非成像式超声检测缺陷类型识别关键技术及其应用研究
|
摘要
缺陷类型识别是定量超声无损检测中重要的基础性问题。随着超声无损检测技术朝着高可靠性、高精度、高实时以及定量化方向发展,研究应用于在线超声检测的缺陷类型识别技术具有日益重要的学术意义和工程价值。虽然通过超声成像重构缺陷几何轮廓的方式能够实现对缺陷类型识别,但需要等待耗时的全局超声扫描和数据合成的过程,其实时性不能满足高速的在线检测需要。而非成像式超声检测缺陷类型识别方法直接从超声反射回波信号中提取特征参数,通过分析特征参数与缺陷类型之间的对应关系实现对缺陷类型识别,由于不需要等待全局超声扫描和数据合成,该方法具有较高的实时性,特别适用于在线超声检测的场合。在实际应用中,由于存在材料结构噪声对信号的干扰以及小样本条件下先验知识缺乏等困难,非成像式超声检测缺陷类型识别的准确性和可推广性受到了严重影响。针对目前存在的这些问题,本论文对非成像式超声检测缺陷类型识别中的关键技术,包括结构噪声消除、缺陷特征提取与类型识别进行了系统的研究,提出了基于小波包变换的时频邻域自适应消噪方法、基于SFFS搜索的时频优选特征提取算法以及两种基于支持向量机的融合决策识别方法法,并分别采用人工缺陷和石油套管自然缺陷对上述方法的可行性和有效性进行了验证。第一章,论述非成像式超声检测缺陷类型识别的重要意义,综合国内外关于非成像式超声检测缺陷类型识别关键问题的研究现状,分析当前研究中存在的问题,确定进一步研究的方法路线。第二章,研究超声反射回波信号的组成、分布特点和平稳特性,分析典型人工缺陷的超声反射回波信号在不同空间域上的信息特征,为后续的信噪分离、特征提取和类型识别工作提供理论基础。第三章,在分析结构噪声分布特点的基础上,提出基于小波包变换的时频邻域自适应消噪方法。通过仿真信号和实测信号的消噪实验,验证该方法在提高信号信噪比和抑制信号失真方面的有效性。第四章,确定超声反射回波信号的多特征提取框架,对四种相互独立的传统特征提取方法进行研究,并给出具体的实现算法。针对传统特征提取方法缺乏量化依据的问题,提出基于小波包分解、Fisher准则和SFFS搜索算法的时频优选特征提取算法,并采用可分性测度对上述特提取方法的有效性进行评价。第五章,针对小样本条件下超声检测缺陷类型识别的困难,提出两种基于支持向量机的融合决策识别方法,分别应用于缺陷类型框架已知和未知的场合。通过对人工缺陷进行类型识别,验证上述识别方法的有效性。第六章,将所提出的方法应用于石油套管自然缺陷的类型识别,研究信号消噪和特征提取对识别正确率的影响,验证多特征融合决策识别方法的识别能力和泛化能力,分析整个识别过程的时间耗费以及应用于石油套管在线超声检测的可行性。第七章,对论文的主要内容、研究结果和创新点进行总结,并对以后的工作进行展望。
Defect identification is an important basic issue in quantitative ultrasonic nondestructive testing. With the development of ultrasonic testing towarding high reliability, high accuracy, real-time and quantitative analysis, it has greatly academic significance and engineering value to research on online ultrasonic defect identification. Although it is possible to achieve defect identification by ultrasound imaging method to synthesize geometric contour of the defect, but because of the time cost for the scan of whole object and the data synthesis, the imaging method can not meet the needs of high-speed online ultrasonic testing. Non-imaging ultrasonic defect identification method, which extracts features directly from ultrasonic signal and achieve defect identification by analyzing the relationship between features and defect types, does not need the time waiting for object scan and data synthesis, so, it is very suitable for online ultrasonic inspection and defect identification. However, there are still some problems in the practical application, such as the disturbance of grain noise, the shortage of priori knowledge in the small-sample situation, which can affect the accuracy and generalization of defects identification seriously. To solve these problems, some systematic studies are carried out on grain noise removal, feature extraction and pattern recognition, and the targeted methods are put forward, including a time-frequency adaptive de-noise method base on wavelet packet decomposition, a time-frequency features extraction method based on SFFS search algorithm, two fusion decision-making identification methods based on support vector machine.At last, tests are carried out with artificial defects and natural defects on oil casing pipe to verify the feasibility and effectiveness of these methods.In the first chapter, the importance of non-imaging ultrasonic defect identification is discussed, the research situation at home and abroad on the key technologies of non-imaging ultrasound defect identification is presented, and problems in current research are analyzed to guide the ways for further research work.In the second chapter, the composition, distribution and non-stationarity of ultrasonic signals are discussed, and the characteristics of ultrasonic signal achieved from typical artificial defect are analyzed at different space domains. These analysis results can provide a theoretical basis to noise removal, feature extraction and recognition in the follow-up section.In the third chapter, considering the distinctness of distribution between defect signal and noise, a time-frequency adaptive de-noise method base on wavelet packet decomposition is presented. Experiments are carried out with both simulated signals and real signals to verify the effectiveness of this method for the signal noise ratio improvement and the suppression of signal distortion.In the forth chapter, the multiple features extraction frame of ultrasonic signal is presented. Four irrelevant traditional feature extraction methods are discussed, and their implementations are presented. Considering the lack of quantitative criterion in traditional feature extraction methods, a new time-frequency feature extraction method based on wavelet decomposition, Fisher principle and SFFS selection algorithm is presented to optimize feature mining capability. The effectiveness of thees feature extraction methods are evaluated with distinguish ability criterion.In the fifth chapter, considering the small sample problem of defect identification in ultrasonic testing, two fusion decision-making identification methods are presented respectively for the applications where the defect type frame is known or unknown. A test with different artificial defects by ultrasonic inspection method is carried out to verify the effectiveness of these identification methods for the improvement of accurate and generalization.In the sixth chapter, theories and methods presented out in this paper are applied to the identification of natural defects on oil casing pipes. The influences caused by noise and feature extraction methods to the identification accurate are discussed. And the accurate and generalization of fusion decision-making identification methods are verified. At last the time costs of these methods are measured, and the feasibility for online ultrasonic testing is analyzed.
