基于多值域特征及数据融合的焊缝缺陷超声检测与识别
|
摘要
随着现代工业的不断发展，焊接构件在锅炉、压力容器、铁路、海洋造船、能源、航空航天等工业领域都得到了广泛的应用。目前对于工业领域中的在役焊接结构，常规的手动超声检测仍然被广泛采用。但是，常规超声检测方法无法实现检测数据的自动存储，检测效率低且容易发生漏检。尤其对于缺陷性质的识别一直是常规超声检测方法中的难题。常规超声检测无法实现缺陷三视投影图像的自动直观显示，对缺陷的识别诊断完全依靠检测者的经验，使得检测结果因人而异，这些都给实际的现场在役检测带来诸多不便。
针对常规手动超声检测中存在的问题，本文首先开发了一套基于视频图像定位的超声检测成像系统，该系统不但成本低廉、结构简单、便于携带，而且能够实现焊缝缺陷连续扫查，检测数据的自动存储，以及缺陷的三视投影成像，为后续的缺陷智能识别提供了可靠的数据。
利用开发的基于视频图像定位的超声检测成像系统对含有气孔、夹渣、裂纹、未焊透和未熔合五类实际焊接缺陷的对接焊缝试件进行了超声检测，实时存储了每个缺陷体的超声回波信号，并获得了缺陷的三视投影成像图，直观的给出了缺陷的位置、大小、分布和取向等形态分布特征，为缺陷特征值的提取提供了可靠的数据来源。采用人工智能方法进行缺陷的识别与判断，最关键的是获取能够反映不同缺陷类别的特征值。通过分析不同缺陷反射体的特性，从多值域的角度出发，分别在时域、频域、时频域、几何统计学和缺陷的位置形态上提取了用于缺陷智能识别的缺陷特征值，实现了实际焊接缺陷的多值域特征提取。
缺陷特征值是缺陷智能识别的关键，正确选择有效的特征量是保证识别系统具有良好的分类性能的前提。为此，本文构建了基于欧氏距离的特征值评价准则，对提取的所有缺陷特征值进行了评价与优化，获取了缺陷的最佳特征值子集，实现了特征空间的降维，为缺陷识别提供了有效的特征向量。
构建基于BP神经网络的智能化模式识别分类器，研究了基于缺陷超声信号特征与形态特征的多值域特征分类识别新方法，对五类实际焊接缺陷进行了智能识别。与常规的基于超声信号特征的缺陷识别结果相比，该方法充分利用了缺陷的位置形态信息，有效地提高了缺陷的识别率。
以Dempster-Shafer(D-S)证据理论为基础，研究了超声检测中缺陷识别的双探头源数据融合新方法。该方法通过对探头信息的融合，可以更准确、更全面地获得被检缺陷的信息。进一步构建了基于BP神经网络与D-S证据理论联合的双探头源缺陷智能识别分类器，实现了五类实际焊接缺陷的智能识别。与单一探头数据下的识别结果相比，该方法融合了双探头源的互补信息，提高了缺陷信息的利用率，降低了单一探头识别系统的不确定性，从而进一步提高了缺陷识别的可靠性和准确率。
With the development of modern industry, welded structures have been widelyused in boiler, pressure vessel, rail, marine, shipbuilding, energy, aerospace and otherindustrial fields. At present, conventional manual ultrasonic testing was widely usedto detect the welded structure in service. However, conventional ultrasonic testingmethod cannot acquire the continuous echoes of flaw, and the data cannot be storedautomatically. Thus this method is inefficient, and the flaw is easy to be missedduring the detection process. Furthermore, flaw recognition is still a difficult problemto be resolved in conventional ultrasonic testing method. The three-view projectionimage of flaw cannot be illustrated automatically and intuitively. So the recognitionand diagnosis of flaw completely relies on the experience of the operator, whichmakes the detection result vary from person to person. Thus, there are many issuesfor detecting welded structures in service by conventional ultrasonic testing.
To solve the problems which exist in conventional ultrasonic testing, a manualultrasonic testing system based on video image positioning was developed in thispaper. This system not only has many characters of cheap cost, simple structure andconvenient to carry, but also can achieve a continuous scanning of weld flaw, theautomatic storage of data and the three-view projection imaging of weld flaw, whichprovides the reliable data for the intelligent recognition of weld flaw.
There are many butt weld specimens, which contain five types of typical weldflaws of porosity, slag, crack, lack of penetration and lack of fusion. They wereinspected by this developed system, and ultrasonic echoes reflected from each defectwere stored in real time. Then the three-view projection image of weld flaw wasshowed, and the location, size and distribution of weld flaw were characterizedconveniently and intuitively, which provides a reliable data source for featureextraction of weld flaw. For intelligent recognition of defect by using artificialintelligence method, the most critical thing is to obtain the feature which can reflectthe characteristic of different defects. By analyzing the characteristics of differentflaw reflectors, flaw features were extracted in time domain, frequency domain andtime-frequency domain. Furthermore, geometric features, statistical features andmorphological features were also extracted. Thus, the flaw features were extracted inmulti-domain in this paper.
Flaw feature plays an important role in intelligent recognition of weld flaw.Correct selection of efficient feature vector is necessary to ensure a goodperformance of classification for the recognition system. Thus, evaluation criterion based on Euclidean distance was constructed to evaluate and optimize the feature.Then the optimum feature subset was obtained, and the dimensionality reduction offeature space was brought out. The results provided efficient feature vectors for theflaw recognition.
Intelligent recognition classifier was constructed base on back propagation (BP)neural network. Then a new method of flaw recognition based on multi-feature ofultrasonic signal feature and morphological feature was studied. And it was applied toidentify the five types of weld flaws. This method made full use of the morphologicalinformation of weld flaw. Thus, compared to the conventional recognition resultbased on ultrasonic signal feature, the recognition rate of weld flaws was improvedeffectively.
Based on Dempster-Shafer (D-S) evidence theory, a new method of flawrecognition based on data fusion of dual-probe sensor was studied. More accurate andcomprehensive flaw information was obtained by the data fusion of dual-probeinformation. Then an intelligent pattern classifier based on BP neural network andD-S evidence theory was developed to carry out the flaw recognition of five types ofweld flaws. This method combined the complementary information of dual-probesensor, improved the utilization of defect information, and reduced the systematicuncertainty of single probe. Thus, compared to the recognition result based on singleprobe, the reliability and accuracy of flaw recognition was improved effectively.
