强噪声环境下7N01铝合金损伤声发射监测研究
摘要
随着高速铁路的不断发展，铝合金在列车结构如牵引梁、枕梁等构件中得到广泛引用。在列车高速运行过程中，铝合金结构由于受到交变载荷的作用，易产生疲劳损伤，从而危及列车的安全运行。目前，常规无损检测方法需要在列车停运状态下对铝合金结构进行离线的检测，因而无法对高速运行过程中的铝合金结构进行在线状态监测。与常规的无损检测技术相比，声发射技术具有对活动性缺陷敏感、可对大型结构快速整体检测等优点，但是目前声发射技术在列车中的检测应用还处于起步阶段。由于对列车用铝合金损伤的声发射特征以及列车运行过程中的噪声信号还缺少认识，因此研究其损伤的声发射特征，以及在运行噪声环境下提取铝合金损伤的声发射信号成为目前列车声发射监测急需解决的问题。
针对列车声发射监测存在的问题，本文开发了一套显微图像原位观测系统，该系统可以对材料损伤过程的行为进行连续图像监测及采集，可为声发射信号的分析提供技术手段。
采用声发射系统与开发的显微图像原位观测系统同步监测列车用铝合金母材及焊缝静载损伤过程，分析了声发射信号时域、频域、时频域的特征，建立了声发射特征与静载损伤裂纹扩展之间的关系，并通过断口分析确定了静载损伤过程中的声发射源，研究结果显示：声发射能量、峰值频率及质心频率的变化可有效监测铝合金微裂纹的萌生。
铝合金结构在列车服役过程中受交变载荷的作用易产生疲劳裂纹，而疲劳裂纹扩展速率是评估铝合金结构剩余寿命的基本数据。在实验室条件下，采用声发射及自制的显微图像原位观测系统监测了铝合金疲劳过程，研究了铝合金母材及焊缝疲劳损伤过程中裂纹萌生、扩展及相应的声发射特征，并通过疲劳断口分析了声发射的产生源。研究结果表明：铝合金疲劳损伤过程中的声发射存在三个不同的变化阶段，分别与疲劳裂纹扩展的三个阶段相对应。在疲劳裂纹萌生阶段，声发射特征值的变化对应的疲劳循环次数早于显微图像原位观测系统首次发现疲劳微裂纹的循环次数，因此声发射特征值可作为疲劳裂纹萌生的指标。建立了声发射计数率与疲劳裂纹扩展速率之间的关系，通过声发射监测得到的特征值以及建立的关系可以计算出疲劳裂纹的扩展速率，从而评估铝合金结构的健康状态，避免了列车结构中应力强度因子的测量困难。
为了分析列车运行过程中噪声的特征，开发了一套小型现场加载系统，在列车运行过程中，采用该系统对列车用铝合金进行加载，来模拟列车服役过程中的声发射信号，同时利用数据采集系统实时获取噪声环境下的声发射信号，为后续的信号分析与处理提供了基础数据。通过对列车静止和运行过程中，铝合金不加载与加载过程产生的声发射信号对比分析，得到了列车运行过程中的噪声信号类型。对采集的噪声与裂纹声发射的混合信号，首先采用时差法分离出噪声与裂纹声发射两个信号集合，分别在时域、频域、时频域分析了噪声信号的特征，并提取了噪声与裂纹声发射信号在上述值域的特征值。对提取的特征值采用欧氏距离评价准则进行了优化，得到最佳特征值子集。在此基础上构建了BP神经网络分类器，对噪声与裂纹声发射信号样本进行了智能识别，有效分离了噪声信号，从而降低了噪声信号对声发射检测结果的影响。
With the development of high-speed railways, aluminum is widely used in trainstructures, such as the traction beams, corbels and other components. When the trainruns at high speed, fatigue damage will be caused by alternating load in thealuminum structure, which endanger the safe operation of the train. Currently,non-destructive methods need to stop the train and test the body of the train off-line,so they are unable to monitor the body parts during operating condition. Comparedwith conventional non-destructive testing methods, acoustic emission technology issensitive to active defects, and can detect the overall structures fast and efficiently,but the application in trains is still in its infancy. Due to the lack of awareness of AEcharacteristics of aluminum alloy and noise signals in running trains, it is urgent toresearch acoustic emission signals from damage of aluminum and extract them fromnoisy environment when acoustic emission technique used in trains.
For the problems of acoustic emission monitoring used in trains, a new in-situmicroscopic observation method was proposed in this paper, which can monitor thematerial damage process and capture damage images continuously, and it willprovide technical assistance to the analysis of acoustic emission signals.
Acoustic emission and the in-situ microscopic observation system were used tomonitor aluminum base metal and weld during static damage process. The time,frequency and time-frequency domain characteristics of acoustic emission signalswere analyzed to establish the relationship between the characteristics and staticdamage behavior. The acoustic emission sources were identified by the fractureanalysis. The results show that acoustic emission energy, peak and centroidfrequency were effective indicators to monitor the crack initiation of aluminum.
Fatigue cracks are easy to cause by alternating loads in aluminum structureduring the service process of trains, and fatigue crack growth rate is the base data toassess damage degree of aluminum structures. Acoustic emission features of crackinitiation and propagation in fatigue damage process of the aluminum base metaland weld were studied under laboratory conditions, and fatigue processes weremonitored by acoustic emission and in-situ microscopic observation system. Thesources of acoustic emission were analyzed by fatigue fracture. The results showthat fatigue damage of aluminum has three different acoustic emission stages, whichcorresponds to the three stages of fatigue crack growth respectively. In the fatiguecrack initiation stage, number of fatigue cycles corresponding to the change ofacoustic emission features was earlier than the number when micro-crack was firstdiscovered by the in-situ microscopic observation system. Therefore the acoustic emission features can be used as indicators of fatigue crack initiation. Relationshipbetween the acoustic emission count rate and fatigue crack growth rate wasestablished. The fatigue crack growth rate can be calculated through the monitoredacoustic emission features and the established relationships. Thus the health statusof aluminum structures was assessed, and the problem of difficult measurement forthe stress intensity factor in actual structure was avoided.