Defect identification is an important basic issue in quantitative ultrasonic nondestructive testing. With the development of ultrasonic testing towarding high reliability, high accuracy, real-time and quantitative analysis, it has greatly academic significance and engineering value to research on online ultrasonic defect identification. Although it is possible to achieve defect identification by ultrasound imaging method to synthesize geometric contour of the defect, but because of the time cost for the scan of whole object and the data synthesis, the imaging method can not meet the needs of high-speed online ultrasonic testing. Non-imaging ultrasonic defect identification method, which extracts features directly from ultrasonic signal and achieve defect identification by analyzing the relationship between features and defect types, does not need the time waiting for object scan and data synthesis, so, it is very suitable for online ultrasonic inspection and defect identification. However, there are still some problems in the practical application, such as the disturbance of grain noise, the shortage of priori knowledge in the small-sample situation, which can affect the accuracy and generalization of defects identification seriously. To solve these problems, some systematic studies are carried out on grain noise removal, feature extraction and pattern recognition, and the targeted methods are put forward, including a time-frequency adaptive de-noise method base on wavelet packet decomposition, a time-frequency features extraction method based on SFFS search algorithm, two fusion decision-making identification methods based on support vector machine.At last, tests are carried out with artificial defects and natural defects on oil casing pipe to verify the feasibility and effectiveness of these methods.In the first chapter, the importance of non-imaging ultrasonic defect identification is discussed, the research situation at home and abroad on the key technologies of non-imaging ultrasound defect identification is presented, and problems in current research are analyzed to guide the ways for further research work.In the second chapter, the composition, distribution and non-stationarity of ultrasonic signals are discussed, and the characteristics of ultrasonic signal achieved from typical artificial defect are analyzed at different space domains. These analysis results can provide a theoretical basis to noise removal, feature extraction and recognition in the follow-up section.In the third chapter, considering the distinctness of distribution between defect signal and noise, a time-frequency adaptive de-noise method base on wavelet packet decomposition is presented. Experiments are carried out with both simulated signals and real signals to verify the effectiveness of this method for the signal noise ratio improvement and the suppression of signal distortion.In the forth chapter, the multiple features extraction frame of ultrasonic signal is presented. Four irrelevant traditional feature extraction methods are discussed, and their implementations are presented. Considering the lack of quantitative criterion in traditional feature extraction methods, a new time-frequency feature extraction method based on wavelet decomposition, Fisher principle and SFFS selection algorithm is presented to optimize feature mining capability. The effectiveness of thees feature extraction methods are evaluated with distinguish ability criterion.In the fifth chapter, considering the small sample problem of defect identification in ultrasonic testing, two fusion decision-making identification methods are presented respectively for the applications where the defect type frame is known or unknown. A test with different artificial defects by ultrasonic inspection method is carried out to verify the effectiveness of these identification methods for the improvement of accurate and generalization.In the sixth chapter, theories and methods presented out in this paper are applied to the identification of natural defects on oil casing pipes. The influences caused by noise and feature extraction methods to the identification accurate are discussed. And the accurate and generalization of fusion decision-making identification methods are verified. At last the time costs of these methods are measured, and the feasibility for online ultrasonic testing is analyzed.
引文
[1] 李国华,吴淼.现代无损检测与评价[M].北京：化学工业出版社,2009.
[2] 杨克己.基于神经网络的检测声学信号处理理论与实践[博士学位论文].杭州：浙江大学,1997.
[3] 罗雄彪,陈铁群.超声无损检测的发展趋势[J].无损检测,2005(03):1-5.
[4] Kim YH, Song SJ, Kim JY. A new technique for the identification of ultrasonic flaw signals using deconvolution[J]. Ultrasonics,2004,41(10):799-804.
[5] SANIIE J, WANG T, BILGUTAY NM. Analysis of homomorphic processing for ultrasonic grain signal characterization[J]. IEEE Trans. On Ultrasonics, Ferroelectrics, and Frequency control,1989,36(3):365-375.
[6] SANIIE J, WANG T, BILGUTAY NM. Statistical evaluation of backscattered ultrasonic grain signals[J]. Journal of the Acoustical Society of America,1998,81(1):400-408.
[7] Grevillot M, Cudel C, Meyer JJ, Jacquey S. Two approaches to multiple specular echo detection using split spectrum processing:moving bandwidth minimization and mathematical morphology[J]. Ultrasonics,1999,37(6):417-422.
[8] Gustafsson MG. Nonlinear clutter suppression using split spectrum processing and optimal detection[J]. Ieee Transactions on Ultrasonics Ferroelectrics and Frequency Control,1996, 43(1):109-124.
[9] 杨克己,胡旭晓.基于神经网络的自适应裂谱分析方法[J].中国机械工程,2002,13(9):806-809.
[10] Sun HC, Saniie J. Ultrasonic flaw detection using split-spectrum processing combined with adaptive-network-based fuzzy inference system[J].1999 Ieee Ultrasonics Symposium Proceedings, Vols 1 and 2,1999:801-804.
[11] Saniie J, Nagle DT, Donohue KD. Analysis of Order Statistic Filters Applied to Ultrasonic Flaw Detection Using Split-Spectrum Processing[J]. Ieee Transactions on Ultrasonics Ferroelectrics and Frequency Control,1991,38(2):133-140.
[12]雷华明,聂文滨,阙沛文.基于最小值选中次数的分离谱加权算法的超声信号处理方法研究[J].无损检测,2005(02)：68-71.
[13]杨克己.基于神经网络的自适应滤波技术及其在超声检测中的应用[J].仪器仪表学报,2005,26(8)：813-817.
[14] Zhu Y, Weight JP. Ultrasonic Nondestructive Evaluation of Highly Scattering Materials Using Adaptive Filtering and DetectionfJ]. Ieee Transactions on Ultrasonics Ferroelectrics and Frequency Control,1994,41(1):26-33.
[15] MALLAT SG, HWANG WL. Sigularity detection and processing with wavelets[J]. IEEE Trans, on Inf. Theory,1992,38(2):617-643.
[16] DONOHO DL. De-noising by soft-thresholding[J]. IEEE Trans. on Inf. Theory,1995,41(3): 613-627.
[17] Lazaro JC, San Emeterio JL, Ramos A, Fernandez-Marron JL. Influence of thresholding
procedures in ultrasonic grain noise reduction using wavelets[J]. Ultrasonics,2002,40(1-8): 263-267.
[18] Rodriuez MA, San Emeterio JL, Lazaro JC, Ramos A. Ultrasonic flaw detection in NDE of highly scattering materials using wavelet and Wigner-Ville transform processing[J]. Ultrasonics,2004,42(1-9):847-851.
[19]马宏伟,王彬.小波变换在超声检测信号去噪中的应用[J].无损检测,2004(02):68-71.