针对常规手动超声检测中存在的问题，本文首先开发了一套基于视频图像定位的超声检测成像系统，该系统不但成本低廉、结构简单、便于携带，而且能够实现焊缝缺陷连续扫查，检测数据的自动存储，以及缺陷的三视投影成像，为后续的缺陷智能识别提供了可靠的数据。
利用开发的基于视频图像定位的超声检测成像系统对含有气孔、夹渣、裂纹、未焊透和未熔合五类实际焊接缺陷的对接焊缝试件进行了超声检测，实时存储了每个缺陷体的超声回波信号，并获得了缺陷的三视投影成像图，直观的给出了缺陷的位置、大小、分布和取向等形态分布特征，为缺陷特征值的提取提供了可靠的数据来源。采用人工智能方法进行缺陷的识别与判断，最关键的是获取能够反映不同缺陷类别的特征值。通过分析不同缺陷反射体的特性，从多值域的角度出发，分别在时域、频域、时频域、几何统计学和缺陷的位置形态上提取了用于缺陷智能识别的缺陷特征值，实现了实际焊接缺陷的多值域特征提取。
缺陷特征值是缺陷智能识别的关键，正确选择有效的特征量是保证识别系统具有良好的分类性能的前提。为此，本文构建了基于欧氏距离的特征值评价准则，对提取的所有缺陷特征值进行了评价与优化，获取了缺陷的最佳特征值子集，实现了特征空间的降维，为缺陷识别提供了有效的特征向量。
构建基于BP神经网络的智能化模式识别分类器，研究了基于缺陷超声信号特征与形态特征的多值域特征分类识别新方法，对五类实际焊接缺陷进行了智能识别。与常规的基于超声信号特征的缺陷识别结果相比，该方法充分利用了缺陷的位置形态信息，有效地提高了缺陷的识别率。
以Dempster-Shafer(D-S)证据理论为基础，研究了超声检测中缺陷识别的双探头源数据融合新方法。该方法通过对探头信息的融合，可以更准确、更全面地获得被检缺陷的信息。进一步构建了基于BP神经网络与D-S证据理论联合的双探头源缺陷智能识别分类器，实现了五类实际焊接缺陷的智能识别。与单一探头数据下的识别结果相比，该方法融合了双探头源的互补信息，提高了缺陷信息的利用率，降低了单一探头识别系统的不确定性，从而进一步提高了缺陷识别的可靠性和准确率。
With the development of modern industry, welded structures have been widelyused in boiler, pressure vessel, rail, marine, shipbuilding, energy, aerospace and otherindustrial fields. At present, conventional manual ultrasonic testing was widely usedto detect the welded structure in service. However, conventional ultrasonic testingmethod cannot acquire the continuous echoes of flaw, and the data cannot be storedautomatically. Thus this method is inefficient, and the flaw is easy to be missedduring the detection process. Furthermore, flaw recognition is still a difficult problemto be resolved in conventional ultrasonic testing method. The three-view projectionimage of flaw cannot be illustrated automatically and intuitively. So the recognitionand diagnosis of flaw completely relies on the experience of the operator, whichmakes the detection result vary from person to person. Thus, there are many issuesfor detecting welded structures in service by conventional ultrasonic testing.
To solve the problems which exist in conventional ultrasonic testing, a manualultrasonic testing system based on video image positioning was developed in thispaper. This system not only has many characters of cheap cost, simple structure andconvenient to carry, but also can achieve a continuous scanning of weld flaw, theautomatic storage of data and the three-view projection imaging of weld flaw, whichprovides the reliable data for the intelligent recognition of weld flaw.
There are many butt weld specimens, which contain five types of typical weldflaws of porosity, slag, crack, lack of penetration and lack of fusion. They wereinspected by this developed system, and ultrasonic echoes reflected from each defectwere stored in real time. Then the three-view projection image of weld flaw wasshowed, and the location, size and distribution of weld flaw were characterizedconveniently and intuitively, which provides a reliable data source for featureextraction of weld flaw. For intelligent recognition of defect by using artificialintelligence method, the most critical thing is to obtain the feature which can reflectthe characteristic of different defects. By analyzing the characteristics of differentflaw reflectors, flaw features were extracted in time domain, frequency domain andtime-frequency domain. Furthermore, geometric features, statistical features andmorphological features were also extracted. Thus, the flaw features were extracted inmulti-domain in this paper.
Flaw feature plays an important role in intelligent recognition of weld flaw.Correct selection of efficient feature vector is necessary to ensure a goodperformance of classification for the recognition system. Thus, evaluation criterion based on Euclidean distance was constructed to evaluate and optimize the feature.Then the optimum feature subset was obtained, and the dimensionality reduction offeature space was brought out. The results provided efficient feature vectors for theflaw recognition.
Intelligent recognition classifier was constructed base on back propagation (BP)neural network. Then a new method of flaw recognition based on multi-feature ofultrasonic signal feature and morphological feature was studied. And it was applied toidentify the five types of weld flaws. This method made full use of the morphologicalinformation of weld flaw. Thus, compared to the conventional recognition resultbased on ultrasonic signal feature, the recognition rate of weld flaws was improvedeffectively.
Based on Dempster-Shafer (D-S) evidence theory, a new method of flawrecognition based on data fusion of dual-probe sensor was studied. More accurate andcomprehensive flaw information was obtained by the data fusion of dual-probeinformation. Then an intelligent pattern classifier based on BP neural network andD-S evidence theory was developed to carry out the flaw recognition of five types ofweld flaws. This method combined the complementary information of dual-probesensor, improved the utilization of defect information, and reduced the systematicuncertainty of single probe. Thus, compared to the recognition result based on singleprobe, the reliability and accuracy of flaw recognition was improved effectively.
引文
[1]韩伟.无损检测技术现状及其新发展[J].可编程控制器与工厂自动化,2005,(1):121-123.
[2] Provan W J. Probabilistic Fracture Mechanics and Reliability[M]. Netherlands:Matinus Nijhoft Publishers,1986:39-42.
[3] Van D G M, Boogaard J. NDT Reliability a Way to Go[C]: Proceedings of theWorld Conference on Non-Destructive Testing, Sao Paulo, Brazil,1992:95-98.
[4]耿荣生.新千年的无损检测技术——从罗马会议看无损检测技术的发展方向[J].无损检测,2001,23(1):2-5.
[5] Ma H W, Zhang X H, Wei J. Research On an Ultrasonic NDT System forComplex Surface Parts[J]. Journal of Materials Processing Technology,2002,129(3):667-670.