In order to analyse the noise features in the moving train, a small in-siteloading system was developed to load aluminum alloy in a running train, whichsimulated acoustic emission signals in the service process of the train. Dataacquisition system was used to get real-time acoustic emission signals under noisyenvironments, which were the basic data provided for subsequent signal analysisand processing. Types of noise signals were analyzed through comparative analysisof acoustic emission signals obtained on the static and operational train, whenaluminum is not loaded and loaded. For the collected mix signal that contain noiseand acoustic emission signals from crack propagation, the time difference methodwas used to separate two signal sets of noise and acoustic emission signals fromcrack propagation. The characteristics of noise signals in time and frequency domain,time-frequency domain were analyzed, then the features of the noise and AE signalsfrom crack propagation in the above range were extracted. The extracted featurevalues were optimized to get the best feature subset using the Euclidean distanceevaluation criteria. On this basis, BP neural network classifier was constructed toidentify samples of noise and acoustic emission signals from crack propagation,which effectively separated the noise signals, thus lay a foundation for the acousticemission technique to monitor the aluminum structures used in trains.
针对列车声发射监测存在的问题，本文开发了一套显微图像原位观测系统，该系统可以对材料损伤过程的行为进行连续图像监测及采集，可为声发射信号的分析提供技术手段。
采用声发射系统与开发的显微图像原位观测系统同步监测列车用铝合金母材及焊缝静载损伤过程，分析了声发射信号时域、频域、时频域的特征，建立了声发射特征与静载损伤裂纹扩展之间的关系，并通过断口分析确定了静载损伤过程中的声发射源，研究结果显示：声发射能量、峰值频率及质心频率的变化可有效监测铝合金微裂纹的萌生。
铝合金结构在列车服役过程中受交变载荷的作用易产生疲劳裂纹，而疲劳裂纹扩展速率是评估铝合金结构剩余寿命的基本数据。在实验室条件下，采用声发射及自制的显微图像原位观测系统监测了铝合金疲劳过程，研究了铝合金母材及焊缝疲劳损伤过程中裂纹萌生、扩展及相应的声发射特征，并通过疲劳断口分析了声发射的产生源。研究结果表明：铝合金疲劳损伤过程中的声发射存在三个不同的变化阶段，分别与疲劳裂纹扩展的三个阶段相对应。在疲劳裂纹萌生阶段，声发射特征值的变化对应的疲劳循环次数早于显微图像原位观测系统首次发现疲劳微裂纹的循环次数，因此声发射特征值可作为疲劳裂纹萌生的指标。建立了声发射计数率与疲劳裂纹扩展速率之间的关系，通过声发射监测得到的特征值以及建立的关系可以计算出疲劳裂纹的扩展速率，从而评估铝合金结构的健康状态，避免了列车结构中应力强度因子的测量困难。
为了分析列车运行过程中噪声的特征，开发了一套小型现场加载系统，在列车运行过程中，采用该系统对列车用铝合金进行加载，来模拟列车服役过程中的声发射信号，同时利用数据采集系统实时获取噪声环境下的声发射信号，为后续的信号分析与处理提供了基础数据。通过对列车静止和运行过程中，铝合金不加载与加载过程产生的声发射信号对比分析，得到了列车运行过程中的噪声信号类型。对采集的噪声与裂纹声发射的混合信号，首先采用时差法分离出噪声与裂纹声发射两个信号集合，分别在时域、频域、时频域分析了噪声信号的特征，并提取了噪声与裂纹声发射信号在上述值域的特征值。对提取的特征值采用欧氏距离评价准则进行了优化，得到最佳特征值子集。在此基础上构建了BP神经网络分类器，对噪声与裂纹声发射信号样本进行了智能识别，有效分离了噪声信号，从而降低了噪声信号对声发射检测结果的影响。
With the development of high-speed railways, aluminum is widely used in trainstructures, such as the traction beams, corbels and other components. When the trainruns at high speed, fatigue damage will be caused by alternating load in thealuminum structure, which endanger the safe operation of the train. Currently,non-destructive methods need to stop the train and test the body of the train off-line,so they are unable to monitor the body parts during operating condition. Comparedwith conventional non-destructive testing methods, acoustic emission technology issensitive to active defects, and can detect the overall structures fast and efficiently,but the application in trains is still in its infancy. Due to the lack of awareness of AEcharacteristics of aluminum alloy and noise signals in running trains, it is urgent toresearch acoustic emission signals from damage of aluminum and extract them fromnoisy environment when acoustic emission technique used in trains.
For the problems of acoustic emission monitoring used in trains, a new in-situmicroscopic observation method was proposed in this paper, which can monitor thematerial damage process and capture damage images continuously, and it willprovide technical assistance to the analysis of acoustic emission signals.
Acoustic emission and the in-situ microscopic observation system were used tomonitor aluminum base metal and weld during static damage process. The time,frequency and time-frequency domain characteristics of acoustic emission signalswere analyzed to establish the relationship between the characteristics and staticdamage behavior. The acoustic emission sources were identified by the fractureanalysis. The results show that acoustic emission energy, peak and centroidfrequency were effective indicators to monitor the crack initiation of aluminum.
Fatigue cracks are easy to cause by alternating loads in aluminum structureduring the service process of trains, and fatigue crack growth rate is the base data toassess damage degree of aluminum structures. Acoustic emission features of crackinitiation and propagation in fatigue damage process of the aluminum base metaland weld were studied under laboratory conditions, and fatigue processes weremonitored by acoustic emission and in-situ microscopic observation system. Thesources of acoustic emission were analyzed by fatigue fracture. The results showthat fatigue damage of aluminum has three different acoustic emission stages, whichcorresponds to the three stages of fatigue crack growth respectively. In the fatiguecrack initiation stage, number of fatigue cycles corresponding to the change ofacoustic emission features was earlier than the number when micro-crack was firstdiscovered by the in-situ microscopic observation system. Therefore the acoustic emission features can be used as indicators of fatigue crack initiation. Relationshipbetween the acoustic emission count rate and fatigue crack growth rate wasestablished. The fatigue crack growth rate can be calculated through the monitoredacoustic emission features and the established relationships. Thus the health statusof aluminum structures was assessed, and the problem of difficult measurement forthe stress intensity factor in actual structure was avoided.
In order to analyse the noise features in the moving train, a small in-siteloading system was developed to load aluminum alloy in a running train, whichsimulated acoustic emission signals in the service process of the train. Dataacquisition system was used to get real-time acoustic emission signals under noisyenvironments, which were the basic data provided for subsequent signal analysisand processing. Types of noise signals were analyzed through comparative analysisof acoustic emission signals obtained on the static and operational train, whenaluminum is not loaded and loaded. For the collected mix signal that contain noiseand acoustic emission signals from crack propagation, the time difference methodwas used to separate two signal sets of noise and acoustic emission signals fromcrack propagation. The characteristics of noise signals in time and frequency domain,time-frequency domain were analyzed, then the features of the noise and AE signalsfrom crack propagation in the above range were extracted. The extracted featurevalues were optimized to get the best feature subset using the Euclidean distanceevaluation criteria. On this basis, BP neural network classifier was constructed toidentify samples of noise and acoustic emission signals from crack propagation,which effectively separated the noise signals, thus lay a foundation for the acousticemission technique to monitor the aluminum structures used in trains.
