基于BP神经网络的柴油机热红外故障诊断方法研究
|
摘要
热红外成像技术始于上世纪50年代，由于其隐蔽性能好、安全指数高、不受电磁干扰等优点，近几年来该技术得到迅猛的发展，已经成为一门新型技术科学。以往的红外技术首先在军事领域得到应用，而现在随着热红外技术的发展日趋成熟，已成为当今各相关行业研究的热点，得到了十分广泛的应用，是当今世界高科技研究领域之一。
柴油机是一种常见的发电机，是用途非常广泛的动力机械。其耐久性和可靠性在运行过程中显得尤为重要，随着发动机内部强化程度的提高，结构也变得极为复杂，在十分恶劣的工作条件下，故障发生的可能性也会大大增加。为确保发动机的正常运行，提高其安全、可靠性，必须加强发动机运行过程中的管理，加强对发动机故障的早期预防和诊断。就如何诊断出动力设备中的故障隐患，并针对传统测试诊断方法中的接触测试的不足的问题，本文叙述了一种非接触式的测试方法，即在热红外成像技术基础上的故障诊断。
热红外技术对诊断电力系统中的故障隐患具有图像直观、不受电磁干扰、不接触探测、安全可靠、判断准确、效率高和检测速度快等特点。特别针对那些悬空的、处在高速运动中的和带电的设备更具有突出的优点。利用柴油机高速运转过程中向外界热辐射的特点，通过红外探测器摄取其温度场的红外图像，测定柴油机表面的温度分布场及其变化情况，能发现发动机可能存在的热状态异常现象并找出潜在的故障点，实现预防和诊断。
热红外图像的预处理和特征提取。在红外图像的分析中，进行图像的预处理是十分重要的一个环节，主要目的是消除图像中混入的各种噪声信号，突出真实的信息，增强有关信息的可检测性和最大限度地简化数据，为下一环节的研究提供便捷。采用中值滤波、平滑滤波、锐化滤波等算法去除图像中的的噪声信息，并用增强算法对图像进行有效的增强。利用边缘检测方法中，Roberts算子、Sober算子和正交算子或阈值分割法，对红外图像进行图像分割。在特征提取这一步研究，是图像识别的一个关键问题，对于神经网络的分类来说，核心就是利用图像的特征进行训练识别，提取的特征是诊断识别的关键。本文从图像矩、目标图像的信息熵、系数变换特征、边缘提取等角度分别讨论了红外目标图像特征提取的方法，已达到目标识别的目的。
BP神经网络。是采用误差反算法作为其学习规则进行有监督学习的前馈网络，实现了多层网络学习。当给定网络一个输入，由输入层送到隐层，经过隐层单元处理，再送到输出层，输出层单元处理后产生一个输出模式，若输出响应与期望输出模式有差距，就将误差沿着连接通路后向传播，并同时修正各层连接的权值。可将红外图像提取的特征输入BP网络进行训练。最后可通过输出判定输入的特征，最终实现目标故障的识别诊断。
Thermal infrared imaging technology began in fifties the last century, because ofgood concealment, high safety index, not subject to electromagnetic interference; itdevelops rapidly, it has become a newly developed technology recent years. Thetechnology was first used in the field of military, but, due to the development of theinfrared technology, it has been widely used in every field.
The diesel engine is a common and widely used power equipment. Its durabilityand reliability are very important during the operation process. Because of internalstructure strengthening, the fault appearing is very possible when working in the harshconditions. In order to ensure the engine working normally, improve the safety andreliability, which must strengthen the administration of the engine working and preventthe fault early. Giving the problem of how to diagnose the fault early, there is a way ofnon-contact type testing, fault diagnosis based on the thermal infrared imagingtechnology.
The technology of fault diagnosis has some advantage such as imaging visually,not subject to electromagnetic interference, non-contact type probing, being safe andreliable, judging accurately, being efficient, high-speed testing, especially applying tothe high-speed operating power equipment. The infrared detector can receive theimage information of the thermal field, when the diesel engine is operating rapidly andradiating. Then the potential fault point will be detected by the analysis of theabnormal phenomenon of the thermal field.
The pretreatment of the thermal infrared image and feature extraction. Thepretreatment is very important for the next step, because it can eliminate the noiseinformation, strengthen the effective information, by median filter, smoothing filter,sharpening filter, and strengthen the image information. Then it will divide the imageby operator like Roberts, Sober and so on. And the feature extraction is the key of theimage recognition, it will also used in the ANNs. The methods of the feature extractioninclude the image moments, the information entropy of the image, coefficient transformation characteristics, edge extraction and so on.