[6]黄民,李功.焊缝超声无损检测中的缺陷智能识别方法[J].北京信息科技大学学报(自然科学版),2009,24(2):33-36.
[7]韩和平.焊缝缺陷深度及高度测定-G-I射线片三维检测仪[J].热力发电,1991,(4):1-6.
[8]袁易全.近代超声原理与应用[M].南京:南京大学出版社,1996:440-462.
[9]金长善.超声工程[M].哈尔滨:哈尔滨工业大学出版社,1989:105-125.
[10]史亦韦.超声检测[M].北京:机械工业出版社,2005:4-16.
[11]刘福顺,汤明.无损检测基础[M].北京:北京航空航天大学出版社,2002:86-120.
[12]沈建中.超声成象技术及其在无损检测中的应用[J].无损检测,1994,16(7):202-206.
[13]王云平.超声无损检测与评价的关键技术问题及其解决方案[J].煤矿机械,2008,(9):194-196.
[14] Stubbs D A, Zawada L P. Detection of Porosity in Glass Ceramic MatrixComposites Using an Ultrasonic Multiple-Gate C-Scan Technique[J].Materials Evaluation,1996,54(7):827-831.
[15]刘文霞,沈京玲,刘颖韬,等.玻璃钢蒙皮纸蜂窝材料的无损检测[J].无损检测,2009,31(12):990-992.
[16] Chertov A M, Maev R G, Severin F M. Acoustic Microscopy of InternalStructure of Resistance Spot Welds[J]. IEEE Transactions on Ultrasonics,Ferroelectrics, and Frequency Control,2007,54(8):1521-1529.
[17]王裕文,刘大文,侯成刚,等. JTUIS系列超声成像无损检测系统[J].低压电器,2000,(2):53-55.
[18] Debbouz O, Navai F. Nondestructive Testing of2017Aluminum Copper AlloyDiffusion Welded Joints by an Automatic Ultrasonic System[J]. MaterialsEvaluation,1999,57(12):1261-1267.
[19]曹宗杰,王久洪,薛锦,等.场致扩散焊接界面结合质量的超声无损评价[J].西安交通大学学报,2003,37(11):1163-1166.
[20] Cao Z J, Chen H D, Xue J, et al. Evaluation of Mechanical Quality ofField-Assisted Diffusion Bonding by Ultrasonic Nondestructive Method[J].Sensors and Actuators A-Physical,2005,118(1):44-48.
[21] Silk M G, Lidington B H. The Potential of Scattered Or Diffracted Ultrasoundin the Determination of Crack Depth[J]. Non-Destructive Testing,1975,8(3):146-151.
[22] Carvalho A A, Rebello J, Souza W V, et al. Reliability of Non-Destructive TestTechniques in the Inspection of Pipelines Used in the Oil Industry[J].International Journal of Pressure Vessels and Piping,2008,85(11):745-751.
[23] Nath S K, Balasubramaniam K, Krishnamurthy C V, et al. Sizing ofSurface-Breaking Cracks in Complex Geometry Components by UltrasonicTime-of-Flight Diffraction Technique[J]. Insight,2007,49(4):200-206.
[24] Garnier C, Pastor M L, Eyma F, et al. The Detection of Aeronautical Defects inSitu On Composite Structures Using Non Destructive Testing[J]. CompositeStructures,2011,93(5):1328-1336.
[25] Nardoni G, Betti F, Guidi A, et al. TOFD, the Emerging Ultrasonic Technique,for Heavy Wall Pressure Vessel Welds Examination[J]. Journal ofNondestructive Testing&Ultrasonics,1999,4(9):1-10.
[26]杨玉国. TOFD超声成像检测技术在厚壁加氢反应器检验中的应用[J].石油化工设备,2010,(3):82-85.
[27]郝以运,刘晴岩,张俭,等. TOFD方法在薄壁堆焊层裂纹类缺陷检测中的应用[J].焊管,2009,(6):36-39.
[28]李衍.超声TOFD法在大厚度压力容器焊缝检测上的应用[J].无损探伤,2005,(4):5-8.
[29] Carvalho A A, Rebello J, Silva R R, et al. Reliability of the Manual andAutomatic Ultrasonic Technique in the Detection of Pipe Weld Defects[J].Insight,2006,48(11):649-654.
[30]迟大钊,刚铁,袁媛,等.面状缺陷超声TOFD法信号和图像的特征与识别[J].焊接学报,2005,26(11):1-5.
[31]方舟正.合成孔径聚焦超声成像系统的实验研究[D].南京:南京航空航天大学硕士学位论文,2003:3-9.
[32] Liou R J, Kao K C, Yeh C Y, et al. Flaw Detection and Sizing of UltrasonicImages Using Wavelet Transform and SAFT[C]: Proceedings of2004International Symposium on Intelligent Signal Processing and CommunicationSystems, ISPACS2004, Seoul, Korea,2004:106-110.
[33] Biagi E, Masotti L, Rossi I, et al. Synthetic Aperture Technique forEchographic Focusing Based On Pulse Compression[J]. IEEE UltrasonicSymposium,2004,2:1425-1428.
[34]王邓志,罗斌,罗宏建.合成孔径聚焦超声成像系统研究[J].东北电力技术,2002,(12):42-45.
[35] Hayes M P, Gough P T. Broad-Band Synthetic Aperture Sonar[J]. IEEEJournal of Oceanic Engineering,1992,17(1):80-94.
[36]沈建中,孙宝申,张凡.合成孔径聚焦声成像时域算法研究[J].声学学报,1997,22(1):42-49.
[37]危荃,邬冠华,钟德煌,等. SAFT成像技术在棒材超声成像检测中的应用[J].无损检测,2008,30(7):415-417.
[38] Nielsen N. P-Scan System for Ultrasonic Weld Inspection[J]. British Journal ofNon-Destructive Testing,1981,23(2):63-69.
[39]腾永平,郑中兴,崔建英,等.便携式超声波P扫描成象系统软件的设计[J].无损检测,1996,18(12):333-335.
[40]刘菲菲,刘松平,李乐刚,等.管道焊缝超声P扫描成像检测技术[J].航空制造技术,2007,(11):97-100.
[41]王宁.超声相控阵焊缝探伤系统的数据采集和处理方法的研究[D].天津:天津大学硕士学位论文,2006:2-15.