引文
[1]张卫华,王伯铭.中国高速列车的创新发展[J].机车电传动,2010,(1):8-12.
[2]牧野一成,蔡千华.车辆隐性裂纹的检查方法[J].国外机车车辆工艺,2009,(2):40-43.
[3]周弋琳,王晓敏,马佳,等.高速列车牵引梁补强板失效机理分析[J].热加工工艺,2012,(23):208-211.
[4]张乐乐,李培,崔进.基于整体-局部方法的焊接构架承载能力的分析[J].铁道学报,2011,(8):33-38.
[5]谭莹,陈明,曹标,等.地铁列车转向架断裂原因分析[J].理化检验(物理分册),2002,(8):349-351.
[6]熊建武,周进.变形铝合金在轨道车辆中的应用[J].企业技术开发,2007,(11):18-19.
[7]吴云兴,戴静敏.车辆用铝合金的性能及其应用（上）[J].铁道车辆,1994,(9):14-19.
[8]吴云兴,戴静敏.车辆用铝合金的性能及其应用（下）[J].铁道车辆,1994,(10):19-24.
[9]户取征二郎,高魁源.日本铝合金车辆的最新技术与发展趋势[J].国外铁道车辆,2002,(2):7-11.
[10]徐贵宝,沈本瑜.高强度铸铝合金在高速列车转向架上的应用[J].机车车辆工艺,1997,(6):1-4.
[11]戴静敏.高速列车用大型挤压铝型材[J].轻合金加工技术,1995,(5):2-7.
[12]刘静安.铝材在铁道车辆中的应用(开发铝材新品种·扩大铝材新用途·拓宽铝材新市场系列文章之十二)[J].轻合金加工技术,1993,(6):5-9.
[13] Montandon J,王其利.车辆零部件的无损检测[J].国外铁道车辆,1984,(2):69-76.
[14]唐德尧,王平.共振解调技术在设备故障诊断与维修中的应用[J].制造业设计技术,2000,(5):44-45.
[15]郑中兴.关于火车轴的超声波探伤[J].无损探伤,2008,(5):11-13.
[16]秦传鑫,高静涛,王超,等.超声相控阵技术在列车轮辋探伤中的应用[J].铁路计算机应用,2010,(10):50-51.
[17]邓维礼,永远.超声波在轮轨材料中传播的数值模拟[J].西南交通大学学报,2012,(5):836-841.
[18]邹强,钱健清,陈昌华.列车车轮缺陷的超声波C扫描分析[J].物理测试,2012,(2):42-46.
[19]陈昌华,汤志贵,陈能进,等.列车车轮缺陷的超声波相控阵分析[J].物理测试,2012,(1):34-39.
[20]蒋齐密,史海滨,康宜华,等.列车轮对的智能化在役检测系统[J].机车车辆工艺,2000,(5):1-4.
[21] МалышEв С П,胥金荣.铁道车辆涡流探伤[J].国外铁道车辆,1991,(1):55-57.
[22]廉杰,陈金方.铁路客车轮对轴承滚柱的涡流探伤法[J].无损检测,1996,18(8):219-220.
[23]孙鸿祥.大型工业CT在摇枕、侧架无损检测中的应用[J].中国仪器仪表,2011,(10):49-52.
[24]肖永顺,胡海峰,陈志强,等.大型工业CT在机车关键部件无损检测中的应用[J]. CT理论与应用研究,2009,(3):72-78.
[25]张俊哲,戚克鹏,刘春海,等.高速列车变截面铸钢件的X射线数字成像检测[J].无损检测,2011,(12):66-68.
[26]国防科技工业无损检测人员资格鉴定与认证培训教材编审委员会.声发射检测[M].北京:机械工业出版社,2005:21-36.
[27]李孟源等.声发射检测及信号处理[M].北京:科学出版社,2010:21-29.
[28] Dukes R, Culpan E A. Acoustic Emission: Its Technique and Applications[J].Physical Science, Measurement and Instrumentation, Management andEducation-Reviews, IEEE Proceedings A,1984,131(4):241-251.
[29]国家质量技术监督局锅炉压力容器检测中心. GB/T18182-2000,金属压力容器声发射检测及结果评价方法[S].国家质检总局,2000.
[30]合肥通用机械研究所. JB/T6916-1993,在役高压气瓶声发射检测和评定方法[S].行业标准-机械,1993.
[31]中国特种设备检测研究中心,大庆石油学院,北京科海恒生科技有限公司,中石化股份有限公司镇海分公司,等. JB/T10764-2007,常压金属储罐声发射检测及评价方法[S].行业标准-机械,2007.
[32]沈功田,耿荣生,刘时风.声发射源定位技术[J].无损检测,2002,24(3):114-118.
[33]林明春,辛爱华,高金杰,等.罐底声发射在线检测及其可靠性验证[J].油气储运,2010,(10):776-779.
[34] Lee H S, Yoon J H, Park J S, et al. A Study on Failure Characteristic ofSpherical Pressure Vessel[J]. Journal of Materials Processing Technology,2005,164:882-888.
[35] Lin S, Jia X L, Sun H J, et al. Thermo-Mechanical Properties of FilamentWound Cfrp Vessel Under Hydraulic and Atmospheric Fatigue Cycling[J].Composites Part B-Engineering,2013,46:227-233.
[36] Kwon J R, Lyu G J, Lee T H, et al. Acoustic Emission Testing of RepairedStorage Tank[J]. International Journal of Pressure Vessels and Piping,2001,78(5):373-378.
[37] Choi Y C, Park J H, Choi K S. An Impact Source Localization Technique fora Nuclear Power Plant by Using Sensors of Different Types[J]. ISATransactions,2011,50(1):111-118.
[38]李国华,吴淼.现代无损检测与评价[M].北京:化学工业出版社,2009:304-352.
[39] Bhat C, Bhat M R, Murthy C. Acoustic Emission Characterization of FailureModes in Composites with ANN[J]. Composite Structures,2003,61(3):213-220.
[40]姜长泓.轨道车辆轮轴故障检测系统研究[D].长春:吉林大学博士学位论文,2006,71-94.
[41]邓艾东,赵力,包永强,等.噪声环境下基于小波熵的声发射识别[J].东南大学学报(自然科学版),2009,(6):1151-1155.
[42]李伟,蒋鹏.基于独立分量分析的声发射信号分离方法[J].压力容器,2008,25(5):10-12.