Back Propagation. It uses the error inverse algorithm as its learning rule forsupervised learning feedforward networks, it realize the multilayer network learning.When a given network input, the signal from input layer to the hidden layer,processed by hidden layer unit, then sent to the output layer, after processed, outputlayer unit to produce an output mode, if the output response and the expected outputmode has some differences, the error will be sent along the connection path backpropagation, at the same time to amend each layer connection weights, The featuresextracted from infrared image can be input BP network to train, finally judging thefeatures input by the output.
柴油机是一种常见的发电机，是用途非常广泛的动力机械。其耐久性和可靠性在运行过程中显得尤为重要，随着发动机内部强化程度的提高，结构也变得极为复杂，在十分恶劣的工作条件下，故障发生的可能性也会大大增加。为确保发动机的正常运行，提高其安全、可靠性，必须加强发动机运行过程中的管理，加强对发动机故障的早期预防和诊断。就如何诊断出动力设备中的故障隐患，并针对传统测试诊断方法中的接触测试的不足的问题，本文叙述了一种非接触式的测试方法，即在热红外成像技术基础上的故障诊断。
热红外技术对诊断电力系统中的故障隐患具有图像直观、不受电磁干扰、不接触探测、安全可靠、判断准确、效率高和检测速度快等特点。特别针对那些悬空的、处在高速运动中的和带电的设备更具有突出的优点。利用柴油机高速运转过程中向外界热辐射的特点，通过红外探测器摄取其温度场的红外图像，测定柴油机表面的温度分布场及其变化情况，能发现发动机可能存在的热状态异常现象并找出潜在的故障点，实现预防和诊断。
热红外图像的预处理和特征提取。在红外图像的分析中，进行图像的预处理是十分重要的一个环节，主要目的是消除图像中混入的各种噪声信号，突出真实的信息，增强有关信息的可检测性和最大限度地简化数据，为下一环节的研究提供便捷。采用中值滤波、平滑滤波、锐化滤波等算法去除图像中的的噪声信息，并用增强算法对图像进行有效的增强。利用边缘检测方法中，Roberts算子、Sober算子和正交算子或阈值分割法，对红外图像进行图像分割。在特征提取这一步研究，是图像识别的一个关键问题，对于神经网络的分类来说，核心就是利用图像的特征进行训练识别，提取的特征是诊断识别的关键。本文从图像矩、目标图像的信息熵、系数变换特征、边缘提取等角度分别讨论了红外目标图像特征提取的方法，已达到目标识别的目的。
BP神经网络。是采用误差反算法作为其学习规则进行有监督学习的前馈网络，实现了多层网络学习。当给定网络一个输入，由输入层送到隐层，经过隐层单元处理，再送到输出层，输出层单元处理后产生一个输出模式，若输出响应与期望输出模式有差距，就将误差沿着连接通路后向传播，并同时修正各层连接的权值。可将红外图像提取的特征输入BP网络进行训练。最后可通过输出判定输入的特征，最终实现目标故障的识别诊断。
Thermal infrared imaging technology began in fifties the last century, because ofgood concealment, high safety index, not subject to electromagnetic interference; itdevelops rapidly, it has become a newly developed technology recent years. Thetechnology was first used in the field of military, but, due to the development of theinfrared technology, it has been widely used in every field.
The diesel engine is a common and widely used power equipment. Its durabilityand reliability are very important during the operation process. Because of internalstructure strengthening, the fault appearing is very possible when working in the harshconditions. In order to ensure the engine working normally, improve the safety andreliability, which must strengthen the administration of the engine working and preventthe fault early. Giving the problem of how to diagnose the fault early, there is a way ofnon-contact type testing, fault diagnosis based on the thermal infrared imagingtechnology.
The technology of fault diagnosis has some advantage such as imaging visually,not subject to electromagnetic interference, non-contact type probing, being safe andreliable, judging accurately, being efficient, high-speed testing, especially applying tothe high-speed operating power equipment. The infrared detector can receive theimage information of the thermal field, when the diesel engine is operating rapidly andradiating. Then the potential fault point will be detected by the analysis of theabnormal phenomenon of the thermal field.