[42]李云龙,余国民,张鸿博,等.自动超声相控阵技术在海洋敷管环焊缝检测中的应用[J].焊管,2006,29(5):40-44.
[43] Adams D E. Structural Health Monitoring Methods for Flight Safety[J].Journal of Failure Analysis and Prevention,2004,4(5):9-14.
[44] Lozev M G, Shell E B, Spencer R L, et al. Testing Superaustenitic StainlessSteel Welds Using Phased Array Ultrasonics[J]. Materials evaluation,2004,62(11):1135-1141.
[45] Moles M, Ginzel E, Dube N. Phased Arrays for Pipeline Girth WeldInspections[J]. Insight Non-Destructive Testing and Condition Monitoring,2002,44(2):86-94.
[46] Werme L O. Fabrication and Testing of Copper Canister for Long TermIsolation of Spent Nuclear Fuel[C]: Materials Research Society SymposiumProceedings, Boston, USA,2000:77-88.
[47]鲍晓宇.相控阵超声检测系统及其关键技术的研究[D].北京:清华大学博士学位论文,2003:12-15.
[48]危荃,邬冠华,吴伟,等.钛合金厚板焊缝超声相控阵信号和图像的特征与识别[J].无损检测,2008,30(8):540-542.
[49] Carvalho A A, Rebello J, Sagrilo L, et al. MFL Signals and Artificial NeuralNetworks Applied to Detection and Classification of Pipe Weld Defects[J].NDT and E International,2006,39(8):661-667.
[50] Da Silva R R, Caloba L P, Siqueira M H S, et al. Pattern Recognition of WeldDefects Detected by Radiographic Test[J]. NDT and E International,2004,37(6):461-470.
[51] Mirapeix J, Garcia-Allende P B, Cobo A, et al. Real-Time Arc-Welding DefectDetection and Classification with Principal Component Analysis and ArtificialNeural Networks[J]. NDT and E International,2007,40(4):315-323.
[52]边肇祺,张学工.模式识别[M].北京:清华大学出版社,2000:2-15.
[53] Santos J B, Perdigao F. Automatic Defects Classification-a Contribution[J].NDT and E International,2001,34(5):313-318.
[54] Li Z, Luo F, Pan M, et al. Application of Support Vector Machine in FlawIdentification of Aircraft Bolts[C]: Fourth International Symposium onPrecision Mechanical Measurements, Hefei, Anhui, China,2008:1-6.
[55] Drai R, Sellidj F, Khelil M, et al. Elaboration of some Signal ProcessingAlgorithms in Ultrasonic Techniques: Application to Materials NDT[J].Ultrasonics,2000,38(1-8):503-507.
[56]黄晶,阙沛文.小波分析在管道缺陷超声检测中的应用[J].传感技术学报,2003,(3):263-266.
[57] Rose J L, Jeong Y H, Alloway E, et al. Methodology for ReflectorClassification Analysis in Complex Geometric Welded Structures[J].Materials Evaluation,1984,42(1):98-101.
[58] Case T J, Waag R C. Flaw Identification From Time and Frequency Features ofUltrasonic Waveforms[J]. IEEE Transactions on Ultrasonics Ferroelectricsand Frequency Control,1996,43(4):592-600.
[59] Drai R, Khelil M, Benchaala A. Time Frequency and Wavelet TransformApplied to Selected Problems in Ultrasonics NDE[J]. NDT and E International,2002,35(8):567-572.
[60] Lombardo A, Masnata A, Settineri L. In-Process Tool-Failure Detection byMeans of Ar Models[J]. International Journal of Advanced ManufacturingTechnology,1997,13(2):86-94.
[61] Masnata A, Sunseri M. Neural Network Classification of Flaws Detected byUltrasonic Means[J]. NDT and E International,1996,29(2):87-93.
[62] Vieira A P, de Moura E P, Goncalves L L, et al. Characterization of WeldingDefects by Fractal Analysis of Ultrasonic Signals[J]. Chaos, Solitons andFractals,2008,38(3):748-754.
[63] Sahoo A K, Zhang Y, Zuo M J. Estimating Crack Size and Location in a SteelPlate Using Ultrasonic Signals and Cfbp Neural Networks[C]: CanadianConference on Electrical and Computer Engineering, Niagara Falls, Canada,2008:1751-1754.
[64] Cau F, Fanni A, Montisci A, et al. Artificial Neural Networks forNon-Destructive Evaluation with Ultrasonic Waves in Not AccessiblePipes[C]: IEEE Industry Applications Society Annual Meeting, Kowloon,Hong Kong, China,2005:685-692.
[65] Windsor C G, Anselme F, Capineri L, et al. The Classification of Weld DefectsFrom Ultrasonic Images[J]. British Journal of Non-Destructive Testing,1993,35(1):15-22.
[66] Ramuhalli P, Kim J, Udpa L, et al. Multichannel Signal Processing Methodsfor Ultrasonic Nondestructive Evaluation[C]: Proceedings of the2nd IEEESensor Array and Multichannel Signal Processing Workshop, New York, USA,2002:229-233.
[67] Spanner J, Udpa L, Polikar R, et al. Neural Networks for Ultrasonic Detectionof Intergranular Stress Corrosion Cracking[J]. The e-Journal ofNondestructive Testing and Ultrasonics,2000,409:215-221.
[68]刚铁.基于神经网络的焊接缺陷智能化超声模式识别与诊断[J].无损检测,1999,21(12):529-532.
[69]卢超,于润桥,彭应秋.焊接缺陷超声检测回波信号的双谱分析[J].数据采集与处理,2003,18(1):57-61.
[70]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.
[71]陈渊.基于小波包和概率神经网络的焊接缺陷识别[J].仪表技术与传感器,2010,(8):89-92.
[72]栾亦琳. TiAl/40Cr扩散焊界面超声信号特征分析与缺陷智能识别研究[D].哈尔滨:哈尔滨工业大学博士学位论文,2008:21-98.
[73] Gao D, Liu Y X, Zhang X G. Binary-tree multi-classifier for welding defectsand its application based on SVM[C]: Proceedings of the World Congress onIntelligent Control and Automation, Dalian, China,2006:8509-8513.
[74] Zhang X G, Zhu Z C, Xu J H, et al. The Classification Algorithm of Defects inWeld Image Based On Asymmetrical SVMs[C]: Proceedings of theInternational Conference on Control and Automation, Budapest, Hungary,2005:1215-1219.
[75]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.
