金属裂纹声发射信号识别及报警的方法研究
|
摘要
金属结构件在交变载荷作用下,出现疲劳裂纹是常见的故障之一,尤其是对于混流式水轮机转轮等结构复杂的大型构件更是如此。由于交变载荷的作用,裂纹不断扩展,常导致结构件的断裂,因而对疲劳裂纹的监测是非常必要的。声发射检测技术是一门新兴的多学科交叉的无损检测技术,已被广泛应用于设备的无损检测、在线监测中。本文在广泛查阅大量国内外科技文献资料的基础上,将声发射技术应用于金属疲劳裂纹的在线检测。
由于声发射信号的瞬态性和随机性,它由一系列频率和模式丰富的信号组成,以及现场工作环境恶劣,声发射源种类较多。很难通过简单的频率或者幅值等滤波方法来获取比较纯净金属疲劳裂纹声发射信号。
结合现场混流式水轮机转轮工作实际情况,初步确定现场较多的声发射信号为金属疲劳裂纹声发射信号、空化信号以及摩擦声发射信号,并增加标准断铅信号。
综述分析声发射的分析方法及13个表征参数;通过采用神经网络模式识别的方法,设计出特征提取器,筛选出最能表达声发射本质的五个特征参数;同时采用可分离性判据的方法得到对分类效果最显著的特征参数,验证特征提取器的正确性;通过实验验证,利用所提取的五个特征参数可以识别出金属裂纹声发射信号。
此外,在大型复杂构件声发射检测中,经常采用多传感器检测系统。可以采用数据层融合的独立分量分析方法和决策层融合的D-S证据理论,来融合多传感器信息,减少识别的不确定性,提高系统的识别、容错和抗干扰能力。
在前面神经网络模式识别的基础上,借助数据融合技术和报警理论实现了对金属裂纹的发生进行报警。
本课题来源于国家自然科学基金项目(50465002)——《混流式水轮机转轮叶片裂纹监测的理论和方法研究》。
Under the alternate loading, accruing flaw in metal structure is one of faults that happen in metal structure frequently, especially in large-scale complex structural parts such as Francis turbine etc. As the effect of alternate loading, the flaw in the metal structure could develop continuously, and at the beginning, the fatigue flaw is very thin, therefore in this case, detecting flaw seems to be very necessary. Acoustic emission (AE) testing is applied widely as a rising multidisciplinary nondestructive testing technology in equipment of nondestructive examination and on-line monitoring. In this article, based on a great deal of resources from home and foreign country, AE technique will be applied to metal fatigue crack's on-line monitoring.
Since AE signal's transient and randomness, it is composed of a series of rich frequency and pattern, and poor working environment and many acoustic emission source categories at the scene. It is very difficult to gain comparatively pure metal fatigue AE signal by simple methods such as frequency or amplitude filtering.
After analyzing the actual work environment of the runner of Francis turbine, many AE signals can be determined initially at the scene, such as metal fatigue crack AE signals, cavitations, fricative AE signals, and increase the standard lead off signals.
Summary of analysis method of AE and 13 characteristic parameters; Feature extraction was designed by use of neural networks and pattern recognition method, and five characteristic parameters that can express AE most were filtered; At the same time, the most notable feature parameters on classification were obtained by use of the separability criterion, to verify the accuracy of feature extraction; According to the experimental results, metal crack AE signals can be identified with the five characteristic parameters.
In addition, in the large and complex component of the AE testing, multi-sensor detection system was used frequently. It can be fused in data layer by the independent component analysis, and decision-making layer by D-S evidence theory, to integrate multi-sensor signals, reduce uncertainty of recognition, improve the capabilities of system's identification, fault-tolerance and anti-jamming.
Based on the analysis of neural networks and pattern recognition referred, when metal crack happened, alarm can be carried out in virtue of the data fusion technology and the warning theory.