The pretreatment of the thermal infrared image and feature extraction. Thepretreatment is very important for the next step, because it can eliminate the noiseinformation, strengthen the effective information, by median filter, smoothing filter,sharpening filter, and strengthen the image information. Then it will divide the imageby operator like Roberts, Sober and so on. And the feature extraction is the key of theimage recognition, it will also used in the ANNs. The methods of the feature extractioninclude the image moments, the information entropy of the image, coefficient transformation characteristics, edge extraction and so on.
Back Propagation. It uses the error inverse algorithm as its learning rule forsupervised learning feedforward networks, it realize the multilayer network learning.When a given network input, the signal from input layer to the hidden layer,processed by hidden layer unit, then sent to the output layer, after processed, outputlayer unit to produce an output mode, if the output response and the expected outputmode has some differences, the error will be sent along the connection path backpropagation, at the same time to amend each layer connection weights, The featuresextracted from infrared image can be input BP network to train, finally judging thefeatures input by the output.
引文
[1].马宝琛.基于神经网络的柴油机故障诊断技术的研究[D].大连海事大学. 2008.
[2].周雪.基于红外图像的洛阳变电站电气设备诊断分析[D].河南理工大学. 2011.
[3].常瑞艳.红外成像故障诊断技术在供电站的应用研究[D].河南理工大学. 2010.
[4].朱凯，王正林.精通Matlab神经网络[M].电子工业出版社. 2010.1.
[5].黎奎，宋宇.基于特征脸和BP神经网络的人脸识别[J].计算机应用研究.2005,6:236-238.
[6].江飞虹，吴文贤，石岩.机载红外图像特征的提取与分析[J].烟台大学学报（自然科学版）. 2007,4:295-298.
[7].梁旗.基于红外热图像电力设备热故障的自动诊断[J].电脑知识与技术.2008,6:1106-1108,1114.
[8].荆文芳.飞机红外图像的检测、识别与跟踪技术研究[D].西北工业大学. 2006.
[9].王格芳，陈国顺.基于红外成像的集成电路检测与诊断[J].激光与红外.1999,5:315-317.
[10].米江，纪国宜.基于改进BP神经网络的风机故障诊断研究[J].发电设备.2010,6:430-434.
[11].杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社. 2001: 41-62,183-201.
[12].张学工，边肇祺等.模式识别（第二版）[M].北京:清华大学出版社. 2000.1:1-100.
[13].李大鹏，张利群，赵岩松.红外无损检测中的裂纹特征提取和图形重建方法研究[J].计算机测量与控制. 2005,13(7):624-626,682.
[14].韩军利.红外图像目标识别技术研究[D].南京理工大学. 2004.
[15].王甜.红外成像制导前视匹配目标识别方法研究[D].华中科技大学. 2006.
[16].邹前进，冯亮，汪亚.红外图像空间噪声分析和预处理方法改进[J].应用光学.2007,7: 426-430.
[17].石晓光.红外辐射测温精度与误差分析[D].长春理工大学. 2006.
[18].张秀凤，娄树理，张燕妮.红外图像模式识别的预处理研究[J].光电技术应用.2006.10:58-60.
[19].沈庭芝，王卫江，闫雪梅.数字图象处理与模式识别[M].北京:北京理工大学出版社. 2007.7:39-69.
[20].王自勇，廖朝佩.红外图像自动目标识别技术进展[J].飞航导弹. 1996,7:41-48.
[21].卢瑞祥，牟轩沁，纪震.一种基于红外图像识别的自动消防监控系统[J].电子技术应用. 1998,2:7-8.
[22].周东华，王桂增.故障诊断技术综述[J].化工自动化和仪表. 1998,1:58-63.
[23].孙即祥，王晓华等.模式识别中的特征提取与计算机视觉不变量[M].北京:国防工业出版社. 2001.
[24].魏伟波，芮筱亭.不变矩方法研究[J].火力与指挥控制. 2007,11.
[25].李了了，邓善熙，丁兴号.基于大津法的图像分块二值化算法[J].微计算机信息.2005,24:57-61.
[26].陈东，黄勇杰，沈振康.基于尺度奇异值变换的红外图像目标特征提取方法研究[J].红外与激光工程. 2001,6:157-159.
[27].Hu.M. Visual Pattern Recognition By Moment Invariants[J]. IRE Trans. Inform. Theory,1962,8:179-187.
[28].Y R Wong. Scene Matching With Invariant Moment[J]. Computer Graphics And ImageProcessing. 1978,8:16-24.