[20]陈国平,于万宝,赵志钦等.电磁致热超声系统设计及基于小波阈值去噪方法的信号处理[J].电子学报,2008,36(6)：1130-1134.
[21]陈益,李书.改进的小波阈值消噪法应用于超声信号处理[J].北京航空航天大学学报,2006,32(4)：466-470.
[22]李斌,庄天戈.一种基于非线性域值小波包的超声图像闪斑抑制方法[J].红外与毫米波学报,2001,20(4)：307-310.
[23]刘守山,杨辰龙,李凌等.基于自适应小波阈值的超声信号消噪[J].浙江大学学报：工学版,2007,41(9)：1557-1560.
[24]袁英民,崔海涛,温卫东.航空发动机叶片超声检测信号的小波分析方法[J].燃气涡轮试验与研究,2003(02).
[25]卢超,张维,邬冠华等.小波变换软阈值去噪在粗晶材料超声检测中的应用[J].应用声学,2003(03).
[26] Cardoso G, Saniie W. Adaptive thresholding technique for denoising ultrasonic signals[J]. 2005 IEEE Ultrasonics Symposium, Vols 1-4,2005:544-547.
[27]车红昆,项占琴,程耀东.超声检测信号时频邻域自适应消噪技术[J].机械工程学报,2007,43(6)：227-232.
[28]简晓明,李明轩.小波变换和自适应噪声抵消在闭合裂纹超声检测中的应用[J].声学学报,2005,25(2)：97-102.
[29]毛捷,李明轩.子带自适应滤波在层状介质脱粘超声检测中的应用[J].声学学报(中文版),2003(03)：212-216.
[30] Liu ZQ, Lu MD, Wei MA. Structure noise reduction of ultrasonic signals using artificial neural network adaptive filtering[J]. Ultrasonics,1997,35(4):325-328.
[31] MALLAT S, Zhang Z. Matching pursuits with time-frequency dictionaries[J]. IEEE Trans. Signal Process,1993,41:3397-3415.
[32] Ruiz-Reyes N, Vera-Candeas P, Curpian-Alonso J, Mata-Campos R, Cuevas-Martinez JC. New matching pursuit-based algorithm for SNR improvement in ultrasonic NDT[J]. Ndt & E International,2005,38(6):453-458.
[33] Izquierdo M, Hernandez M, Graullera O, Ullate L. Time-frequency Wiener filtering for structural noise reduction[J]. Ultrasonics,2002,40:259-261.
[34] Song SJ, Kim HJ, Cho H. Development of an intelligent system for ultrasonic flaw classification in weldments[J]. Nuclear Engineering and Design,2002,212(1-3):307-320.
[35] Santos JB, Perdigao F. Automatic defects classification - a contribution[J]. Ndt & E International,2001,34(5):313-318.
[36] Case TJ, Waag RC. Flaw identification from time and frequency features of ultrasonic waveforms[J]. Ieee Transactions on Ultrasonics Ferroelectrics and Frequency Control,1996,
43(4):592-600.
[37]侯平魁,林良骥.水下目标识别的特征融合分类器设计[J].电子学报,2001,29(4):443-446.
[38]刚铁,王东华.表面缺陷的超声检测与识别[J].无损探伤,2000(03):12-14.
[39]刚铁,吴林.焊接缺陷的超声回波信号分析与最佳特征子集的选择[J].应用声学,1999,18(2)：38-43.
[40]田惠生,曹国秀,李延宁.功率谱分析在混凝土质量超声检测中的应用研究[J].西安交通大学学报,1997,31(12)：14-19.
[41] Wu Y, Du R. Feature extraction and assessment using wavelet packets for monitoring of machining processes[J]. Mechanical Systems and Signal Processing,1996,10(1):29-53.
[42] Kyungmi L, Estivill-Castro V. Feature extraction and gating techniques for ultrasonic shaft signal classification[J]. Applied Soft Computing,2007,7(1):156-65.
[43] Simone G, Morabitoa FC, Polikarb R. Feature extraction techniques for ultrasonic signal classification[J]. International Journal of Applied Electromagnetics and Mechanics,2001, 15(1):291-294.
[44]师小红,徐章遂,敦怡.构件裂纹缺陷的超声识别[J].固体火箭技术,2007,30(6):556-558.
[45]唐明州,张记龙.粘接结构超声信号的小波分解与特征提取[J].测试技术学报,2003(04)：362-366.
[46]张海燕,周全,夏金东.超声缺陷回波信号的小波包降噪及特征提取[J].仪器仪表学报,2006(01)：94-97.
[47]段方勇.层次介质结构的超声回波信号特征提取方法研究[J].信号处理,1998,14(3):220-225.
[48] Simone G, Morabito FC, Polikar R, Ramuhalli P, Udpa L, Udpa S. Feature extraction techniques for ultrasonic signal classification[J]. International Journal of Applied Electromagnetics and Mechanics,2001,15(1-4):291-294.
[49] Avci E, Turkoglu I, Poyraz M. Intelligent target recognition based on wavelet packet neural network[J]. Expert Systems with Applications,2005,29(1):175-182.
[50] Bettayeb F, Rachedi T, Benbartaoui H. An improved automated ultrasonic NDE system by wavelet and neuron networks[J]. Ultrasonics,2004,42(1-9):853-858.
[51] Margrave FW, Rigas K, Bradley DA, Barrowcliffe P. The use of neural networks in ultrasonic flaw detection[J]. Measurement,1999,25(2):143-154.
[52] Masnata A, Sunseri M. Neural network classification of flaws detected by ultrasonic means[J]. Ndt & E International,1996,29(2):87-93.
[53]简晓明,李明轩.超声检测中人工神经网络对缺陷定量评价[J].声学学报(中文版),2000(01)：71-77.
[54]吴淼,张海燕,孙智等.超声检测缺陷分类的小波分析与神经网络方法[J].中国矿业大学学报,2000(03)：239-243.
[55] Rizzo P, Bartoli I, Marzani A, di Scalea FL. Defect classification in pipes by neural networks using multiple guided ultrasonic wave features extracted after wavelet processing[J]. Journal of Pressure Vessel Technology-Transactions of the Asme,2005,
127(3):294-303.
[56] Jordan R, Feeney F, Nesbitt N, Evertsen JA. Classification of wood species by neural network analysis of ultrasonic signals[J]. Ultrasonics,1998,36(1-5):219-222.