由于声发射信号的瞬态性和随机性,它由一系列频率和模式丰富的信号组成,以及现场工作环境恶劣,声发射源种类较多。很难通过简单的频率或者幅值等滤波方法来获取比较纯净金属疲劳裂纹声发射信号。
结合现场混流式水轮机转轮工作实际情况,初步确定现场较多的声发射信号为金属疲劳裂纹声发射信号、空化信号以及摩擦声发射信号,并增加标准断铅信号。
综述分析声发射的分析方法及13个表征参数;通过采用神经网络模式识别的方法,设计出特征提取器,筛选出最能表达声发射本质的五个特征参数;同时采用可分离性判据的方法得到对分类效果最显著的特征参数,验证特征提取器的正确性;通过实验验证,利用所提取的五个特征参数可以识别出金属裂纹声发射信号。
此外,在大型复杂构件声发射检测中,经常采用多传感器检测系统。可以采用数据层融合的独立分量分析方法和决策层融合的D-S证据理论,来融合多传感器信息,减少识别的不确定性,提高系统的识别、容错和抗干扰能力。
在前面神经网络模式识别的基础上,借助数据融合技术和报警理论实现了对金属裂纹的发生进行报警。
本课题来源于国家自然科学基金项目(50465002)——《混流式水轮机转轮叶片裂纹监测的理论和方法研究》。
Under the alternate loading, accruing flaw in metal structure is one of faults that happen in metal structure frequently, especially in large-scale complex structural parts such as Francis turbine etc. As the effect of alternate loading, the flaw in the metal structure could develop continuously, and at the beginning, the fatigue flaw is very thin, therefore in this case, detecting flaw seems to be very necessary. Acoustic emission (AE) testing is applied widely as a rising multidisciplinary nondestructive testing technology in equipment of nondestructive examination and on-line monitoring. In this article, based on a great deal of resources from home and foreign country, AE technique will be applied to metal fatigue crack's on-line monitoring.
Since AE signal's transient and randomness, it is composed of a series of rich frequency and pattern, and poor working environment and many acoustic emission source categories at the scene. It is very difficult to gain comparatively pure metal fatigue AE signal by simple methods such as frequency or amplitude filtering.
After analyzing the actual work environment of the runner of Francis turbine, many AE signals can be determined initially at the scene, such as metal fatigue crack AE signals, cavitations, fricative AE signals, and increase the standard lead off signals.
Summary of analysis method of AE and 13 characteristic parameters; Feature extraction was designed by use of neural networks and pattern recognition method, and five characteristic parameters that can express AE most were filtered; At the same time, the most notable feature parameters on classification were obtained by use of the separability criterion, to verify the accuracy of feature extraction; According to the experimental results, metal crack AE signals can be identified with the five characteristic parameters.
In addition, in the large and complex component of the AE testing, multi-sensor detection system was used frequently. It can be fused in data layer by the independent component analysis, and decision-making layer by D-S evidence theory, to integrate multi-sensor signals, reduce uncertainty of recognition, improve the capabilities of system's identification, fault-tolerance and anti-jamming.
Based on the analysis of neural networks and pattern recognition referred, when metal crack happened, alarm can be carried out in virtue of the data fusion technology and the warning theory.