[29].肖斌.基于不变矩的图像几何变换不变性识别研究[D].陕西师范大学. 2007.4.
[30].翟俊海，赵文秀，王熙照.图像特征提取研究[J].河北大学学报（自然科学版）.2009,1:106-112.
[31].付立冬，姜学军，谭小波.红外图像特征提取方法研究[J].科技信息.2009,15:495,473.
[32].李月景等.图像识别技术及其应用[M].北京:机械工业出版社. 1985.
[33].蒋先刚.数字图像模式识别工程软件设计[M]. 2008.4.
[34].沈功田，张万岭.压力容器无损检测——红外热成像技术[J].压力容器.2004,10:523-528.
[35].华顺刚，曾令宜，苏铁明，周羽.基于线性降维技术和BP神经网络的热红外人脸图像识别[J].大连理工大学学报. 2010,1:62-66.
[36].周茵.红外测温技术在电力设备故障诊断中的应用[J].电力系统装备. 2003,9:24-25.
[37].何苗等. BP小波神经网络自适应调节步长的改进算法[J].济南大学学报（自然科学版）. 2001,4:315-318.
[38].董辉.基于神经网络的图像识别系统的研究[D].西南农业大学. 2005.5.
[39].董俊.基于神经网络的图像复原算法研究[D].西安科技大学. 2009.4.
[40].杨晓.红外图像的目标识别技术研究[D].中北大学. 2009.
[41].王静伟. BP神经网络改进算法的研究[J].中国水运. 2008,1:157-158.
[42].戚德虎，康继昌. BP神经网络的设计[J].计算机工程与设计. 1998,4:48-50.
[43].Ya hia A H. Infrared thermal mapping of microelectronic circuits[J]. SPIE.1985,590:148-244..
[44].Dorigo M. Gambardella L.M. Ant colony system:a cooperative learning approach to thetraveling salesman problem[J]. IEEE Transaction on Evolutionary Computing. 1997,1:53.
[45].Venkatesh Y V, Raja S K. On the Classification of Multispectral Satellite Images Usingthe Multilayer Perceptron[J]. Pattern Recognition. 2003,36:2161-2175.
[46].Avcibas I.,Sankur B.,Sayood K. Statistical evaluation of image quality measures[J].Journal of Electronic Imaging. 2002,2:206-223.
[47].Shang G, Zhong L,Chen L. Discussion about BP Neural Network Structure and Choiceof Samples Training Parameter[J]. Journal of Wuhan University of Technology. 1997.
[48].杨伟，倪黔东，吴军基. BP神经网络权值初始值与收敛性的研究[J].电力系统及其自动化学报. 2002,(2):20-22.
[49].牟世刚.车辆车型与车牌识别系统的研究[D].山东大学. 2007.
[50].许锋，卢建刚，孙优贤.神经网络在图像处理中的应用[J].信息与控制.2003,32(4):344-351.
[51].李洪霞.红外热像仪在人体病灶诊断技术中的应用[D].中北大学. 2010.
[52].王格芳，王学明，陈国顺，贾志军.基于神经网络的红外诊断系统研究[J].红外与激光工程. 2002,6:526-529.
[53].ZhuYongliYang,YH,Gogg B Wet a1.An expert system for power system faultanalysis[J].IEEE.Transaction on Power Delivery, 1992,7(1):43-46.
[54].Carter Chris F,Cross Nicola.Combustion monitoring using infrared array-baseddetectors[J].Measurement Science and Technology, 2003,2(3):26-31.
[55].AKhotanzad, Y. H. Hong. Invariant image recognition by Zernike moments[J]. IEEETrans. Pattern Anal. Mach. Intell, 1990,12(5):489-497.
[56]. C.H.Teh, R.T.Chin. On image analysis by the methods fo moment[J]. IEEE Trans.Pattern Anal. Mach. Intell , 1988,10(4):496-513.
[57].M.R.Teague. Image analysis via the general theary of moment[J]. J.Opt.Soc, 1980,70(8):920-930.
[58].Breiter R.Recent development for high-performance staring IR imaging modules[J].SPIE, 1998,3379: 344–353.
[59].Luo Zilai.Researeh on Fault Diagnosis Method of Diesel Engine Based on BPNetwork[J]. VehieheEngine, 2008.6(176):119-123.
[60].Kurdur D.Hazinokos D.A novel blind deconvolution scheme for image restoration usingrecursive filtering[J]. IEEE Transactions on Signal Processing, 1998,46(2):156～161.