[76] Shitole C N, Zahran O, Al-Nuaimy W. Combining Fuzzy Logic and NeuralNetworks in Classification of Weld Defects Using Ultrasonic Time-of-FlightDiffraction[J]. Insight,2007,49(2):79-82.
[77] Moura E P, Silva R R, Siqueira M, et al. Pattern Recognition of Weld Defectsin Preprocessed TOFD Signals Using Linear Classifiers[J]. Journal ofNondestructive Evaluation,2004,23(4):163-172.
[78]刘晓楠.焊缝缺陷的超声检测与定位系统研究[D].哈尔滨:哈尔滨工业大学硕士学位论文,2008:28-32.
[79]吴学功.基于USB摄像头的数字图像检测技术研究[D].南京:东南大学硕士学位论文,2006:5-8.
[80]吴学功,张文锦.利用普通摄像头实现振动的实时测量[J].电子工程师,2006,32(7):4-7.
[81]赵秋荷.摄像头固定的场景中视频物体的运动检测[D].南京:南京航空航天大学硕士学位论文,2005:7-14.
[82]魏会明,苏光辉,秋穗正,等.基于小波分析和遗传算法的沸腾曲线特征点研究[J].原子能科学技术,2009,8(5):421-425.
[83]常瑞生.基于小波理论的摩擦焊接头缺陷检测与识别[D].西安:西北工业大学硕士学位论文,2004:11-14.
[84]聂颖.基于时频分析的超声信号处理方法的研究[D].大连:大连理工大学硕士学位论文,2006:25-29.
[85] Brereton R G. Chemometrics: Data Analysis for the Laboratory and ChemicalPlant[M]. USA: Wiley,2003:183-270.
[86] Duda R O, Hart R E, Stork D G. Pattern Classification[M]. USA: Wiley,2001:584-674.
[87] Lei Y G, He Z J, Zi Y Y. Application of an Intelligent Classification Method toMechanical Fault Diagnosis[J]. Expert Systems with Applications,2009,36(6):9941-9948.
[88]刘永红.神经网络理论的发展与前沿问题[J].信息与控制,1999,28(1):31-46.
[89]钟珞,饶文碧,邹承明.人工神经网络及其融合应用技术[M].北京:科学出版社,2007:1-8.
[90] Zhu D Q, Yang Y Q, Li W Z. Blind Fault Diagnosis Algorithm for IntegratedCircuit Based On the CPN Neural Networks[C]: Lecture Notes in ComputerScience, Berlin, Germany,2004:619-626.
[91]钟珞,魏志华,陈新艳,等.使用神经网络的软件工程成本模型[J].武汉工业大学学报,1996,18(4):78-81.
[92]栗然,张锋奇,盛世清,等.专家系统与人工神经网络的发展与结合[J].华北电力大学学报,1998,25(2):36-42.
[93]郝梓倩,陈贻焕,李廷军,等.基于人工神经网络的自动控制系统[J].现代电子技术,2006,(2):9-11.
[94]胡守仁等.神经网络导论[M].长沙:国防科技大学出版社,1993:1-76.
[95]焦李成.神经网络系统理论[M].西安:西安电子科技大学出版社,1990:1-16.
[96]史忠植.神经计算[M].北京:电子工业出版社,1993:1-102.
[97]杜华英,赵跃龙.人工神经网络典型模型的比较研究[J].计算机技术与发展,2006,16(5):97-99.
[98] Rumelhart D E, McClelland J L. Parallel Distributed Processing: Explorationsin the Microstructure of Cognition[M]. USA: The MIT press,1986:1-567.
[99]朱泽君,黄涛,刘曦霞,等.多传感器数据融合技术研究现状及发展方向[J].舰船电子工程,2009,29(2):13-16.
[100]Yager R R. A Framework for Multi-Source Data Fusion[J]. InformationSciences,2004,163(1-3):175-200.
[101]Horiuchi T. Decision Rule for Pattern Classification by Integrating IntervalFeature Values[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1998,20(4):440-448.
[102]Durrant-Whyte H F. Consistent Integration and Propagation of DisparateSensor Observations.[J]. International Journal of Robotics Research,1987,6(3):3-24.
[103]Zeytinoglu M, Mintz M. Robust Fixed Size Confidence Procedures for aRestricted Parameter Space[J]. Annals of Statistics,1988,16(3):1241-1253.
[104]Gu J, Meng M, Cook A, et al. Micro Sensor Based Eye Movement Detectionand Neural Network Based Sensor Fusion and Fault Detection andRecovery[C]: Canadian Conference on Electrical and Computer Engineering,Halifax, Canada,2000:518-522.
[105]Lalithakumari S, Sheelarani B, Venkatraman B. Artificial Neural NetworkBased Defect Detection of Welds in TOFD Technique[J]. International Journalof Computer Applications,2012,41(20):17-20.
[106]Mostafaei, Khalaj, Makui. Engine Fault Diagnosis Decision-Making withIncomplete Information Using Dempster-Shafer Theory[J]. Journal of Basicand Applied,2012,2(1):105-113.
[107]Shafer G. A Mathematical Theory of Evidence[M]. USA: Princeton universitypress,1976:1-302.
[108]Dempster. Upper and Lower Probabilities Induced by a MultiplicandMapping[J]. Annals of Mathematical Statistics,1967,(38):325-339.
[109]Daniel J, Lauffenburger J P, Basset M. Multi-Criterion Dempster-ShaferFusion for Speed Limit Determination[C]: Preprints of the18th IFAC WorldCongress, Milano, Italy,2011:668-673.
[110]陈艳琴,罗大庸.多信息融合技术及在无损检测中的应用[J].电子科技大学学报,2003,32(6):661-664.
[111]Quan R, Quan S, Huang L, et al. Information Fusion in Fault Diagnosis forAutomotive Fuel Cell System Based On Ds Evidence Theory[J]. Journal ofComputational Information Systems,2011,7(1):97-105.
[112]Dempster A. A Generalization of Bayesian Inference[J]. Journal of the RoyalStatistical Society,1968,30:205-245.
[113]刘雷健,杨静宇.基于融合信息的物体识别[J].模式识别与人工智能,1993,6(1):27-33.
[2] Provan W J. Probabilistic Fracture Mechanics and Reliability[M]. Netherlands:Matinus Nijhoft Publishers,1986:39-42.
[3] Van D G M, Boogaard J. NDT Reliability a Way to Go[C]: Proceedings of theWorld Conference on Non-Destructive Testing, Sao Paulo, Brazil,1992:95-98.