[43]殷冬萌.木塑复合材料缺陷及损伤的声发射信号特征分析及神经网络模式识别[D].南京:南京农业大学硕士学位论文,2007,17-49.
[44] Bourchak M, Farrow I R, Bond I P, et al. Acoustic Emission Energy as aFatigue Damage Parameter for CFRP Composites[J]. International Journal ofFatigue,2007,29(3):457-470.
[45] Sasikumar T, RajendraBoopathy S, Usha K M, et al. Failure StrengthPrediction of Unidirectional Tensile Coupons Using Acoustic Emission PeakAmplitude and Energy Parameter with Artificial Neural Networks[J].Composites Science and Technology,2009,69(7-8):1151-1155.
[46] Drummond G, Watson J F, Acarnley P P. Acoustic Emission From WireRopes During Proof Load and Fatigue Testing[J]. NDT&E International,2007,40(1):94-101.
[47] Hoang T D, Herbelot C, Imad A. Rupture and Damage Mechanism Analysisof a Bolted Assembly Using Coupling Techniques Between AE and DIC[J].Engineering Structures,2010,32(9):2793-2803.
[48] Guo Y B, Ammula S C. Real-Time Acoustic Emission Monitoring forSurface Damage in Hard Machining[J]. International Journal of MachineTools&Manufacture,2005,45(14):1622-1627.
[49] Elforjani M, Mba D. Accelerated Natural Fault Diagnosis in Slow SpeedBearings with Acoustic Emission[J]. Engineering Fracture Mechanics,2010,77(1):112-127.
[50] Morgan B C, Tilley R. Inspection of Power Plant Headers Utilizing AcousticEmission Monitoring[J]. NDT&E International,1999,32(3):167-175.
[51] Aggelis D G, Soulioti D V, Sapouridis N, et al. Acoustic EmissionCharacterization of the Fracture Process in Fibre Reinforced Concrete[J].Construction and Building Materials,2011,25(11):4126-4131.
[52] Szmechta M, Boczar T, Fracz P. Frequency and Time-Frequency Analysis ofAcoustic Cavitation Noise in Insulating Oils[J]. Acta Physica Polonica A,2011,120(4):744-747.
[53] Chen X Z, Li B Z. Acoustic Emission Method for Tool Condition MonitoringBased on Wavelet Analysis[J]. International Journal of AdvancedManufacturing Technology,2007,33(9-10):968-976.
[54] Qi G, Barhorst A, Hashemi J, et al. Discrete Wavelet Decomposition ofAcoustic Emission Signals from Carbon-Fiber-Reinforced Composites[J].Composites Science and Technology,1997,57(4):389-403.
[55] Yang L, Zhou Y C, Mao W G, et al. Real-Time Acoustic Emission TestingBased on Wavelet Transform for The Failure Process of Thermal BarrierCoatings[J]. Applied Physics Letters,2008,93(23190623).
[56] Sasikumar T, Rajendraboopathy S, Usha K M, et al. Artificial NeuralNetwork Prediction of Ultimate Strength of Unidirectional T-300/914Tensile Specimens Using Acoustic Emission Response[J]. Journal ofNondestructive Evaluation,2008,27(4):127-133.
[57] Kwak J S, Ha M K. Neural Network Approach for Diagnosis of GrindingOperation by Acoustic Emission and Power Signals[J]. Journal of MaterialsProcessing Technology,2004,147(1):65-71.
[58] Kim J K, Lee M C. Real-Time Diagnostic System Using Acoustic Emissionfor a Cylinder Liner in a Large Two-Stroke Diesel Engine[J]. InternationalJournal of Precision Engineering and Manufacturing,2009,10(3):51-58.
[59] Saxena A, Saad A. Evolving an Artificial Neural Network Classifier forCondition Monitoring of Rotating Mechanical Systems[J]. Applied SoftComputing,2007,7(1):441-454.
[60] Hessel G, Schmitt W, Van Der Vorst K, et al. A Neutral Network Approachfor Acoustic Leak Monitoring in the Vver-440Pressure Vessel Head[J].Progress in Nuclear Energy,1999,34(3):173-183.
[61] Lee M R, Lee J H, Kim J T. Condition Monitoring of a Nuclear Power PlantCheck Valve Based on Acoustic Emission and a Neural Network[J]. Journalof Pressure Vessel Technology-Transactions of the ASME,2005,127(3):230-236.
[62] Yella S, Gupta N K, Dougherty M S. Comparison of Pattern RecognitionTechniques for the Classification of Impact Acoustic Emissions[J].Transportation Research Part C-Emerging Technologies,2007,15(6):345-360.
[63] Rippengill S, Worden K, Holford K M, et al. Automatic Classification ofAcoustic Emission Patterns[J]. Strain,2003,39(1):31-41.
[64] Cao Z, Wang B F, Wang K M, et al. Chemical Acoustic Emissions From GasEvolution Processes Recorded by a Piezoelectric Transducer[J]. Sensors andActuators B-Chemical,1998,50(1):27-37.
[65] Shaira M, Godin N, Guy P, et al. Evaluation of the Strain-InducedMartensitic Transformation by Acoustic Emission Monitoring in304LAustenitic Stainless Steel: Identification of the AE Signature of theMartensitic Transformation and Power-Law Statistics[J]. Materials Scienceand Engineering A-Structural Materials Properties Microstructure andProcessing,2008,492(1-2):392-399.
[66]李丽菲,沈功田,张万岭,等.低碳钢氢致开裂声发射信号分析与模式识别[J].无损检测,2009,(10):773-776.
[67]徐锋,刘云飞.基于EMD的胶合板损伤声发射信号特征提取及神经网络模式识别[J].振动与冲击,2012,31(15):30-35.
[68] Yang B L, Zhuang X M, Zhang T H, et al. Damage Mode Identification forthe Clustering Analysis of AE Signals in Thermoplastic Composites[J].Journal of Nondestructive Evaluation,2009,28(3-4):163-168.
[69] Pappas Y Z, Kostopoulos V. Toughness Characterization and AcousticEmission Monitoring of a2-D Carbon/Carbon Composite[J]. EngineeringFracture Mechanics,2001,68(14):1557-1573.
[70] Kostopouios V, Loutas T, Dassios K. Fracture Behavior and DamageMechanisms Identification of SiC/Glass Ceramic Composites Using AEMonitoring[J]. Composites Science and Technology,2007,67(7-8):1740-1746.
[71] Kalogiannakis G, Quintelier J, De Baets P, et al. Identification of WearMechanisms of Glass/Polyester Composites by Means of AcousticEmission[J]. Wear,2008,264(3-4):235-244.
