技术及探伤仪》编写组.超声波探伤技术及探伤仪[M].北京:国防工业出版社,1977.
[29]国家发展和改革委员会.JB/T 4730.3-2005,承压设备无损检测第3部分:超声检测[S].北京:[出版者不详],2005.
[30] Boggess Albert ,Narcowich Francis J.小波与傅里叶分析基础[M].北京:电子工业出版社,2004.
[31]夏纪真.超声检测中的缺陷定性方法[EB/OL].http://www.ndtinfo.net/hichina/wenxian/xjz-wenku/xjz-ut-dingxing.htm,2000-10-10/2008-3-20.
[32]蒋志峰.超声检测频域分析及对缺陷识别应用研究[D].杭州:浙江大学,2004.
[33]郑祥明,顾向华,史立丰,等.超声兰姆波的时频分析[J].声学学报.2003,28(4):368～374.
[34] Rodríguez M A,San Emeterio J L,Lázaro J C,et al.Ultrasonic flaw detection in NDE of higly scattering materials using wavelet and Wigner-Ville transform processing[J].Ultrasonics,2004,42(1-9):847～851.
[35]毛捷,简晓明,李明轩,等.信号处理在超声检测中的应用[J].应用声学,2000,19(3):45～47.
[36]张?.LY12铝合金细小夹杂物超声频谱分析法检测试验研究[D].西安:西北工业大学,2003.
[37]飞思科技产品研发中心.MATLAB7辅助信号处理技术与应用[M].北京:电子工业出版社,2005.
[38]岳钊,牛文成.小波分析在超声传感器系统特征信号预处理中的应用[J].南开大学学报(自然科学版),2005,38(2):5～9.
[39]焦卫东.基于互信息的小波特征提取方法及其在机械故障诊断中的应用[J].中国机械工程,2004,15(21):1946～1947.
[40]曾浩,周祖德,陈幼平,等.激光焊接质量实时检测和控制的进展[J].激光杂志,2000,21(1):2～5.
[41]飞思科技产品研发中心.小波分析理论与MATLAB7实现[M].北京:电子工业出版社,2005.
[42]罗莉.小波分析在焊缝缺陷识别中的应用[D].兰州:兰州理工大学,2004.
[43]许丹,刘强.基于小波多分辨率分析的高性能XY工作台故障诊断[J].中国机械工程,2007,18(5):573～576.
[44] Mallats H W.Singularity Detection and Processing with Wavelets[J].IEEE Trans.on Information Theory,1992,38(2):617～643.
[45] Chen Changming,Kovacevic Radovan,Jandgric Dragana.Wavelet transform analysis of acoustic emission in monitoring friction stir welding of 6061 aluminum[J].International Journal of Machine Tools and Manufacture,2003,43(13):1383～1390.
[46]程龙跃,李功.小波包分解在超声检测缺陷回波信号处理中的应用[J].安徽冶金,2006,(1):43～48.
[47] Chen Y J,Shi Y W,Zhang X P.Detection of weak bonding in friction welds by ultrasound[J].Ultrasonics,1998,36(1-5):141～146.
[48]郭建平.小波与分形在摩擦焊超声检测信号处理中的应用研究(D).西安:西北工业大学,2006.
[49]张淑艳.摩擦焊超声检测信号的小波分形分析[D].西安:西北工业大学,2005.
[50]张广明,赵明涛,王裕文,等.超声缺陷检测中小波变换信号处理的参数确定[J].声学学报,2000,25(5):450～454.
[51]刘素美,李书光.超声检测信号处理的小波基选择[J].新疆石油学院学报,2004,16(4):75～78.
[52]袁英民,孙金立,万钧,等.某航空发动机压气机叶片超声检测信号处理-四种典型小波基的应用比较[J].无损检测,2004,26(7):332～335.
[53]边肇祺.模式识别(第二版)[M].北京:清华大学出版社,2007.
[54]蔡元龙.模式识别[M].西安:西北电讯工程学院出版社,1986.
[55]苏金明,阮沈勇.MATLAB6.1实用指南(下册)[M].北京:电子工业出版社,2002.
[56]李建文,徐彦霖,王增勇.应用模式识别技术识别超声检测的缺陷类型[J].仪器仪表学报,2004,25(4):585～586.
[57]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].北京:电子工业出版社,2007.
[58]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005.
[59] Martínóscar,López Manuel,Martín Fernando.Artificial neural networks for quality control by ultrasonic testing in resistance spot welding[J].Journal of Materials Processing Technology,2007,183(2-3):226～233.
[60] Mathworks Inc.Neural network toolbox User's Guide[EB/OL].http://www.mathworks.com.
[61] Mirapeix J.García-Allende P B.Cobo A,et al.Real-time arc-welding defect detection and classification with principal component analysis and artificial neural networks[J].NDT&E International,2007,40(4):315～323.
[62]杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社,2002.
[63]何方国,齐欢.基于主成分分析与神经网络的非线性评价模型[J].武汉理工大学学报,2007,29(8):183-186.
[64]高惠璇.应用多元统计分析[M].北京:北京大学出版社,2005.
[65]于秀林.多元统计分析[M].北京:中国统计出版社,1999.
[66]何晓群.现代统计分析方法与应用(第二版)[M].北京:中国人民大学出版社,2007.