[61].Banham Mark M,Katsaggelos A K.Digital image restoration[J]. IEEE Signal ProcessingMagazine, 1997,14(3):24～41.
[62].A.Benediktsson,H.Swain,K.Ersoy.Neural Network Approaches Versus StatisticalMethods in Classification of Multi Source Remote Sensing Data[J]. IEEE Transactions onGeosciences and Remote Sensing, 1990,28(4):540-552.
[2].周雪.基于红外图像的洛阳变电站电气设备诊断分析[D].河南理工大学. 2011.
[3].常瑞艳.红外成像故障诊断技术在供电站的应用研究[D].河南理工大学. 2010.
[4].朱凯，王正林.精通Matlab神经网络[M].电子工业出版社. 2010.1.
[5].黎奎，宋宇.基于特征脸和BP神经网络的人脸识别[J].计算机应用研究.2005,6:236-238.
[6].江飞虹，吴文贤，石岩.机载红外图像特征的提取与分析[J].烟台大学学报（自然科学版）. 2007,4:295-298.
[7].梁旗.基于红外热图像电力设备热故障的自动诊断[J].电脑知识与技术.2008,6:1106-1108,1114.
[8].荆文芳.飞机红外图像的检测、识别与跟踪技术研究[D].西北工业大学. 2006.
[9].王格芳，陈国顺.基于红外成像的集成电路检测与诊断[J].激光与红外.1999,5:315-317.
[10].米江，纪国宜.基于改进BP神经网络的风机故障诊断研究[J].发电设备.2010,6:430-434.
[11].杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社. 2001: 41-62,183-201.
[12].张学工，边肇祺等.模式识别（第二版）[M].北京:清华大学出版社. 2000.1:1-100.
[13].李大鹏，张利群，赵岩松.红外无损检测中的裂纹特征提取和图形重建方法研究[J].计算机测量与控制. 2005,13(7):624-626,682.
[14].韩军利.红外图像目标识别技术研究[D].南京理工大学. 2004.
[15].王甜.红外成像制导前视匹配目标识别方法研究[D].华中科技大学. 2006.
[16].邹前进，冯亮，汪亚.红外图像空间噪声分析和预处理方法改进[J].应用光学.2007,7: 426-430.
[17].石晓光.红外辐射测温精度与误差分析[D].长春理工大学. 2006.
[18].张秀凤，娄树理，张燕妮.红外图像模式识别的预处理研究[J].光电技术应用.2006.10:58-60.
[19].沈庭芝，王卫江，闫雪梅.数字图象处理与模式识别[M].北京:北京理工大学出版社. 2007.7:39-69.
[20].王自勇，廖朝佩.红外图像自动目标识别技术进展[J].飞航导弹. 1996,7:41-48.
[21].卢瑞祥，牟轩沁，纪震.一种基于红外图像识别的自动消防监控系统[J].电子技术应用. 1998,2:7-8.
[22].周东华，王桂增.故障诊断技术综述[J].化工自动化和仪表. 1998,1:58-63.
[23].孙即祥，王晓华等.模式识别中的特征提取与计算机视觉不变量[M].北京:国防工业出版社. 2001.
[24].魏伟波，芮筱亭.不变矩方法研究[J].火力与指挥控制. 2007,11.
[25].李了了，邓善熙，丁兴号.基于大津法的图像分块二值化算法[J].微计算机信息.2005,24:57-61.
[26].陈东，黄勇杰，沈振康.基于尺度奇异值变换的红外图像目标特征提取方法研究[J].红外与激光工程. 2001,6:157-159.
[27].Hu.M. Visual Pattern Recognition By Moment Invariants[J]. IRE Trans. Inform. Theory,1962,8:179-187.
[28].Y R Wong. Scene Matching With Invariant Moment[J]. Computer Graphics And ImageProcessing. 1978,8:16-24.
[29].肖斌.基于不变矩的图像几何变换不变性识别研究[D].陕西师范大学. 2007.4.
[30].翟俊海，赵文秀，王熙照.图像特征提取研究[J].河北大学学报（自然科学版）.2009,1:106-112.
[31].付立冬，姜学军，谭小波.红外图像特征提取方法研究[J].科技信息.2009,15:495,473.
[32].李月景等.图像识别技术及其应用[M].北京:机械工业出版社. 1985.