[72] Sause M, Haider F, Horn S. Quantification of Metallic Coating Failure onCarbon Fiber Reinforced Plastics Using Acoustic Emission[J]. Surface&Coatings Technology,2009,204(3):300-308.
[73]王军,殷冬萌,刘云飞.新型木塑材料缺陷及损伤的声发射信号分析[J].声学技术,2008,27(4):497-500.
[74]王健,金周庚,刘哲军. C/E复合材料声发射信号小波分析及人工神经网络模式识别[J].宇航材料工艺,2001,31(1):49-57.
[75] Salazar A, Vergara L, Llinares R. Learning Material Defect Patterns bySeparating Mixtures of Independent Component Analyzers From NDT SonicSignals[J]. Mechanical Systems and Signal Processing,2010,24(6):1870-1886.
[76]何沿江,齐明侠,罗红梅.基于ICA和SVM的滚动轴承声发射故障诊断技术[J].振动与冲击,2008,27(3):150-153.
[77]刘国华,黄平捷,龚翔,等.基于分形维和独立分量分析的声发射特征提取[J].华南理工大学学报（自然科学版）,2008,36(1):76-80.
[78] Biancohni M E, Brutti C, Paparo G, et al. Fatigue Cracks Nucleation on Steel,Acoustic Emission and Fractal Analysis[J]. International Journal of Fatigue,2006,28(12):1820-1825.
[79] Piotrkowski R, Castro E, Gallego A. Wavelet Power, Entropy andBispectrum Applied to AE Signals for Damage Identification and Evaluationof Corroded Galvanized Steel[J]. Mechanical Systems and Signal Processing,2009,23(2):432-445.
[80]刘国华,黄平捷,杨金泉,等.基于高阶谱的混凝土材料断裂声发射特征提取[J].吉林大学学报(工学版),2009,39(3):804-808.
[81]薛华.高速列车用A6N01S和A7N01S铝合金焊接接头疲劳裂纹扩展速率研究[D].天津:天津大学学位论文,2007,10-20.
[82]李刚卿,邢立伟,郑浩敏,等.高速列车制造焊接技术应用展望[J].焊接,2011,(5):14-19.
[83]杨尚磊,孙文,孟立春,等.机车车辆A7N01铝合金的MIG焊接[C]:2008轻金属与高强材料焊接国际论坛,北京,2008:289-293.
[84]路浩,刘雪松,孟立春,等.高速列车车体服役状态残余应力超声波法无损测量及验证[J].焊接学报,2009,30(4):81-83.
[85]高锷君,张泉林.钢件表面裂纹深度的定量电测[J].无锡轻工业学院学报,1992,11(3):247-252.
[86]侯贵仓,常小榕.疲劳裂纹电位法测量研究[J].燃气涡轮试验与研究,2008,21(4):38-41.
[87]王亮,丁传富.高温下直流电位法测量裂纹长度的应用[J].航空材料学报,2006,26(3):359-360.
[88]王增勇,余波,孙朝明,等.电位法测试导体表面裂纹深度研究[J].无损检测,2007,29(7):404-406.
[89]徐励.复型技术在小疲劳裂纹测试中的应用[J].物理测试,1990,(6):50-51.
[90] Shi Z. Studies on Quantitative Acoustic Emission with Applications toMaterial Fatigue Testing[D]. United States: Georgia Institute of Technology,2001,69-90.
[91] Daniel I M, Luo J J, Sifniotopoulos C G, et al. Acoustic Emission Monitoringof Fatigue Damage in Metals[J]. Review of Progress in QuantitativeNondestructive Evaluation,1997,16(A&B):451-458.
[92]贺玲,吴玲达,蔡益朝.高维空间中数据的相似性度量[J].数学的实践与认识,2006,36(9):189-194.
[93]李海林,郭崇慧.基于多维形态特征表示的时间序列相似性度量[J].系统工程理论与实践,2013,993-1004.
[94]谢明霞,郭建忠,张海波,等.高维数据相似性度量方法研究[J].计算机工程与科学,2010,32(5):92-96.
[95]胡广书.数字信号处理—理论、算法与实现(第二版)[M].北京:清华大学出版社,2009:55-99.
[96] Torrence C, Compo G P. A Practical Guide to Wavelet Analysis[J]. Bulletinof the American Meteorological Society,1998,79(1):61-78.
[97] Daubechies I. The Wavelet Transform, Time-Frequency Localization andSignal Analysis[J]. IEEE Transactions on Information Theory,1990,36(5):961-1005.
[98] Peng Z K, Chu F L. Application of The Wavelet Transform in MachineCondition Monitoring and Fault Diagnostics: A Review with Bibliography[J].Mechanical Systems and Signal Processing,2004,18(2):199-221.
[99]王潜龙,冯全科,屈展,等.基于声发射与小波包理论的压力管道泄漏检测[J].西安交通大学学报,2003,37(5):515-518.
[100]廖传军,李学军,刘德顺.小波再分配尺度谱在声发射信号特征提取中的应用[J].机械工程学报,2009,45(2):273-279.
[101]赵元喜,胥永刚,高立新,等.基于谐波小波包和BP神经网络的滚动轴承声发射故障模式识别技术[J].振动与冲击,2010,29(10):162-165.
[102]李学军,廖传军,褚福磊.适于声发射信号故障特征提取的小波函数[J].机械工程学报,2008,44(3):177-181.
[103]唐向宏,李齐良.时频分析与小波变换[M].北京:科学出版社,2008:221-228.
[104]杨富生.小波变换的工程分析与应用[M].北京:科学出版社,2001:245-259.
[105]张德丰. MATLAB小波分析[M].北京:机械工业出版社,2009:254-271.
[106]葛哲学.小波分析理论与MATLAB R2007实现[M].北京:电子工业出版社,2007:109-117.
[107]齐敏,李大健,郝重阳.模式识别导论[M].北京:清华大学出版社,2009:127-148.
[108]孙即祥等.现代模式识别[M].长沙:国防科技大学出版社,2002:190-241.
[109]师汉民,陈吉红.人工神经网络及其在机械工程领域中的应用[J].中国机械工程,1997,8(2):5-10.
[110]王学武,谭得健.神经网络的应用与发展趋势[J].计算机工程与应用,2003,39(3):98-100,113.
[111]袁曾任.人工神经元网络及其应用[M].南宁：广西科学技术出版社，1999:66-131.
[112]马锐.人工神经网络原理[M].北京:机械工业出版社，2010:45-66.
[113]戚德虎. BP神经网络的设计[J].计算机工程与设计,1998,19(2):48-50.
[114]丛爽,向微. BP网络结构、参数及训练方法的设计与选择[J].计算机工程,2001,27(10):36-38.
[115]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,2005:69-90.