引文
[1]覃大清,刘光宁,陶星明.混流式水轮机转轮叶片裂纹问题.大电机技术,2005(4):39-44
[2]《国防科技工业无损检测人员资格鉴定与认证培训教材》编审委员会编.声发射检测.北京:机械工业出版社,2005:7-109
[3]Ronnie K.Miller and Paul Mclntire eds,Vol.5,Acoustic Emission Testing,Nondestructive Testing Handbook,American Society for Nondestructive Testing,1987
[4]T.Drouillard,"Acoustic Emission:A Bibliography with Abstracts",Frances Laner,ed.New York,NY:IFI Plenum Data Company(1979)
[5]T.F.Drouillard,"Acoustic Emission-The First Half Century",Progress in Acoustic Emission VII,The Japanese Society for NDI,Japan,1994
[6]耿荣生,沈功田,刘时风.声发射信号处理专题综述.无损检测,2002:24(1-12)
[7]刘时风.焊接缺陷声发射检测信号谱估计及人工神经网络模式识别研究.[博士学位论文].北京:清华大学机械工程系,1996年
[8]戴光.在用压力容器活性缺陷的声发射特性与模糊综合分析.[博士学位论文],杭州:浙江大学化工机械系,1996年
[9]沈功田.金属压力容器的声发射源特性及识别方法的研究.[博士学位论文],北京:清华大学机械工程系,1998年
[10]沈功田,耿荣生,刘时风.声发射信号的参数分析方法.无损检测,2002,24(2):72-77
[11]宫琴,叶大田,丁海艳.瞬态诱发耳声发射信号的检测分析及应用.航天医学与医学工程,2003,16(2):147-151
[12]陈晓智,李蓓智,杨建国.一种新的声发射刀具磨损小波分析方法.无损检测,2007,29(1):12-15
[13]唐颀,庞宝君,韩增尧等.单层板超高速撞击声发射波的频谱特征分析.宇航学报,2007,28(4):1059-1064
[14]周洁,毛汉领,黄振峰等.金属疲劳断裂的声发射检测技术.中国测试技术,2007,33(3):7-9
[15]黄德双著.神经网络模式识别系统理论.北京:电子工业出版社,1996,5
[16]关新平 主编.信号处理与模式识别.北京:机械工业出版社,2006,04:2-66
[17]闻新,周露.Matlab神经网络仿真与应用.北京:科学出版社2003,7
[18]飞思科技产品研发中心编著.神经网络理论与MATLAB7实现.北京:电子工业出版社,2005:99-108
[19]舒宁,马洪超,孙和利编著.模式识别的理论与方法.武汉:武汉大学出版社,2004:78-85
[20]钟珞,潘昊,封筠,何平主编.模式识别.武汉:武汉大学出版社,2006.9:122-140
[21]边肇祺,张学工等.模式识别[M].北京:清华大学出版社,2001
[22]沈清,汤霖.模式识别导论[M].长沙:国防科技大学出版社,1997
[23]胡泽.基于MATLAB的神经网络模式识别与系统辨识方法研究.[硕士学位论文],西南石油学院,2005,4
[24]蔡泽高,刘以宽,王承忠等.金属磨损与断裂.上海:上海交通大学出版社,1985:220-238
[25]刘贵杰,巩亚东,王宛山.基于摩擦声发射信号的磨削表面粗糙度在线检测方法研究.摩擦学学报,2003,23(3):236-239
[26]秦萍,傅和平,闫兵等.基于声发射监测的静载荷滑动轴承接触摩擦故障诊断的实验研究.摩擦学学报,2006,26(6):585-589
[27]樊世英,混流式水轮机转轮裂纹原因分析及预防措施.水力发电,2002(5):38-41
[28]罗伟文,郑时雄,黄振峰等.混流式水轮机转轮叶片裂纹故障及其原因分析.机械加工工业与装备,2006(9):28-30
[29]聂荣舁主编.水轮机中的空化与空蚀.北京:水利电力出版社,1985:1-80
[30]王金刚,郭培全,王西奎等.空化效应在有机废水处理中的应用研究.化学进展,2005,17(3):549-553
[31]张俊华,张伟,蒲中奇等.轴流转桨式水轮机空化程度声信号辨识研究.中国电机工程学报,2006,26(8):72-76
[32]Branko Bajic.Multidimensional cavitation monitoring update[J].International Water Powerand Dam Construction,2004,56(11):38-41
[33]Branko Bajic.Cavitation diagnostics and monitoring[J].International Water Power and Dam Construction,2003,55(2):32-35
[34]Bellet L,Laperrousaz E,Dorey J M.Cavitation erosion prediction on Francis turbines[J].International Journal on Hydropower & Dams,1997,4(3):56-62
[35]黄继汤.空化与空蚀的原理及应用.北京:清华大学出版社,1991,203-216
[36]Heiple C R,Carpenter S H.Acoustic emission produced by deformation of metals and alloys a review 1 Part Ⅰ and Part Ⅱ[J].J Acoustic Emission,1987,6(3),177-204
[37]Sui E,Grabec I.Application of a neural network to the estimation of surface roughness from AE signals generated by friction process[J].Int J machTols Manufacture,1995,35(8):1077-1086
[38]孙涛,宏建.目标识别中的信息融合技术.自动化仪表,2001,22(2),1-4