[57] Horng MH, Chen SM. Multi-class Classification of Ultrasonic Supraspinatus Images based on Radial Basis Function Neural Network[J]. Journal of Medical and Biological Engineering, 2009,29(5):242-250.
[58] de Carvalho AA, Veiga J, da Silva IC, Pereira C, Rebello JMA. Preliminary study of classification of defects by ultrasonic pulse-echo signals using an artificial neural network[J]. Insight,2003,45(11):754-757.
[59]刘旭,夏金东,弓乐等.射频信号在超声检测缺陷识别中的应用研究[J].机械工程学报,2002,38(4)：84-87.
[60]陶卿,姚慧,范劲松. 一种新的机器学习算法：Support Vector Machines[J]模式识别与人工智能,2000,3(9)：285-290.
[61]祁亨年.支持向量机及其应用研究综述[J].计算机工程,2004,30(10):6-9.
[62] Steve R, Gunn. Support Vector Machines for Classification and Regression:Faculty of Engineering Science and Mathematics; 1998.
[63]张英,基于支持向量机的过程工业数据挖掘技术研究[博士学位论文].杭州：浙大大学,2005.
[64]边肇祺,张学工.模式识别(第二版)[M].北京：清华大学出版社,2000.
[65]李喜来,李艾华,白向峰.基于hmm—Svm融合模型的鲁棒人脸识别算法[J].光电工程,2010,37(6)：103-107.
[66]李伟红,龚卫国,陈伟民等.基于svm Rfe的人脸特征选择方法[J].光电工程,2006,33(5)：113-117.
[67]谢赛琴,沈福明,邱雪娜.基于支持向量机的人脸识别方法[J].计算机工程,2009,35(16)： 186-188.
[68]赵武锋,严晓浪.基于多尺度梯度角和svm的正面人脸识别方法[J].浙江大学学报：工学版,2008,42(4)：590-592.
[69]王凯.基于多分类支持向量机的有杆抽油泵故障诊断研究[J].西安石油大学学报：自然科学版,2010,2010(1)：91-95.
[70]邓森,杨军锋,郭明威等.基于虚拟仪器和模糊svm的航空发动机润滑系统故障诊断方法[J].润滑与密封,2010,2010(3)：90-95.
[71]万书亭,佟海侠,董炳辉.基于最小二乘支持向量机的滚动轴承故障诊断[J].振动.测试与诊断,2010,30(2)：149-152.
[72]李宏坤,周帅,黄文宗.基于时频图像特征提取的状态识别方法研究与应用[J].振动与冲击,2010,29(7)：184-188.
[73]申清明,高建民,李成.焊缝缺陷类型识别方法的研究[J].西安交通大学学报,2010,44(7)：100-103.
[74]王明达,张来斌,梁伟等.基于独立分量分析和支持向量机的管道泄漏识别方法[J].石油学报,2010,31(4)：659-663.
[75]涂宏斌,周新建.一种基于支持向量机的轴承表面缺陷检测方法[J].华东交通大学学报,2006,4：96-98.
[76]汤光华,王俐莉,严榴香等.基于支持向量机的雷达一维距离像识别[J].仪器仪表学报,2006,27(6)：779-780.
[77]张春城,周正欧.基于支持向量机的浅地层探地雷达目标分类识别研究[J].电子学报,2005,33(6)：1091-1094.
[78]张葛祥,荣海娜,金炜东.支持向量机在雷达辐射源信号识别中的应用[J].西南交通大学学报,2006,41(1)：25-30.
[79]李晓峰,沈毅.基于支持向量机的超声乳腺肿瘤图像计算机辅助诊断系统[J].光电子.激光,2008,19(1)：115-119.
[80]陈艳江,刘艳艳,赵国忠等.基于支持向量机的中药太赫兹光谱鉴别[J].光谱学与光谱分析,2009,29(9)：2346-2350.
[81]邢玉娟,李明.Nap序列核函数在话者识别中的应用[J].计算机工程,2010,36(8):194-196.
[82]王欢良,韩纪庆,李海峰等.基于hmm/Svm两级结构的汉语易混淆语音识别[J].模式识别与人工智能,2006,19(5)：578-584.
[83]朱志宇,张冰,刘维亭.基于模糊支持向量机的语音识别方法[J].计算机工程,2006,32(2)： 180-182.
[84]李政,罗飞路,潘孟春.基于支持向量机的航空发动机叶片超声检测[J].传感技术学报,2008,21(11)：1940-1943.
[85]戴波,赵晶,周炎.超声波管道内检测腐蚀缺陷分类识别研究[J].机床与液压,2008,36(B07)： 194-198.
[86]薛海涛,李永艳,崔春翔等.基于支持向量机的铝合金点焊多类缺陷识别[J].焊接学报,2008,29(8)：97-100.
[87]刘清坤,阙沛文,宋寿鹏.基于支持向量机的石油管线缺陷识别方法研究[J].传感技术学报,2005,24(3)：31-34.
[88]张晓光,肖兴明,任世锦等.基于广义加权支持向量机的焊接缺陷分类方法[J].华东理工大学学报：自然科学版,2005,31(5)：644-648.
[89] Lawrence.A.Klein.多传感器数据融合理论及应用[M].北京：北京理工大学出版社,2004.
[90]杨元喜,曾安敏.大地测量数据融合模式及其分析[J].武汉大学学报：信息科学版,2008,33(8)：771-774.
[91]乔玉良,连胤卓,邬明权.基于遥感与gis数据融合的煤矿资源开发动态分析[J].煤炭学报,2008,33(9)：1020-1024.
[92]金龙,陈小宏,王守东.基于支持向量机与信息融合的地震油气预测方法[J].石油地球物理勘探,2006,41(1)：76-80.
[93]梁义维,熊诗波.基于神经网络和Dempster—Shafter信息融合的煤岩界面预测[J].煤炭学报,2003,28(1)：86-90.
[94]邱声春.数据挖掘和数据融合技术在天气预报和气象服务中的应用研究[J].山西气象,2007,2：34-36.
[95]林孔元,任冬梅.基于过程理解的多模型综合预报系统[J].模式识别与人工智能,1999,12(4)：443-449.
[96]高太长,黄子洋,张鹏等.大气电场资料与雷达回波融合的一种方法[J].解放军理工
大学学报：自然科学版,2006,7(3)：302-306.
[97]宗长富,潘钊,胡丹等.基于扩展卡尔曼滤波的信息融合技术在车辆状态估计中的应用[J].机械工程学报,2009,45(10)：272-277.