[33].蒋先刚.数字图像模式识别工程软件设计[M]. 2008.4.
[34].沈功田，张万岭.压力容器无损检测——红外热成像技术[J].压力容器.2004,10:523-528.
[35].华顺刚，曾令宜，苏铁明，周羽.基于线性降维技术和BP神经网络的热红外人脸图像识别[J].大连理工大学学报. 2010,1:62-66.
[36].周茵.红外测温技术在电力设备故障诊断中的应用[J].电力系统装备. 2003,9:24-25.
[37].何苗等. BP小波神经网络自适应调节步长的改进算法[J].济南大学学报（自然科学版）. 2001,4:315-318.
[38].董辉.基于神经网络的图像识别系统的研究[D].西南农业大学. 2005.5.
[39].董俊.基于神经网络的图像复原算法研究[D].西安科技大学. 2009.4.
[40].杨晓.红外图像的目标识别技术研究[D].中北大学. 2009.
[41].王静伟. BP神经网络改进算法的研究[J].中国水运. 2008,1:157-158.
[42].戚德虎，康继昌. BP神经网络的设计[J].计算机工程与设计. 1998,4:48-50.
[43].Ya hia A H. Infrared thermal mapping of microelectronic circuits[J]. SPIE.1985,590:148-244..
[44].Dorigo M. Gambardella L.M. Ant colony system:a cooperative learning approach to thetraveling salesman problem[J]. IEEE Transaction on Evolutionary Computing. 1997,1:53.
[45].Venkatesh Y V, Raja S K. On the Classification of Multispectral Satellite Images Usingthe Multilayer Perceptron[J]. Pattern Recognition. 2003,36:2161-2175.
[46].Avcibas I.,Sankur B.,Sayood K. Statistical evaluation of image quality measures[J].Journal of Electronic Imaging. 2002,2:206-223.
[47].Shang G, Zhong L,Chen L. Discussion about BP Neural Network Structure and Choiceof Samples Training Parameter[J]. Journal of Wuhan University of Technology. 1997.
[48].杨伟，倪黔东，吴军基. BP神经网络权值初始值与收敛性的研究[J].电力系统及其自动化学报. 2002,(2):20-22.
[49].牟世刚.车辆车型与车牌识别系统的研究[D].山东大学. 2007.
[50].许锋，卢建刚，孙优贤.神经网络在图像处理中的应用[J].信息与控制.2003,32(4):344-351.
[51].李洪霞.红外热像仪在人体病灶诊断技术中的应用[D].中北大学. 2010.
[52].王格芳，王学明，陈国顺，贾志军.基于神经网络的红外诊断系统研究[J].红外与激光工程. 2002,6:526-529.
[53].ZhuYongliYang,YH,Gogg B Wet a1.An expert system for power system faultanalysis[J].IEEE.Transaction on Power Delivery, 1992,7(1):43-46.
[54].Carter Chris F,Cross Nicola.Combustion monitoring using infrared array-baseddetectors[J].Measurement Science and Technology, 2003,2(3):26-31.
[55].AKhotanzad, Y. H. Hong. Invariant image recognition by Zernike moments[J]. IEEETrans. Pattern Anal. Mach. Intell, 1990,12(5):489-497.
[56]. C.H.Teh, R.T.Chin. On image analysis by the methods fo moment[J]. IEEE Trans.Pattern Anal. Mach. Intell , 1988,10(4):496-513.
[57].M.R.Teague. Image analysis via the general theary of moment[J]. J.Opt.Soc, 1980,70(8):920-930.
[58].Breiter R.Recent development for high-performance staring IR imaging modules[J].SPIE, 1998,3379: 344–353.
[59].Luo Zilai.Researeh on Fault Diagnosis Method of Diesel Engine Based on BPNetwork[J]. VehieheEngine, 2008.6(176):119-123.
[60].Kurdur D.Hazinokos D.A novel blind deconvolution scheme for image restoration usingrecursive filtering[J]. IEEE Transactions on Signal Processing, 1998,46(2):156～161.
[61].Banham Mark M,Katsaggelos A K.Digital image restoration[J]. IEEE Signal ProcessingMagazine, 1997,14(3):24～41.
[62].A.Benediktsson,H.Swain,K.Ersoy.Neural Network Approaches Versus StatisticalMethods in Classification of Multi Source Remote Sensing Data[J]. IEEE Transactions onGeosciences and Remote Sensing, 1990,28(4):540-552.