[116]王贇松,许洪国.快速收敛的BP神经网络算法[J].吉林大学学报(工学版),2003,33(4):79-84.
[2]牧野一成,蔡千华.车辆隐性裂纹的检查方法[J].国外机车车辆工艺,2009,(2):40-43.
[3]周弋琳,王晓敏,马佳,等.高速列车牵引梁补强板失效机理分析[J].热加工工艺,2012,(23):208-211.
[4]张乐乐,李培,崔进.基于整体-局部方法的焊接构架承载能力的分析[J].铁道学报,2011,(8):33-38.
[5]谭莹,陈明,曹标,等.地铁列车转向架断裂原因分析[J].理化检验(物理分册),2002,(8):349-351.
[6]熊建武,周进.变形铝合金在轨道车辆中的应用[J].企业技术开发,2007,(11):18-19.
[7]吴云兴,戴静敏.车辆用铝合金的性能及其应用（上）[J].铁道车辆,1994,(9):14-19.
[8]吴云兴,戴静敏.车辆用铝合金的性能及其应用（下）[J].铁道车辆,1994,(10):19-24.
[9]户取征二郎,高魁源.日本铝合金车辆的最新技术与发展趋势[J].国外铁道车辆,2002,(2):7-11.
[10]徐贵宝,沈本瑜.高强度铸铝合金在高速列车转向架上的应用[J].机车车辆工艺,1997,(6):1-4.
[11]戴静敏.高速列车用大型挤压铝型材[J].轻合金加工技术,1995,(5):2-7.
[12]刘静安.铝材在铁道车辆中的应用(开发铝材新品种·扩大铝材新用途·拓宽铝材新市场系列文章之十二)[J].轻合金加工技术,1993,(6):5-9.
[13] Montandon J,王其利.车辆零部件的无损检测[J].国外铁道车辆,1984,(2):69-76.
[14]唐德尧,王平.共振解调技术在设备故障诊断与维修中的应用[J].制造业设计技术,2000,(5):44-45.
[15]郑中兴.关于火车轴的超声波探伤[J].无损探伤,2008,(5):11-13.
[16]秦传鑫,高静涛,王超,等.超声相控阵技术在列车轮辋探伤中的应用[J].铁路计算机应用,2010,(10):50-51.
[17]邓维礼,永远.超声波在轮轨材料中传播的数值模拟[J].西南交通大学学报,2012,(5):836-841.
[18]邹强,钱健清,陈昌华.列车车轮缺陷的超声波C扫描分析[J].物理测试,2012,(2):42-46.
[19]陈昌华,汤志贵,陈能进,等.列车车轮缺陷的超声波相控阵分析[J].物理测试,2012,(1):34-39.
[20]蒋齐密,史海滨,康宜华,等.列车轮对的智能化在役检测系统[J].机车车辆工艺,2000,(5):1-4.
[21] МалышEв С П,胥金荣.铁道车辆涡流探伤[J].国外铁道车辆,1991,(1):55-57.
[22]廉杰,陈金方.铁路客车轮对轴承滚柱的涡流探伤法[J].无损检测,1996,18(8):219-220.
[23]孙鸿祥.大型工业CT在摇枕、侧架无损检测中的应用[J].中国仪器仪表,2011,(10):49-52.
[24]肖永顺,胡海峰,陈志强,等.大型工业CT在机车关键部件无损检测中的应用[J]. CT理论与应用研究,2009,(3):72-78.
[25]张俊哲,戚克鹏,刘春海,等.高速列车变截面铸钢件的X射线数字成像检测[J].无损检测,2011,(12):66-68.
[26]国防科技工业无损检测人员资格鉴定与认证培训教材编审委员会.声发射检测[M].北京:机械工业出版社,2005:21-36.
[27]李孟源等.声发射检测及信号处理[M].北京:科学出版社,2010:21-29.
[28] Dukes R, Culpan E A. Acoustic Emission: Its Technique and Applications[J].Physical Science, Measurement and Instrumentation, Management andEducation-Reviews, IEEE Proceedings A,1984,131(4):241-251.
[29]国家质量技术监督局锅炉压力容器检测中心. GB/T18182-2000,金属压力容器声发射检测及结果评价方法[S].国家质检总局,2000.
[30]合肥通用机械研究所. JB/T6916-1993,在役高压气瓶声发射检测和评定方法[S].行业标准-机械,1993.
[31]中国特种设备检测研究中心,大庆石油学院,北京科海恒生科技有限公司,中石化股份有限公司镇海分公司,等. JB/T10764-2007,常压金属储罐声发射检测及评价方法[S].行业标准-机械,2007.
[32]沈功田,耿荣生,刘时风.声发射源定位技术[J].无损检测,2002,24(3):114-118.
[33]林明春,辛爱华,高金杰,等.罐底声发射在线检测及其可靠性验证[J].油气储运,2010,(10):776-779.
[34] Lee H S, Yoon J H, Park J S, et al. A Study on Failure Characteristic ofSpherical Pressure Vessel[J]. Journal of Materials Processing Technology,2005,164:882-888.
[35] Lin S, Jia X L, Sun H J, et al. Thermo-Mechanical Properties of FilamentWound Cfrp Vessel Under Hydraulic and Atmospheric Fatigue Cycling[J].Composites Part B-Engineering,2013,46:227-233.
[36] Kwon J R, Lyu G J, Lee T H, et al. Acoustic Emission Testing of RepairedStorage Tank[J]. International Journal of Pressure Vessels and Piping,2001,78(5):373-378.
[37] Choi Y C, Park J H, Choi K S. An Impact Source Localization Technique fora Nuclear Power Plant by Using Sensors of Different Types[J]. ISATransactions,2011,50(1):111-118.
[38]李国华,吴淼.现代无损检测与评价[M].北京:化学工业出版社,2009:304-352.
[39] Bhat C, Bhat M R, Murthy C. Acoustic Emission Characterization of FailureModes in Composites with ANN[J]. Composite Structures,2003,61(3):213-220.
[40]姜长泓.轨道车辆轮轴故障检测系统研究[D].长春:吉林大学博士学位论文,2006,71-94.
[41]邓艾东,赵力,包永强,等.噪声环境下基于小波熵的声发射识别[J].东南大学学报(自然科学版),2009,(6):1151-1155.
[42]李伟,蒋鹏.基于独立分量分析的声发射信号分离方法[J].压力容器,2008,25(5):10-12.
[43]殷冬萌.木塑复合材料缺陷及损伤的声发射信号特征分析及神经网络模式识别[D].南京:南京农业大学硕士学位论文,2007,17-49.