[98]汪明磊,陈无畏,王檀彬等.基于分层传感器信息融合的智能车辆导航[J].农业机械学报,2009,11：165-170.
[99]陈莹,韩崇昭.运动车辆的多传感融合跟踪[J].西安交通大学学报,2004,38(10):1035-1039.
[100]张铁柱,蒋宏.机载雷达和红外数据融合的智能目标识别[J].红外与激光工程,2010,2010(4)：756-760.
[101]王成,王鑫全,等.被动式多雷达系统的多目标数据融合[J].电子学报,2001,29(11):F003-F003.
[102]郝重阳,唐文彬.雷达和红外成像双传感器信息融合目标识别研究[J].航空学报,1998,19(6)：726-729.
[103]向阳,史习智.混凝土结构缺陷的融合识别研究[J].振动工程学报,2001,14(1):36-41.
[104]佟晓君,马群,陈海彬等.混凝土强度无损检测逆回归综合法[J].机械强度,2005,27(5)：620-623.
[105]严寒冰,殷国富,刘小莹.大型回转体超声检测中缺陷类型的在线识别[J].应用基础与工程科学学报,2008,16(2)：247-254.
[106]刘继忠,周晓军,蒋志峰.数据融合技术在棒材缺陷超声识别中的应用[J].农业机械学报,2006,37(1)：160-162.
[107]郭建,陈勇,孙炳楠等.基于多传感器信息融合的结构损伤识别研究[J].振动工程学报,2005,18(2)：155-160.
[108]王学军,史习智.水下目标识别和数据融合[J].声学学报,1999,24(5):544-549.
[109]刚铁,吴林.超声检测中的多源信息融合技术与缺陷识别[J].机械工程学报,1999,35(1)： 11-14.
[110] http://baike.baidu.com/view/1202016.htm.
[111]Ohtsuka Y, Higashi M, Nishikawa M. Fundamental experiment for inspection of cooling pipes in operation by using ultrasonic technique[J]. Fusion Engineering and Design,2006, 81(8-14):1583-1587.
[112] Fei CG, Han ZZ, Liu QK. Ultrasonic flaw classification of seafloor petroleum transporting pipeline based on chaotic genetic algorithm and SVM[J]. Journal of X-Ray Science and Technology,2006,14(1):1-9.
[113] Li J, Zhan XL, Jin SJ. An Automatic Flaw Classification Method of Ultrasonic Nondestructive Testing for Pipeline Girth Welds[J]. Icia: 2009 International Conference on Information and Automation, Vols 1-3,2009:1463-1468.
[114] Cardoso G, Saniie J. Compression of ultrasonic data using transform thresholding and parameter estimation techniques[J].2002 Ieee Ultrasonics Symposium Proceedings, Vols 1 and 2,2002:837-840.
[115]张贤达,保铮.非平稳信号分析与处理[M].北京：国防工业出版社,1998.
[116] Sin SK, Chen CH. A comparison of deconvolution techniques for the ultrasonic nondestructive evaluation of materials[J]. Ieee Transactions on Image Processing,1992,1(1):
3-10.
[117]张贤达.现代信号处理(第二版)[M].北京：清华大学出版社,2002.
[118] Izquierdo MAG, Hernandez MG, Graullera O, Anaya JJ. Signal-to-noise ratio enhancement based on the whitening transformation of colored structural noise[J]. Ultrasonics,2000, 38(1-8):500-502.
[119]徐伯勋,白旭滨,傅孝毅.信号处理中的数学变换和估计方法[M].北京：清华大学出版社,2004.
[120] Blanco S, Figliola A, Quiroga RQ, Rosso OA, Serrano E. Time-frequency analysis of electroencephalogram series. Ⅲ. Wavelet packets and information cost function[J]. Physical Review E,1998,57(1):932-940.
[121]边肇祺,张学工.模式识别(第二版)[M].北京：清华大学出版社,2000.
[122]Andrew R W统计模式识别(第二版)[M].北京：电子工业出版社,2004.
[123] Chang C-C, Lin T-Y. Linear feature extraction by integrating pairwise and global discriminatory information via sequential forward floating selection and kernel QR factorization with column pivoting[J]. Pattern Recognition,2008,41(4):1373-1383.
[124] Ververidis D, Kotropoulos C. Fast and accurate sequential floating forward feature selection with the Bayes classifier applied to speech emotion recognition[J]. Signal Processing,2008, 88(12):2956-2970.
[125]白鹏,张喜斌,张斌.支持向量机理论及其工程应用实例[M].陕西：西安电子科技大学出版社,2008.
[126]邓乃杨,田英杰.数据挖掘中的新方法--支持向量机[M].北京：科学出版社,2004.
[127]王北明.热轧钢管的质量[M].北京：冶金工业出版社,1987.
[128]严泽生.现代热连轧无缝钢管生产[M].北京：冶金工业出版社,2009.
[2] 杨克己.基于神经网络的检测声学信号处理理论与实践[博士学位论文].杭州：浙江大学,1997.
[3] 罗雄彪,陈铁群.超声无损检测的发展趋势[J].无损检测,2005(03):1-5.
[4] Kim YH, Song SJ, Kim JY. A new technique for the identification of ultrasonic flaw signals using deconvolution[J]. Ultrasonics,2004,41(10):799-804.
[5] SANIIE J, WANG T, BILGUTAY NM. Analysis of homomorphic processing for ultrasonic grain signal characterization[J]. IEEE Trans. On Ultrasonics, Ferroelectrics, and Frequency control,1989,36(3):365-375.
[6] SANIIE J, WANG T, BILGUTAY NM. Statistical evaluation of backscattered ultrasonic grain signals[J]. Journal of the Acoustical Society of America,1998,81(1):400-408.
[7] Grevillot M, Cudel C, Meyer JJ, Jacquey S. Two approaches to multiple specular echo detection using split spectrum processing:moving bandwidth minimization and mathematical morphology[J]. Ultrasonics,1999,37(6):417-422.
[8] Gustafsson MG. Nonlinear clutter suppression using split spectrum processing and optimal detection[J]. Ieee Transactions on Ultrasonics Ferroelectrics and Frequency Control,1996, 43(1):109-124.
[9] 杨克己,胡旭晓.基于神经网络的自适应裂谱分析方法[J].中国机械工程,2002,13(9):806-809.
[10] Sun HC, Saniie J. Ultrasonic flaw detection using split-spectrum processing combined with adaptive-network-based fuzzy inference system[J].1999 Ieee Ultrasonics Symposium Proceedings, Vols 1 and 2,1999:801-804.