[4]耿荣生.新千年的无损检测技术——从罗马会议看无损检测技术的发展方向[J].无损检测,2001,23(1):2-5.
[5] Ma H W, Zhang X H, Wei J. Research On an Ultrasonic NDT System forComplex Surface Parts[J]. Journal of Materials Processing Technology,2002,129(3):667-670.
[6]黄民,李功.焊缝超声无损检测中的缺陷智能识别方法[J].北京信息科技大学学报(自然科学版),2009,24(2):33-36.
[7]韩和平.焊缝缺陷深度及高度测定-G-I射线片三维检测仪[J].热力发电,1991,(4):1-6.
[8]袁易全.近代超声原理与应用[M].南京:南京大学出版社,1996:440-462.
[9]金长善.超声工程[M].哈尔滨:哈尔滨工业大学出版社,1989:105-125.
[10]史亦韦.超声检测[M].北京:机械工业出版社,2005:4-16.
[11]刘福顺,汤明.无损检测基础[M].北京:北京航空航天大学出版社,2002:86-120.
[12]沈建中.超声成象技术及其在无损检测中的应用[J].无损检测,1994,16(7):202-206.
[13]王云平.超声无损检测与评价的关键技术问题及其解决方案[J].煤矿机械,2008,(9):194-196.
[14] Stubbs D A, Zawada L P. Detection of Porosity in Glass Ceramic MatrixComposites Using an Ultrasonic Multiple-Gate C-Scan Technique[J].Materials Evaluation,1996,54(7):827-831.
[15]刘文霞,沈京玲,刘颖韬,等.玻璃钢蒙皮纸蜂窝材料的无损检测[J].无损检测,2009,31(12):990-992.
[16] Chertov A M, Maev R G, Severin F M. Acoustic Microscopy of InternalStructure of Resistance Spot Welds[J]. IEEE Transactions on Ultrasonics,Ferroelectrics, and Frequency Control,2007,54(8):1521-1529.
[17]王裕文,刘大文,侯成刚,等. JTUIS系列超声成像无损检测系统[J].低压电器,2000,(2):53-55.
[18] Debbouz O, Navai F. Nondestructive Testing of2017Aluminum Copper AlloyDiffusion Welded Joints by an Automatic Ultrasonic System[J]. MaterialsEvaluation,1999,57(12):1261-1267.
[19]曹宗杰,王久洪,薛锦,等.场致扩散焊接界面结合质量的超声无损评价[J].西安交通大学学报,2003,37(11):1163-1166.
[20] Cao Z J, Chen H D, Xue J, et al. Evaluation of Mechanical Quality ofField-Assisted Diffusion Bonding by Ultrasonic Nondestructive Method[J].Sensors and Actuators A-Physical,2005,118(1):44-48.
[21] Silk M G, Lidington B H. The Potential of Scattered Or Diffracted Ultrasoundin the Determination of Crack Depth[J]. Non-Destructive Testing,1975,8(3):146-151.
[22] Carvalho A A, Rebello J, Souza W V, et al. Reliability of Non-Destructive TestTechniques in the Inspection of Pipelines Used in the Oil Industry[J].International Journal of Pressure Vessels and Piping,2008,85(11):745-751.
[23] Nath S K, Balasubramaniam K, Krishnamurthy C V, et al. Sizing ofSurface-Breaking Cracks in Complex Geometry Components by UltrasonicTime-of-Flight Diffraction Technique[J]. Insight,2007,49(4):200-206.
[24] Garnier C, Pastor M L, Eyma F, et al. The Detection of Aeronautical Defects inSitu On Composite Structures Using Non Destructive Testing[J]. CompositeStructures,2011,93(5):1328-1336.
[25] Nardoni G, Betti F, Guidi A, et al. TOFD, the Emerging Ultrasonic Technique,for Heavy Wall Pressure Vessel Welds Examination[J]. Journal ofNondestructive Testing&Ultrasonics,1999,4(9):1-10.
[26]杨玉国. TOFD超声成像检测技术在厚壁加氢反应器检验中的应用[J].石油化工设备,2010,(3):82-85.
[27]郝以运,刘晴岩,张俭,等. TOFD方法在薄壁堆焊层裂纹类缺陷检测中的应用[J].焊管,2009,(6):36-39.
[28]李衍.超声TOFD法在大厚度压力容器焊缝检测上的应用[J].无损探伤,2005,(4):5-8.
[29] Carvalho A A, Rebello J, Silva R R, et al. Reliability of the Manual andAutomatic Ultrasonic Technique in the Detection of Pipe Weld Defects[J].Insight,2006,48(11):649-654.
[30]迟大钊,刚铁,袁媛,等.面状缺陷超声TOFD法信号和图像的特征与识别[J].焊接学报,2005,26(11):1-5.
[31]方舟正.合成孔径聚焦超声成像系统的实验研究[D].南京:南京航空航天大学硕士学位论文,2003:3-9.
[32] Liou R J, Kao K C, Yeh C Y, et al. Flaw Detection and Sizing of UltrasonicImages Using Wavelet Transform and SAFT[C]: Proceedings of2004International Symposium on Intelligent Signal Processing and CommunicationSystems, ISPACS2004, Seoul, Korea,2004:106-110.
[33] Biagi E, Masotti L, Rossi I, et al. Synthetic Aperture Technique forEchographic Focusing Based On Pulse Compression[J]. IEEE UltrasonicSymposium,2004,2:1425-1428.
[34]王邓志,罗斌,罗宏建.合成孔径聚焦超声成像系统研究[J].东北电力技术,2002,(12):42-45.
[35] Hayes M P, Gough P T. Broad-Band Synthetic Aperture Sonar[J]. IEEEJournal of Oceanic Engineering,1992,17(1):80-94.
[36]沈建中,孙宝申,张凡.合成孔径聚焦声成像时域算法研究[J].声学学报,1997,22(1):42-49.
[37]危荃,邬冠华,钟德煌,等. SAFT成像技术在棒材超声成像检测中的应用[J].无损检测,2008,30(7):415-417.
[38] Nielsen N. P-Scan System for Ultrasonic Weld Inspection[J]. British Journal ofNon-Destructive Testing,1981,23(2):63-69.
[39]腾永平,郑中兴,崔建英,等.便携式超声波P扫描成象系统软件的设计[J].无损检测,1996,18(12):333-335.