[44] Bourchak M, Farrow I R, Bond I P, et al. Acoustic Emission Energy as aFatigue Damage Parameter for CFRP Composites[J]. International Journal ofFatigue,2007,29(3):457-470.
[45] Sasikumar T, RajendraBoopathy S, Usha K M, et al. Failure StrengthPrediction of Unidirectional Tensile Coupons Using Acoustic Emission PeakAmplitude and Energy Parameter with Artificial Neural Networks[J].Composites Science and Technology,2009,69(7-8):1151-1155.
[46] Drummond G, Watson J F, Acarnley P P. Acoustic Emission From WireRopes During Proof Load and Fatigue Testing[J]. NDT&E International,2007,40(1):94-101.
[47] Hoang T D, Herbelot C, Imad A. Rupture and Damage Mechanism Analysisof a Bolted Assembly Using Coupling Techniques Between AE and DIC[J].Engineering Structures,2010,32(9):2793-2803.
[48] Guo Y B, Ammula S C. Real-Time Acoustic Emission Monitoring forSurface Damage in Hard Machining[J]. International Journal of MachineTools&Manufacture,2005,45(14):1622-1627.
[49] Elforjani M, Mba D. Accelerated Natural Fault Diagnosis in Slow SpeedBearings with Acoustic Emission[J]. Engineering Fracture Mechanics,2010,77(1):112-127.
[50] Morgan B C, Tilley R. Inspection of Power Plant Headers Utilizing AcousticEmission Monitoring[J]. NDT&E International,1999,32(3):167-175.
[51] Aggelis D G, Soulioti D V, Sapouridis N, et al. Acoustic EmissionCharacterization of the Fracture Process in Fibre Reinforced Concrete[J].Construction and Building Materials,2011,25(11):4126-4131.
[52] Szmechta M, Boczar T, Fracz P. Frequency and Time-Frequency Analysis ofAcoustic Cavitation Noise in Insulating Oils[J]. Acta Physica Polonica A,2011,120(4):744-747.
[53] Chen X Z, Li B Z. Acoustic Emission Method for Tool Condition MonitoringBased on Wavelet Analysis[J]. International Journal of AdvancedManufacturing Technology,2007,33(9-10):968-976.
[54] Qi G, Barhorst A, Hashemi J, et al. Discrete Wavelet Decomposition ofAcoustic Emission Signals from Carbon-Fiber-Reinforced Composites[J].Composites Science and Technology,1997,57(4):389-403.
[55] Yang L, Zhou Y C, Mao W G, et al. Real-Time Acoustic Emission TestingBased on Wavelet Transform for The Failure Process of Thermal BarrierCoatings[J]. Applied Physics Letters,2008,93(23190623).
[56] Sasikumar T, Rajendraboopathy S, Usha K M, et al. Artificial NeuralNetwork Prediction of Ultimate Strength of Unidirectional T-300/914Tensile Specimens Using Acoustic Emission Response[J]. Journal ofNondestructive Evaluation,2008,27(4):127-133.
[57] Kwak J S, Ha M K. Neural Network Approach for Diagnosis of GrindingOperation by Acoustic Emission and Power Signals[J]. Journal of MaterialsProcessing Technology,2004,147(1):65-71.
[58] Kim J K, Lee M C. Real-Time Diagnostic System Using Acoustic Emissionfor a Cylinder Liner in a Large Two-Stroke Diesel Engine[J]. InternationalJournal of Precision Engineering and Manufacturing,2009,10(3):51-58.
[59] Saxena A, Saad A. Evolving an Artificial Neural Network Classifier forCondition Monitoring of Rotating Mechanical Systems[J]. Applied SoftComputing,2007,7(1):441-454.
[60] Hessel G, Schmitt W, Van Der Vorst K, et al. A Neutral Network Approachfor Acoustic Leak Monitoring in the Vver-440Pressure Vessel Head[J].Progress in Nuclear Energy,1999,34(3):173-183.
[61] Lee M R, Lee J H, Kim J T. Condition Monitoring of a Nuclear Power PlantCheck Valve Based on Acoustic Emission and a Neural Network[J]. Journalof Pressure Vessel Technology-Transactions of the ASME,2005,127(3):230-236.
[62] Yella S, Gupta N K, Dougherty M S. Comparison of Pattern RecognitionTechniques for the Classification of Impact Acoustic Emissions[J].Transportation Research Part C-Emerging Technologies,2007,15(6):345-360.
[63] Rippengill S, Worden K, Holford K M, et al. Automatic Classification ofAcoustic Emission Patterns[J]. Strain,2003,39(1):31-41.
[64] Cao Z, Wang B F, Wang K M, et al. Chemical Acoustic Emissions From GasEvolution Processes Recorded by a Piezoelectric Transducer[J]. Sensors andActuators B-Chemical,1998,50(1):27-37.
[65] Shaira M, Godin N, Guy P, et al. Evaluation of the Strain-InducedMartensitic Transformation by Acoustic Emission Monitoring in304LAustenitic Stainless Steel: Identification of the AE Signature of theMartensitic Transformation and Power-Law Statistics[J]. Materials Scienceand Engineering A-Structural Materials Properties Microstructure andProcessing,2008,492(1-2):392-399.
[66]李丽菲,沈功田,张万岭,等.低碳钢氢致开裂声发射信号分析与模式识别[J].无损检测,2009,(10):773-776.
[67]徐锋,刘云飞.基于EMD的胶合板损伤声发射信号特征提取及神经网络模式识别[J].振动与冲击,2012,31(15):30-35.
[68] Yang B L, Zhuang X M, Zhang T H, et al. Damage Mode Identification forthe Clustering Analysis of AE Signals in Thermoplastic Composites[J].Journal of Nondestructive Evaluation,2009,28(3-4):163-168.
[69] Pappas Y Z, Kostopoulos V. Toughness Characterization and AcousticEmission Monitoring of a2-D Carbon/Carbon Composite[J]. EngineeringFracture Mechanics,2001,68(14):1557-1573.
[70] Kostopouios V, Loutas T, Dassios K. Fracture Behavior and DamageMechanisms Identification of SiC/Glass Ceramic Composites Using AEMonitoring[J]. Composites Science and Technology,2007,67(7-8):1740-1746.
[71] Kalogiannakis G, Quintelier J, De Baets P, et al. Identification of WearMechanisms of Glass/Polyester Composites by Means of AcousticEmission[J]. Wear,2008,264(3-4):235-244.
[72] Sause M, Haider F, Horn S. Quantification of Metallic Coating Failure onCarbon Fiber Reinforced Plastics Using Acoustic Emission[J]. Surface&Coatings Technology,2009,204(3):300-308.