[11] Saniie J, Nagle DT, Donohue KD. Analysis of Order Statistic Filters Applied to Ultrasonic Flaw Detection Using Split-Spectrum Processing[J]. Ieee Transactions on Ultrasonics Ferroelectrics and Frequency Control,1991,38(2):133-140.
[12]雷华明,聂文滨,阙沛文.基于最小值选中次数的分离谱加权算法的超声信号处理方法研究[J].无损检测,2005(02)：68-71.
[13]杨克己.基于神经网络的自适应滤波技术及其在超声检测中的应用[J].仪器仪表学报,2005,26(8)：813-817.
[14] Zhu Y, Weight JP. Ultrasonic Nondestructive Evaluation of Highly Scattering Materials Using Adaptive Filtering and DetectionfJ]. Ieee Transactions on Ultrasonics Ferroelectrics and Frequency Control,1994,41(1):26-33.
[15] MALLAT SG, HWANG WL. Sigularity detection and processing with wavelets[J]. IEEE Trans, on Inf. Theory,1992,38(2):617-643.
[16] DONOHO DL. De-noising by soft-thresholding[J]. IEEE Trans. on Inf. Theory,1995,41(3): 613-627.
[17] Lazaro JC, San Emeterio JL, Ramos A, Fernandez-Marron JL. Influence of thresholding
procedures in ultrasonic grain noise reduction using wavelets[J]. Ultrasonics,2002,40(1-8): 263-267.
[18] Rodriuez MA, San Emeterio JL, Lazaro JC, Ramos A. Ultrasonic flaw detection in NDE of highly scattering materials using wavelet and Wigner-Ville transform processing[J]. Ultrasonics,2004,42(1-9):847-851.
[19]马宏伟,王彬.小波变换在超声检测信号去噪中的应用[J].无损检测,2004(02):68-71.
[20]陈国平,于万宝,赵志钦等.电磁致热超声系统设计及基于小波阈值去噪方法的信号处理[J].电子学报,2008,36(6)：1130-1134.
[21]陈益,李书.改进的小波阈值消噪法应用于超声信号处理[J].北京航空航天大学学报,2006,32(4)：466-470.
[22]李斌,庄天戈.一种基于非线性域值小波包的超声图像闪斑抑制方法[J].红外与毫米波学报,2001,20(4)：307-310.
[23]刘守山,杨辰龙,李凌等.基于自适应小波阈值的超声信号消噪[J].浙江大学学报：工学版,2007,41(9)：1557-1560.
[24]袁英民,崔海涛,温卫东.航空发动机叶片超声检测信号的小波分析方法[J].燃气涡轮试验与研究,2003(02).
[25]卢超,张维,邬冠华等.小波变换软阈值去噪在粗晶材料超声检测中的应用[J].应用声学,2003(03).
[26] Cardoso G, Saniie W. Adaptive thresholding technique for denoising ultrasonic signals[J]. 2005 IEEE Ultrasonics Symposium, Vols 1-4,2005:544-547.
[27]车红昆,项占琴,程耀东.超声检测信号时频邻域自适应消噪技术[J].机械工程学报,2007,43(6)：227-232.
[28]简晓明,李明轩.小波变换和自适应噪声抵消在闭合裂纹超声检测中的应用[J].声学学报,2005,25(2)：97-102.
[29]毛捷,李明轩.子带自适应滤波在层状介质脱粘超声检测中的应用[J].声学学报(中文版),2003(03)：212-216.
[30] Liu ZQ, Lu MD, Wei MA. Structure noise reduction of ultrasonic signals using artificial neural network adaptive filtering[J]. Ultrasonics,1997,35(4):325-328.
[31] MALLAT S, Zhang Z. Matching pursuits with time-frequency dictionaries[J]. IEEE Trans. Signal Process,1993,41:3397-3415.
[32] Ruiz-Reyes N, Vera-Candeas P, Curpian-Alonso J, Mata-Campos R, Cuevas-Martinez JC. New matching pursuit-based algorithm for SNR improvement in ultrasonic NDT[J]. Ndt & E International,2005,38(6):453-458.
[33] Izquierdo M, Hernandez M, Graullera O, Ullate L. Time-frequency Wiener filtering for structural noise reduction[J]. Ultrasonics,2002,40:259-261.
[34] Song SJ, Kim HJ, Cho H. Development of an intelligent system for ultrasonic flaw classification in weldments[J]. Nuclear Engineering and Design,2002,212(1-3):307-320.
[35] Santos JB, Perdigao F. Automatic defects classification - a contribution[J]. Ndt & E International,2001,34(5):313-318.
[36] Case TJ, Waag RC. Flaw identification from time and frequency features of ultrasonic waveforms[J]. Ieee Transactions on Ultrasonics Ferroelectrics and Frequency Control,1996,
43(4):592-600.
[37]侯平魁,林良骥.水下目标识别的特征融合分类器设计[J].电子学报,2001,29(4):443-446.
[38]刚铁,王东华.表面缺陷的超声检测与识别[J].无损探伤,2000(03):12-14.
[39]刚铁,吴林.焊接缺陷的超声回波信号分析与最佳特征子集的选择[J].应用声学,1999,18(2)：38-43.
[40]田惠生,曹国秀,李延宁.功率谱分析在混凝土质量超声检测中的应用研究[J].西安交通大学学报,1997,31(12)：14-19.
[41] Wu Y, Du R. Feature extraction and assessment using wavelet packets for monitoring of machining processes[J]. Mechanical Systems and Signal Processing,1996,10(1):29-53.
[42] Kyungmi L, Estivill-Castro V. Feature extraction and gating techniques for ultrasonic shaft signal classification[J]. Applied Soft Computing,2007,7(1):156-65.
[43] Simone G, Morabitoa FC, Polikarb R. Feature extraction techniques for ultrasonic signal classification[J]. International Journal of Applied Electromagnetics and Mechanics,2001, 15(1):291-294.
[44]师小红,徐章遂,敦怡.构件裂纹缺陷的超声识别[J].固体火箭技术,2007,30(6):556-558.
[45]唐明州,张记龙.粘接结构超声信号的小波分解与特征提取[J].测试技术学报,2003(04)：362-366.
[46]张海燕,周全,夏金东.超声缺陷回波信号的小波包降噪及特征提取[J].仪器仪表学报,2006(01)：94-97.
[47]段方勇.层次介质结构的超声回波信号特征提取方法研究[J].信号处理,1998,14(3):220-225.