[39]刘俊,付警奇,董新平.数据融合在目标识别中的应用.传感器技术,2001,20(6):8-11
[40]刘同明,夏祖勋.数据融合技术.北京:国防工业出版社,1998,1-57
[41]康耀红.数据融合原理与应用.西安:西安电子科技大学出版社,1997,3-45
[42]Linas J,Waltz E.Multi-sensor data fusion.Norwood,MA:Artech House,1990.8-9
[43]Hall D L.Mathematical techniques in multi-sensor data fusion.Boston,London:Artech House,1992.13-14
[44]赵宗贵,耿立贤,周中元等编译.多传感器融合.南京:电子工业部二十八研究所,1993,5-6
[45]赵宗贵编译.数据融合方法概论.南京:电子工业部二十八研究所,1998,11-12
[46]刘同明,夏祖助,解洪成.数据融合技术及其应用.北京:国防工业出版社,1998:4-6
[47]Varshney P K.Multi-sensor data fusion.Electronics & Communication Engineering Journal,1997,9(6):245-253
[48]杨万海.多传感器数据融合及其应用.西安:西安电子科技大学,2004,92-132
[49]戴亚平,刘征,郁光辉译著.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
[50]王欣.多传感器数据融合问题的研究.[博士学位论文],吉林:吉林大学计算机应用技术,2006
[51]李冲祥.神经网络和证据理论集成的数据融合故障诊断方法研究.[硕士学位论文],河北:燕山大学机械工程学院机械电子工程,2003
[52]李光海.声发射源识别技术的研究.[博士学位论文],华南理工大学,2002,10
[53]周洁.裂纹声发射源定位研究及发展趋势预估初探.[硕士学位论文],广西:广西大学机械工程学院机械电子工程,2006
[54]马建仓,牛奕龙,陈海洋编.盲信号处理.北京:国防工业出版社,2006:85-118
[55]Jutten C,Herault J.Blind separation of sources.Part Ⅰ:An adaptive algorithm based on neuromimatic architecture.Signal Processing,1991,24(1):1-10
[56]Bell A j,Sejnowski T J.An information maximization approach to blind separation and blind deconvolution.Neural Computation,1995,7(6):1004-1034
[57]Hyvarinen A,Karhunen J,Oja E.Independent Component Analysis.New York: John Wiley,2001
[58]吴响容.模式分类特征提取中的独立分量分析.[硕士学位论文],广西:广西师范大学电路与系统专业,2005
[59]Aapo Hyvarinen,Juha Karhunen,ErkkiO ja;Ⅰ ndependentC omponentA nalysis[M].AW iley-Interscience Publication.JO HN WILEY&SONS,INC.2001
[60]A.Hyv"arinen and E Oja A fast fixed-point talgorithm for independent component analysis[J].Neural Computation,9(7):1483-1492,1997
[61]A.Hyvdrmen.Fast and Robust Fixed-Point Algorithms for Independent Component Analysis[J].IE EE Transactions on Neural Networks10(3):626-634,1999
[62]Yair Shimshoni,Nathan Intrator.Classification of seismic signals by integrating ensembles of neural networks[J].IEEE Transactions on Signal Processing,1998,46(5)1194-1201
[63]李光海,刘正义.声发射源多传感器数据融合识别技术研究.无损检测,2003,25(4):171-175
[64]程婷.多传感器数据融合算法研究.[硕士学位论文],四川:电子科技大学信号与信息处理专业,2006
[65]Seizer F,Gutfinger D.Ladar and flir based fusion for automatic target classification[J/OL].SPIE,1993.236-246
[66]Dempster AP.Upper and lower probabilities induced by a multi-valued mapping[J].Annals of Mathematical Statistics,1967,38(1):325-339
[67]刘雷健等.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
[68]张遂强,郝伟,李志农.基于全信息技术的自适应报警方法研究.机械科学与技术,2006,25(12):1499-1502
[69]史毓达,卢炎生,王黎明.基于贝叶斯决策模型的火灾报警模式识别系统应用研究.华中师范大学学报,2007,41(2):211-217
[70]Varshney P K,Chair Z.Optimal data fusion in multiple sensor detection systems.IEEE Trans.AES,1986,22(1):98-101
[71]Reibman A R,Nolte L W.Optimal detection and performance of distributed sensor systems.IEEE Trans.AES,1987,23(1):24-30
[72]Elias-Fuste A R,et al.CFAR data fusion center with inhomogeneous receivers.IEEE Trans.on AES,1992,28(1):276-284
[73]康耀红.多传感器目标检测与跟踪的数据融合理论.[硕士学位论文],西安:西安电子科技大学,1995
[2]《国防科技工业无损检测人员资格鉴定与认证培训教材》编审委员会编.声发射检测.北京:机械工业出版社,2005:7-109
[3]Ronnie K.Miller and Paul Mclntire eds,Vol.5,Acoustic Emission Testing,Nondestructive Testing Handbook,American Society for Nondestructive Testing,1987
[4]T.Drouillard,"Acoustic Emission:A Bibliography with Abstracts",Frances Laner,ed.New York,NY:IFI Plenum Data Company(1979)
[5]T.F.Drouillard,"Acoustic Emission-The First Half Century",Progress in Acoustic Emission VII,The Japanese Society for NDI,Japan,1994
[6]耿荣生,沈功田,刘时风.声发射信号处理专题综述.无损检测,2002:24(1-12)
[7]刘时风.焊接缺陷声发射检测信号谱估计及人工神经网络模式识别研究.[博士学位论文].北京:清华大学机械工程系,1996年
[8]戴光.在用压力容器活性缺陷的声发射特性与模糊综合分析.[博士学位论文],杭州:浙江大学化工机械系,1996年
[9]沈功田.金属压力容器的声发射源特性及识别方法的研究.[博士学位论文],北京:清华大学机械工程系,1998年
[10]沈功田,耿荣生,刘时风.声发射信号的参数分析方法.无损检测,2002,24(2):72-77
[11]宫琴,叶大田,丁海艳.瞬态诱发耳声发射信号的检测分析及应用.航天医学与医学工程,2003,16(2):147-151
[12]陈晓智,李蓓智,杨建国.一种新的声发射刀具磨损小波分析方法.无损检测,2007,29(1):12-15
[13]唐颀,庞宝君,韩增尧等.单层板超高速撞击声发射波的频谱特征分析.宇航学报,2007,28(4):1059-1064
[14]周洁,毛汉领,黄振峰等.金属疲劳断裂的声发射检测技术.中国测试技术,2007,33(3):7-9
[15]黄德双著.神经网络模式识别系统理论.北京:电子工业出版社,1996,5
[16]关新平 主编.信号处理与模式识别.北京:机械工业出版社,2006,04:2-66
[17]闻新,周露.Matlab神经网络仿真与应用.北京:科学出版社2003,7
[18]飞思科技产品研发中心编著.神经网络理论与MATLAB7实现.北京:电子工业出版社,2005:99-108
[19]舒宁,马洪超,孙和利编著.模式识别的理论与方法.武汉:武汉大学出版社,2004:78-85
[20]钟珞,潘昊,封筠,何平主编.模式识别.武汉:武汉大学出版社,2006.9:122-140
[21]边肇祺,张学工等.模式识别[M].北京:清华大学出版社,2001
[22]沈清,汤霖.模式识别导论[M].长沙:国防科技大学出版社,1997
[23]胡泽.基于MATLAB的神经网络模式识别与系统辨识方法研究.[硕士学位论文],西南石油学院,2005,4
[24]蔡泽高,刘以宽,王承忠等.金属磨损与断裂.上海:上海交通大学出版社,1985:220-238
[25]刘贵杰,巩亚东,王宛山.基于摩擦声发射信号的磨削表面粗糙度在线检测方法研究.摩擦学学报,2003,23(3):236-239
[26]秦萍,傅和平,闫兵等.基于声发射监测的静载荷滑动轴承接触摩擦故障诊断的实验研究.摩擦学学报,2006,26(6):585-589
[27]樊世英,混流式水轮机转轮裂纹原因分析及预防措施.水力发电,2002(5):38-41
[28]罗伟文,郑时雄,黄振峰等.混流式水轮机转轮叶片裂纹故障及其原因分析.机械加工工业与装备,2006(9):28-30
[29]聂荣舁主编.水轮机中的空化与空蚀.北京:水利电力出版社,1985:1-80
[30]王金刚,郭培全,王西奎等.空化效应在有机废水处理中的应用研究.化学进展,2005,17(3):549-553
[31]张俊华,张伟,蒲中奇等.轴流转桨式水轮机空化程度声信号辨识研究.中国电机工程学报,2006,26(8):72-76
[32]Branko Bajic.Multidimensional cavitation monitoring update[J].International Water Powerand Dam Construction,2004,56(11):38-41
[33]Branko Bajic.Cavitation diagnostics and monitoring[J].International Water Power and Dam Construction,2003,55(2):32-35
[34]Bellet L,Laperrousaz E,Dorey J M.Cavitation erosion prediction on Francis turbines[J].International Journal on Hydropower & Dams,1997,4(3):56-62
[35]黄继汤.空化与空蚀的原理及应用.北京:清华大学出版社,1991,203-216
[36]Heiple C R,Carpenter S H.Acoustic emission produced by deformation of metals and alloys a review 1 Part Ⅰ and Part Ⅱ[J].J Acoustic Emission,1987,6(3),177-204
[37]Sui E,Grabec I.Application of a neural network to the estimation of surface roughness from AE signals generated by friction process[J].Int J machTols Manufacture,1995,35(8):1077-1086
[38]孙涛,宏建.目标识别中的信息融合技术.自动化仪表,2001,22(2),1-4
[39]刘俊,付警奇,董新平.数据融合在目标识别中的应用.传感器技术,2001,20(6):8-11
[40]刘同明,夏祖勋.数据融合技术.北京:国防工业出版社,1998,1-57