[40]刘菲菲,刘松平,李乐刚,等.管道焊缝超声P扫描成像检测技术[J].航空制造技术,2007,(11):97-100.
[41]王宁.超声相控阵焊缝探伤系统的数据采集和处理方法的研究[D].天津:天津大学硕士学位论文,2006:2-15.
[42]李云龙,余国民,张鸿博,等.自动超声相控阵技术在海洋敷管环焊缝检测中的应用[J].焊管,2006,29(5):40-44.
[43] Adams D E. Structural Health Monitoring Methods for Flight Safety[J].Journal of Failure Analysis and Prevention,2004,4(5):9-14.
[44] Lozev M G, Shell E B, Spencer R L, et al. Testing Superaustenitic StainlessSteel Welds Using Phased Array Ultrasonics[J]. Materials evaluation,2004,62(11):1135-1141.
[45] Moles M, Ginzel E, Dube N. Phased Arrays for Pipeline Girth WeldInspections[J]. Insight Non-Destructive Testing and Condition Monitoring,2002,44(2):86-94.
[46] Werme L O. Fabrication and Testing of Copper Canister for Long TermIsolation of Spent Nuclear Fuel[C]: Materials Research Society SymposiumProceedings, Boston, USA,2000:77-88.
[47]鲍晓宇.相控阵超声检测系统及其关键技术的研究[D].北京:清华大学博士学位论文,2003:12-15.
[48]危荃,邬冠华,吴伟,等.钛合金厚板焊缝超声相控阵信号和图像的特征与识别[J].无损检测,2008,30(8):540-542.
[49] Carvalho A A, Rebello J, Sagrilo L, et al. MFL Signals and Artificial NeuralNetworks Applied to Detection and Classification of Pipe Weld Defects[J].NDT and E International,2006,39(8):661-667.
[50] Da Silva R R, Caloba L P, Siqueira M H S, et al. Pattern Recognition of WeldDefects Detected by Radiographic Test[J]. NDT and E International,2004,37(6):461-470.
[51] Mirapeix J, Garcia-Allende P B, Cobo A, et al. Real-Time Arc-Welding DefectDetection and Classification with Principal Component Analysis and ArtificialNeural Networks[J]. NDT and E International,2007,40(4):315-323.
[52]边肇祺,张学工.模式识别[M].北京:清华大学出版社,2000:2-15.
[53] Santos J B, Perdigao F. Automatic Defects Classification-a Contribution[J].NDT and E International,2001,34(5):313-318.
[54] Li Z, Luo F, Pan M, et al. Application of Support Vector Machine in FlawIdentification of Aircraft Bolts[C]: Fourth International Symposium onPrecision Mechanical Measurements, Hefei, Anhui, China,2008:1-6.
[55] Drai R, Sellidj F, Khelil M, et al. Elaboration of some Signal ProcessingAlgorithms in Ultrasonic Techniques: Application to Materials NDT[J].Ultrasonics,2000,38(1-8):503-507.
[56]黄晶,阙沛文.小波分析在管道缺陷超声检测中的应用[J].传感技术学报,2003,(3):263-266.
[57] Rose J L, Jeong Y H, Alloway E, et al. Methodology for ReflectorClassification Analysis in Complex Geometric Welded Structures[J].Materials Evaluation,1984,42(1):98-101.
[58] Case T J, Waag R C. Flaw Identification From Time and Frequency Features ofUltrasonic Waveforms[J]. IEEE Transactions on Ultrasonics Ferroelectricsand Frequency Control,1996,43(4):592-600.
[59] Drai R, Khelil M, Benchaala A. Time Frequency and Wavelet TransformApplied to Selected Problems in Ultrasonics NDE[J]. NDT and E International,2002,35(8):567-572.
[60] Lombardo A, Masnata A, Settineri L. In-Process Tool-Failure Detection byMeans of Ar Models[J]. International Journal of Advanced ManufacturingTechnology,1997,13(2):86-94.
[61] Masnata A, Sunseri M. Neural Network Classification of Flaws Detected byUltrasonic Means[J]. NDT and E International,1996,29(2):87-93.
[62] Vieira A P, de Moura E P, Goncalves L L, et al. Characterization of WeldingDefects by Fractal Analysis of Ultrasonic Signals[J]. Chaos, Solitons andFractals,2008,38(3):748-754.
[63] Sahoo A K, Zhang Y, Zuo M J. Estimating Crack Size and Location in a SteelPlate Using Ultrasonic Signals and Cfbp Neural Networks[C]: CanadianConference on Electrical and Computer Engineering, Niagara Falls, Canada,2008:1751-1754.
[64] Cau F, Fanni A, Montisci A, et al. Artificial Neural Networks forNon-Destructive Evaluation with Ultrasonic Waves in Not AccessiblePipes[C]: IEEE Industry Applications Society Annual Meeting, Kowloon,Hong Kong, China,2005:685-692.
[65] Windsor C G, Anselme F, Capineri L, et al. The Classification of Weld DefectsFrom Ultrasonic Images[J]. British Journal of Non-Destructive Testing,1993,35(1):15-22.
[66] Ramuhalli P, Kim J, Udpa L, et al. Multichannel Signal Processing Methodsfor Ultrasonic Nondestructive Evaluation[C]: Proceedings of the2nd IEEESensor Array and Multichannel Signal Processing Workshop, New York, USA,2002:229-233.
[67] Spanner J, Udpa L, Polikar R, et al. Neural Networks for Ultrasonic Detectionof Intergranular Stress Corrosion Cracking[J]. The e-Journal ofNondestructive Testing and Ultrasonics,2000,409:215-221.
[68]刚铁.基于神经网络的焊接缺陷智能化超声模式识别与诊断[J].无损检测,1999,21(12):529-532.
[69]卢超,于润桥,彭应秋.焊接缺陷超声检测回波信号的双谱分析[J].数据采集与处理,2003,18(1):57-61.
[70]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.
[71]陈渊.基于小波包和概率神经网络的焊接缺陷识别[J].仪表技术与传感器,2010,(8):89-92.
[72]栾亦琳. TiAl/40Cr扩散焊界面超声信号特征分析与缺陷智能识别研究[D].哈尔滨:哈尔滨工业大学博士学位论文,2008:21-98.
[73] Gao D, Liu Y X, Zhang X G. Binary-tree multi-classifier for welding defectsand its application based on SVM[C]: Proceedings of the World Congress onIntelligent Control and Automation, Dalian, China,2006:8509-8513.
[74] Zhang X G, Zhu Z C, Xu J H, et al. The Classification Algorithm of Defects inWeld Image Based On Asymmetrical SVMs[C]: Proceedings of theInternational Conference on Control and Automation, Budapest, Hungary,2005:1215-1219.
[75]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.
[76] Shitole C N, Zahran O, Al-Nuaimy W. Combining Fuzzy Logic and NeuralNetworks in Classification of Weld Defects Using Ultrasonic Time-of-FlightDiffraction[J]. Insight,2007,49(2):79-82.
[77] Moura E P, Silva R R, Siqueira M, et al. Pattern Recognition of Weld Defectsin Preprocessed TOFD Signals Using Linear Classifiers[J]. Journal ofNondestructive Evaluation,2004,23(4):163-172.
[78]刘晓楠.焊缝缺陷的超声检测与定位系统研究[D].哈尔滨:哈尔滨工业大学硕士学位论文,2008:28-32.
[79]吴学功.基于USB摄像头的数字图像检测技术研究[D].南京:东南大学硕士学位论文,2006:5-8.
[80]吴学功,张文锦.利用普通摄像头实现振动的实时测量[J].电子工程师,2006,32(7):4-7.
[81]赵秋荷.摄像头固定的场景中视频物体的运动检测[D].南京:南京航空航天大学硕士学位论文,2005:7-14.
[82]魏会明,苏光辉,秋穗正,等.基于小波分析和遗传算法的沸腾曲线特征点研究[J].原子能科学技术,2009,8(5):421-425.
[83]常瑞生.基于小波理论的摩擦焊接头缺陷检测与识别[D].西安:西北工业大学硕士学位论文,2004:11-14.
[84]聂颖.基于时频分析的超声信号处理方法的研究[D].大连:大连理工大学硕士学位论文,2006:25-29.
[85] Brereton R G. Chemometrics: Data Analysis for the Laboratory and ChemicalPlant[M]. USA: Wiley,2003:183-270.
[86] Duda R O, Hart R E, Stork D G. Pattern Classification[M]. USA: Wiley,2001:584-674.
[87] Lei Y G, He Z J, Zi Y Y. Application of an Intelligent Classification Method toMechanical Fault Diagnosis[J]. Expert Systems with Applications,2009,36(6):9941-9948.
[88]刘永红.神经网络理论的发展与前沿问题[J].信息与控制,1999,28(1):31-46.
[89]钟珞,饶文碧,邹承明.人工神经网络及其融合应用技术[M].北京:科学出版社,2007:1-8.
[90] Zhu D Q, Yang Y Q, Li W Z. Blind Fault Diagnosis Algorithm for IntegratedCircuit Based On the CPN Neural Networks[C]: Lecture Notes in ComputerScience, Berlin, Germany,2004:619-626.
[91]钟珞,魏志华,陈新艳,等.使用神经网络的软件工程成本模型[J].武汉工业大学学报,1996,18(4):78-81.
[92]栗然,张锋奇,盛世清,等.专家系统与人工神经网络的发展与结合[J].华北电力大学学报,1998,25(2):36-42.
[93]郝梓倩,陈贻焕,李廷军,等.基于人工神经网络的自动控制系统[J].现代电子技术,2006,(2):9-11.
[94]胡守仁等.神经网络导论[M].长沙:国防科技大学出版社,1993:1-76.
[95]焦李成.神经网络系统理论[M].西安:西安电子科技大学出版社,1990:1-16.
[96]史忠植.神经计算[M].北京:电子工业出版社,1993:1-102.
[97]杜华英,赵跃龙.人工神经网络典型模型的比较研究[J].计算机技术与发展,2006,16(5):97-99.
[98] Rumelhart D E, McClelland J L. Parallel Distributed Processing: Explorationsin the Microstructure of Cognition[M]. USA: The MIT press,1986:1-567.
[99]朱泽君,黄涛,刘曦霞,等.多传感器数据融合技术研究现状及发展方向[J].舰船电子工程,2009,29(2):13-16.
[100]Yager R R. A Framework for Multi-Source Data Fusion[J]. InformationSciences,2004,163(1-3):175-200.
[101]Horiuchi T. Decision Rule for Pattern Classification by Integrating IntervalFeature Values[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1998,20(4):440-448.
[102]Durrant-Whyte H F. Consistent Integration and Propagation of DisparateSensor Observations.[J]. International Journal of Robotics Research,1987,6(3):3-24.
[103]Zeytinoglu M, Mintz M. Robust Fixed Size Confidence Procedures for aRestricted Parameter Space[J]. Annals of Statistics,1988,16(3):1241-1253.
[104]Gu J, Meng M, Cook A, et al. Micro Sensor Based Eye Movement Detectionand Neural Network Based Sensor Fusion and Fault Detection andRecovery[C]: Canadian Conference on Electrical and Computer Engineering,Halifax, Canada,2000:518-522.
[105]Lalithakumari S, Sheelarani B, Venkatraman B. Artificial Neural NetworkBased Defect Detection of Welds in TOFD Technique[J]. International Journalof Computer Applications,2012,41(20):17-20.
[106]Mostafaei, Khalaj, Makui. Engine Fault Diagnosis Decision-Making withIncomplete Information Using Dempster-Shafer Theory[J]. Journal of Basicand Applied,2012,2(1):105-113.
[107]Shafer G. A Mathematical Theory of Evidence[M]. USA: Princeton universitypress,1976:1-302.
[108]Dempster. Upper and Lower Probabilities Induced by a MultiplicandMapping[J]. Annals of Mathematical Statistics,1967,(38):325-339.
[109]Daniel J, Lauffenburger J P, Basset M. Multi-Criterion Dempster-ShaferFusion for Speed Limit Determination[C]: Preprints of the18th IFAC WorldCongress, Milano, Italy,2011:668-673.
[110]陈艳琴,罗大庸.多信息融合技术及在无损检测中的应用[J].电子科技大学学报,2003,32(6):661-664.
[111]Quan R, Quan S, Huang L, et al. Information Fusion in Fault Diagnosis forAutomotive Fuel Cell System Based On Ds Evidence Theory[J]. Journal ofComputational Information Systems,2011,7(1):97-105.
[112]Dempster A. A Generalization of Bayesian Inference[J]. Journal of the RoyalStatistical Society,1968,30:205-245.
[113]刘雷健,杨静宇.基于融合信息的物体识别[J].模式识别与人工智能,1993,6(1):27-33.