[48] Simone G, Morabito FC, Polikar R, Ramuhalli P, Udpa L, Udpa S. Feature extraction techniques for ultrasonic signal classification[J]. International Journal of Applied Electromagnetics and Mechanics,2001,15(1-4):291-294.
[49] Avci E, Turkoglu I, Poyraz M. Intelligent target recognition based on wavelet packet neural network[J]. Expert Systems with Applications,2005,29(1):175-182.
[50] Bettayeb F, Rachedi T, Benbartaoui H. An improved automated ultrasonic NDE system by wavelet and neuron networks[J]. Ultrasonics,2004,42(1-9):853-858.
[51] Margrave FW, Rigas K, Bradley DA, Barrowcliffe P. The use of neural networks in ultrasonic flaw detection[J]. Measurement,1999,25(2):143-154.
[52] Masnata A, Sunseri M. Neural network classification of flaws detected by ultrasonic means[J]. Ndt & E International,1996,29(2):87-93.
[53]简晓明,李明轩.超声检测中人工神经网络对缺陷定量评价[J].声学学报(中文版),2000(01)：71-77.
[54]吴淼,张海燕,孙智等.超声检测缺陷分类的小波分析与神经网络方法[J].中国矿业大学学报,2000(03)：239-243.
[55] Rizzo P, Bartoli I, Marzani A, di Scalea FL. Defect classification in pipes by neural networks using multiple guided ultrasonic wave features extracted after wavelet processing[J]. Journal of Pressure Vessel Technology-Transactions of the Asme,2005,
127(3):294-303.
[56] Jordan R, Feeney F, Nesbitt N, Evertsen JA. Classification of wood species by neural network analysis of ultrasonic signals[J]. Ultrasonics,1998,36(1-5):219-222.
[57] Horng MH, Chen SM. Multi-class Classification of Ultrasonic Supraspinatus Images based on Radial Basis Function Neural Network[J]. Journal of Medical and Biological Engineering, 2009,29(5):242-250.
[58] de Carvalho AA, Veiga J, da Silva IC, Pereira C, Rebello JMA. Preliminary study of classification of defects by ultrasonic pulse-echo signals using an artificial neural network[J]. Insight,2003,45(11):754-757.
[59]刘旭,夏金东,弓乐等.射频信号在超声检测缺陷识别中的应用研究[J].机械工程学报,2002,38(4)：84-87.
[60]陶卿,姚慧,范劲松. 一种新的机器学习算法：Support Vector Machines[J]模式识别与人工智能,2000,3(9)：285-290.
[61]祁亨年.支持向量机及其应用研究综述[J].计算机工程,2004,30(10):6-9.
[62] Steve R, Gunn. Support Vector Machines for Classification and Regression:Faculty of Engineering Science and Mathematics; 1998.
[63]张英,基于支持向量机的过程工业数据挖掘技术研究[博士学位论文].杭州：浙大大学,2005.
[64]边肇祺,张学工.模式识别(第二版)[M].北京：清华大学出版社,2000.
[65]李喜来,李艾华,白向峰.基于hmm—Svm融合模型的鲁棒人脸识别算法[J].光电工程,2010,37(6)：103-107.
[66]李伟红,龚卫国,陈伟民等.基于svm Rfe的人脸特征选择方法[J].光电工程,2006,33(5)：113-117.
[67]谢赛琴,沈福明,邱雪娜.基于支持向量机的人脸识别方法[J].计算机工程,2009,35(16)： 186-188.
[68]赵武锋,严晓浪.基于多尺度梯度角和svm的正面人脸识别方法[J].浙江大学学报：工学版,2008,42(4)：590-592.
[69]王凯.基于多分类支持向量机的有杆抽油泵故障诊断研究[J].西安石油大学学报：自然科学版,2010,2010(1)：91-95.
[70]邓森,杨军锋,郭明威等.基于虚拟仪器和模糊svm的航空发动机润滑系统故障诊断方法[J].润滑与密封,2010,2010(3)：90-95.
[71]万书亭,佟海侠,董炳辉.基于最小二乘支持向量机的滚动轴承故障诊断[J].振动.测试与诊断,2010,30(2)：149-152.
[72]李宏坤,周帅,黄文宗.基于时频图像特征提取的状态识别方法研究与应用[J].振动与冲击,2010,29(7)：184-188.
[73]申清明,高建民,李成.焊缝缺陷类型识别方法的研究[J].西安交通大学学报,2010,44(7)：100-103.
[74]王明达,张来斌,梁伟等.基于独立分量分析和支持向量机的管道泄漏识别方法[J].石油学报,2010,31(4)：659-663.
[75]涂宏斌,周新建.一种基于支持向量机的轴承表面缺陷检测方法[J].华东交通大学学报,2006,4：96-98.
[76]汤光华,王俐莉,严榴香等.基于支持向量机的雷达一维距离像识别[J].仪器仪表学报,2006,27(6)：779-780.
[77]张春城,周正欧.基于支持向量机的浅地层探地雷达目标分类识别研究[J].电子学报,2005,33(6)：1091-1094.
[78]张葛祥,荣海娜,金炜东.支持向量机在雷达辐射源信号识别中的应用[J].西南交通大学学报,2006,41(1)：25-30.
[79]李晓峰,沈毅.基于支持向量机的超声乳腺肿瘤图像计算机辅助诊断系统[J].光电子.激光,2008,19(1)：115-119.
[80]陈艳江,刘艳艳,赵国忠等.基于支持向量机的中药太赫兹光谱鉴别[J].光谱学与光谱分析,2009,29(9)：2346-2350.
[81]邢玉娟,李明.Nap序列核函数在话者识别中的应用[J].计算机工程,2010,36(8):194-196.
[82]王欢良,韩纪庆,李海峰等.基于hmm/Svm两级结构的汉语易混淆语音识别[J].模式识别与人工智能,2006,19(5)：578-584.
[83]朱志宇,张冰,刘维亭.基于模糊支持向量机的语音识别方法[J].计算机工程,2006,32(2)： 180-182.
[84]李政,罗飞路,潘孟春.基于支持向量机的航空发动机叶片超声检测[J].传感技术学报,2008,21(11)：1940-1943.
[85]戴波,赵晶,周炎.超声波管道内检测腐蚀缺陷分类识别研究[J].机床与液压,2008,36(B07)： 194-198.
[86]薛海涛,李永艳,崔春翔等.基于支持向量机的铝合金点焊多类缺陷识别[J].焊接学报,2008,29(8)：97-100.
[87]刘清坤,阙沛文,宋寿鹏.基于支持向量机的石油管线缺陷识别方法研究[J].传感技术学报,2005,24(3)：31-34.