[41]康耀红.数据融合原理与应用.西安:西安电子科技大学出版社,1997,3-45
[42]Linas J,Waltz E.Multi-sensor data fusion.Norwood,MA:Artech House,1990.8-9
[43]Hall D L.Mathematical techniques in multi-sensor data fusion.Boston,London:Artech House,1992.13-14
[44]赵宗贵,耿立贤,周中元等编译.多传感器融合.南京:电子工业部二十八研究所,1993,5-6
[45]赵宗贵编译.数据融合方法概论.南京:电子工业部二十八研究所,1998,11-12
[46]刘同明,夏祖助,解洪成.数据融合技术及其应用.北京:国防工业出版社,1998:4-6
[47]Varshney P K.Multi-sensor data fusion.Electronics & Communication Engineering Journal,1997,9(6):245-253
[48]杨万海.多传感器数据融合及其应用.西安:西安电子科技大学,2004,92-132
[49]戴亚平,刘征,郁光辉译著.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
[50]王欣.多传感器数据融合问题的研究.[博士学位论文],吉林:吉林大学计算机应用技术,2006
[51]李冲祥.神经网络和证据理论集成的数据融合故障诊断方法研究.[硕士学位论文],河北:燕山大学机械工程学院机械电子工程,2003
[52]李光海.声发射源识别技术的研究.[博士学位论文],华南理工大学,2002,10
[53]周洁.裂纹声发射源定位研究及发展趋势预估初探.[硕士学位论文],广西:广西大学机械工程学院机械电子工程,2006
[54]马建仓,牛奕龙,陈海洋编.盲信号处理.北京:国防工业出版社,2006:85-118
[55]Jutten C,Herault J.Blind separation of sources.Part Ⅰ:An adaptive algorithm based on neuromimatic architecture.Signal Processing,1991,24(1):1-10
[56]Bell A j,Sejnowski T J.An information maximization approach to blind separation and blind deconvolution.Neural Computation,1995,7(6):1004-1034
[57]Hyvarinen A,Karhunen J,Oja E.Independent Component Analysis.New York: John Wiley,2001
[58]吴响容.模式分类特征提取中的独立分量分析.[硕士学位论文],广西:广西师范大学电路与系统专业,2005
[59]Aapo Hyvarinen,Juha Karhunen,ErkkiO ja;Ⅰ ndependentC omponentA nalysis[M].AW iley-Interscience Publication.JO HN WILEY&SONS,INC.2001
[60]A.Hyv"arinen and E Oja A fast fixed-point talgorithm for independent component analysis[J].Neural Computation,9(7):1483-1492,1997
[61]A.Hyvdrmen.Fast and Robust Fixed-Point Algorithms for Independent Component Analysis[J].IE EE Transactions on Neural Networks10(3):626-634,1999
[62]Yair Shimshoni,Nathan Intrator.Classification of seismic signals by integrating ensembles of neural networks[J].IEEE Transactions on Signal Processing,1998,46(5)1194-1201
[63]李光海,刘正义.声发射源多传感器数据融合识别技术研究.无损检测,2003,25(4):171-175
[64]程婷.多传感器数据融合算法研究.[硕士学位论文],四川:电子科技大学信号与信息处理专业,2006
[65]Seizer F,Gutfinger D.Ladar and flir based fusion for automatic target classification[J/OL].SPIE,1993.236-246
[66]Dempster AP.Upper and lower probabilities induced by a multi-valued mapping[J].Annals of Mathematical Statistics,1967,38(1):325-339
[67]刘雷健等.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
[68]张遂强,郝伟,李志农.基于全信息技术的自适应报警方法研究.机械科学与技术,2006,25(12):1499-1502
[69]史毓达,卢炎生,王黎明.基于贝叶斯决策模型的火灾报警模式识别系统应用研究.华中师范大学学报,2007,41(2):211-217
[70]Varshney P K,Chair Z.Optimal data fusion in multiple sensor detection systems.IEEE Trans.AES,1986,22(1):98-101
[71]Reibman A R,Nolte L W.Optimal detection and performance of distributed sensor systems.IEEE Trans.AES,1987,23(1):24-30
[72]Elias-Fuste A R,et al.CFAR data fusion center with inhomogeneous receivers.IEEE Trans.on AES,1992,28(1):276-284
[73]康耀红.多传感器目标检测与跟踪的数据融合理论.[硕士学位论文],西安:西安电子科技大学,1995