[73]王军,殷冬萌,刘云飞.新型木塑材料缺陷及损伤的声发射信号分析[J].声学技术,2008,27(4):497-500.
[74]王健,金周庚,刘哲军. C/E复合材料声发射信号小波分析及人工神经网络模式识别[J].宇航材料工艺,2001,31(1):49-57.
[75] Salazar A, Vergara L, Llinares R. Learning Material Defect Patterns bySeparating Mixtures of Independent Component Analyzers From NDT SonicSignals[J]. Mechanical Systems and Signal Processing,2010,24(6):1870-1886.
[76]何沿江,齐明侠,罗红梅.基于ICA和SVM的滚动轴承声发射故障诊断技术[J].振动与冲击,2008,27(3):150-153.
[77]刘国华,黄平捷,龚翔,等.基于分形维和独立分量分析的声发射特征提取[J].华南理工大学学报（自然科学版）,2008,36(1):76-80.
[78] Biancohni M E, Brutti C, Paparo G, et al. Fatigue Cracks Nucleation on Steel,Acoustic Emission and Fractal Analysis[J]. International Journal of Fatigue,2006,28(12):1820-1825.
[79] Piotrkowski R, Castro E, Gallego A. Wavelet Power, Entropy andBispectrum Applied to AE Signals for Damage Identification and Evaluationof Corroded Galvanized Steel[J]. Mechanical Systems and Signal Processing,2009,23(2):432-445.
[80]刘国华,黄平捷,杨金泉,等.基于高阶谱的混凝土材料断裂声发射特征提取[J].吉林大学学报(工学版),2009,39(3):804-808.
[81]薛华.高速列车用A6N01S和A7N01S铝合金焊接接头疲劳裂纹扩展速率研究[D].天津:天津大学学位论文,2007,10-20.
[82]李刚卿,邢立伟,郑浩敏,等.高速列车制造焊接技术应用展望[J].焊接,2011,(5):14-19.
[83]杨尚磊,孙文,孟立春,等.机车车辆A7N01铝合金的MIG焊接[C]:2008轻金属与高强材料焊接国际论坛,北京,2008:289-293.
[84]路浩,刘雪松,孟立春,等.高速列车车体服役状态残余应力超声波法无损测量及验证[J].焊接学报,2009,30(4):81-83.
[85]高锷君,张泉林.钢件表面裂纹深度的定量电测[J].无锡轻工业学院学报,1992,11(3):247-252.
[86]侯贵仓,常小榕.疲劳裂纹电位法测量研究[J].燃气涡轮试验与研究,2008,21(4):38-41.
[87]王亮,丁传富.高温下直流电位法测量裂纹长度的应用[J].航空材料学报,2006,26(3):359-360.
[88]王增勇,余波,孙朝明,等.电位法测试导体表面裂纹深度研究[J].无损检测,2007,29(7):404-406.
[89]徐励.复型技术在小疲劳裂纹测试中的应用[J].物理测试,1990,(6):50-51.
[90] Shi Z. Studies on Quantitative Acoustic Emission with Applications toMaterial Fatigue Testing[D]. United States: Georgia Institute of Technology,2001,69-90.
[91] Daniel I M, Luo J J, Sifniotopoulos C G, et al. Acoustic Emission Monitoringof Fatigue Damage in Metals[J]. Review of Progress in QuantitativeNondestructive Evaluation,1997,16(A&B):451-458.
[92]贺玲,吴玲达,蔡益朝.高维空间中数据的相似性度量[J].数学的实践与认识,2006,36(9):189-194.
[93]李海林,郭崇慧.基于多维形态特征表示的时间序列相似性度量[J].系统工程理论与实践,2013,993-1004.
[94]谢明霞,郭建忠,张海波,等.高维数据相似性度量方法研究[J].计算机工程与科学,2010,32(5):92-96.
[95]胡广书.数字信号处理—理论、算法与实现(第二版)[M].北京:清华大学出版社,2009:55-99.
[96] Torrence C, Compo G P. A Practical Guide to Wavelet Analysis[J]. Bulletinof the American Meteorological Society,1998,79(1):61-78.
[97] Daubechies I. The Wavelet Transform, Time-Frequency Localization andSignal Analysis[J]. IEEE Transactions on Information Theory,1990,36(5):961-1005.
[98] Peng Z K, Chu F L. Application of The Wavelet Transform in MachineCondition Monitoring and Fault Diagnostics: A Review with Bibliography[J].Mechanical Systems and Signal Processing,2004,18(2):199-221.
[99]王潜龙,冯全科,屈展,等.基于声发射与小波包理论的压力管道泄漏检测[J].西安交通大学学报,2003,37(5):515-518.
[100]廖传军,李学军,刘德顺.小波再分配尺度谱在声发射信号特征提取中的应用[J].机械工程学报,2009,45(2):273-279.
[101]赵元喜,胥永刚,高立新,等.基于谐波小波包和BP神经网络的滚动轴承声发射故障模式识别技术[J].振动与冲击,2010,29(10):162-165.
[102]李学军,廖传军,褚福磊.适于声发射信号故障特征提取的小波函数[J].机械工程学报,2008,44(3):177-181.
[103]唐向宏,李齐良.时频分析与小波变换[M].北京:科学出版社,2008:221-228.
[104]杨富生.小波变换的工程分析与应用[M].北京:科学出版社,2001:245-259.
[105]张德丰. MATLAB小波分析[M].北京:机械工业出版社,2009:254-271.
[106]葛哲学.小波分析理论与MATLAB R2007实现[M].北京:电子工业出版社,2007:109-117.
[107]齐敏,李大健,郝重阳.模式识别导论[M].北京:清华大学出版社,2009:127-148.
[108]孙即祥等.现代模式识别[M].长沙:国防科技大学出版社,2002:190-241.
[109]师汉民,陈吉红.人工神经网络及其在机械工程领域中的应用[J].中国机械工程,1997,8(2):5-10.
[110]王学武,谭得健.神经网络的应用与发展趋势[J].计算机工程与应用,2003,39(3):98-100,113.
[111]袁曾任.人工神经元网络及其应用[M].南宁：广西科学技术出版社，1999:66-131.
[112]马锐.人工神经网络原理[M].北京:机械工业出版社，2010:45-66.
[113]戚德虎. BP神经网络的设计[J].计算机工程与设计,1998,19(2):48-50.
[114]丛爽,向微. BP网络结构、参数及训练方法的设计与选择[J].计算机工程,2001,27(10):36-38.
[115]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,2005:69-90.
[116]王贇松,许洪国.快速收敛的BP神经网络算法[J].吉林大学学报(工学版),2003,33(4):79-84.