[88]张晓光,肖兴明,任世锦等.基于广义加权支持向量机的焊接缺陷分类方法[J].华东理工大学学报：自然科学版,2005,31(5)：644-648.
[89] Lawrence.A.Klein.多传感器数据融合理论及应用[M].北京：北京理工大学出版社,2004.
[90]杨元喜,曾安敏.大地测量数据融合模式及其分析[J].武汉大学学报：信息科学版,2008,33(8)：771-774.
[91]乔玉良,连胤卓,邬明权.基于遥感与gis数据融合的煤矿资源开发动态分析[J].煤炭学报,2008,33(9)：1020-1024.
[92]金龙,陈小宏,王守东.基于支持向量机与信息融合的地震油气预测方法[J].石油地球物理勘探,2006,41(1)：76-80.
[93]梁义维,熊诗波.基于神经网络和Dempster—Shafter信息融合的煤岩界面预测[J].煤炭学报,2003,28(1)：86-90.
[94]邱声春.数据挖掘和数据融合技术在天气预报和气象服务中的应用研究[J].山西气象,2007,2：34-36.
[95]林孔元,任冬梅.基于过程理解的多模型综合预报系统[J].模式识别与人工智能,1999,12(4)：443-449.
[96]高太长,黄子洋,张鹏等.大气电场资料与雷达回波融合的一种方法[J].解放军理工
大学学报：自然科学版,2006,7(3)：302-306.
[97]宗长富,潘钊,胡丹等.基于扩展卡尔曼滤波的信息融合技术在车辆状态估计中的应用[J].机械工程学报,2009,45(10)：272-277.
[98]汪明磊,陈无畏,王檀彬等.基于分层传感器信息融合的智能车辆导航[J].农业机械学报,2009,11：165-170.
[99]陈莹,韩崇昭.运动车辆的多传感融合跟踪[J].西安交通大学学报,2004,38(10):1035-1039.
[100]张铁柱,蒋宏.机载雷达和红外数据融合的智能目标识别[J].红外与激光工程,2010,2010(4)：756-760.
[101]王成,王鑫全,等.被动式多雷达系统的多目标数据融合[J].电子学报,2001,29(11):F003-F003.
[102]郝重阳,唐文彬.雷达和红外成像双传感器信息融合目标识别研究[J].航空学报,1998,19(6)：726-729.
[103]向阳,史习智.混凝土结构缺陷的融合识别研究[J].振动工程学报,2001,14(1):36-41.
[104]佟晓君,马群,陈海彬等.混凝土强度无损检测逆回归综合法[J].机械强度,2005,27(5)：620-623.
[105]严寒冰,殷国富,刘小莹.大型回转体超声检测中缺陷类型的在线识别[J].应用基础与工程科学学报,2008,16(2)：247-254.
[106]刘继忠,周晓军,蒋志峰.数据融合技术在棒材缺陷超声识别中的应用[J].农业机械学报,2006,37(1)：160-162.
[107]郭建,陈勇,孙炳楠等.基于多传感器信息融合的结构损伤识别研究[J].振动工程学报,2005,18(2)：155-160.
[108]王学军,史习智.水下目标识别和数据融合[J].声学学报,1999,24(5):544-549.
[109]刚铁,吴林.超声检测中的多源信息融合技术与缺陷识别[J].机械工程学报,1999,35(1)： 11-14.
[110] http://baike.baidu.com/view/1202016.htm.
[111]Ohtsuka Y, Higashi M, Nishikawa M. Fundamental experiment for inspection of cooling pipes in operation by using ultrasonic technique[J]. Fusion Engineering and Design,2006, 81(8-14):1583-1587.
[112] Fei CG, Han ZZ, Liu QK. Ultrasonic flaw classification of seafloor petroleum transporting pipeline based on chaotic genetic algorithm and SVM[J]. Journal of X-Ray Science and Technology,2006,14(1):1-9.
[113] Li J, Zhan XL, Jin SJ. An Automatic Flaw Classification Method of Ultrasonic Nondestructive Testing for Pipeline Girth Welds[J]. Icia: 2009 International Conference on Information and Automation, Vols 1-3,2009:1463-1468.
[114] Cardoso G, Saniie J. Compression of ultrasonic data using transform thresholding and parameter estimation techniques[J].2002 Ieee Ultrasonics Symposium Proceedings, Vols 1 and 2,2002:837-840.
[115]张贤达,保铮.非平稳信号分析与处理[M].北京：国防工业出版社,1998.
[116] Sin SK, Chen CH. A comparison of deconvolution techniques for the ultrasonic nondestructive evaluation of materials[J]. Ieee Transactions on Image Processing,1992,1(1):
3-10.
[117]张贤达.现代信号处理(第二版)[M].北京：清华大学出版社,2002.
[118] Izquierdo MAG, Hernandez MG, Graullera O, Anaya JJ. Signal-to-noise ratio enhancement based on the whitening transformation of colored structural noise[J]. Ultrasonics,2000, 38(1-8):500-502.
[119]徐伯勋,白旭滨,傅孝毅.信号处理中的数学变换和估计方法[M].北京：清华大学出版社,2004.
[120] Blanco S, Figliola A, Quiroga RQ, Rosso OA, Serrano E. Time-frequency analysis of electroencephalogram series. Ⅲ. Wavelet packets and information cost function[J]. Physical Review E,1998,57(1):932-940.
[121]边肇祺,张学工.模式识别(第二版)[M].北京：清华大学出版社,2000.
[122]Andrew R W统计模式识别(第二版)[M].北京：电子工业出版社,2004.
[123] Chang C-C, Lin T-Y. Linear feature extraction by integrating pairwise and global discriminatory information via sequential forward floating selection and kernel QR factorization with column pivoting[J]. Pattern Recognition,2008,41(4):1373-1383.
[124] Ververidis D, Kotropoulos C. Fast and accurate sequential floating forward feature selection with the Bayes classifier applied to speech emotion recognition[J]. Signal Processing,2008, 88(12):2956-2970.
[125]白鹏,张喜斌,张斌.支持向量机理论及其工程应用实例[M].陕西：西安电子科技大学出版社,2008.
[126]邓乃杨,田英杰.数据挖掘中的新方法--支持向量机[M].北京：科学出版社,2004.
[127]王北明.热轧钢管的质量[M].北京：冶金工业出版社,1987.
[128]严泽生.现代热连轧无缝钢管生产[M].北京：冶金工业出版社,2009.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |