小波分析提取JEM特征及GA-BP分类算法
|
摘要
常规防空雷达受其固有低重复频率等性能的影响,将其应用于飞机目标自动分类与识别的问题一直是目标识别研究领域的难点。目前,国内装备有大量的常规防空雷达,如果能在常规防空雷达目标识别上取得突破,将具有重大的军事与经济意义。如何准确实时地提取飞机目标的有效特征并对多传感器信息准确融合是解决目标自动分类与识别问题的关键技术。本文的主要工作是研究了小波分析提取飞机目标发动机周期调制特征的方法以及构造实现飞机目标分类识别的智能化类型融合模型和算法。
由于飞机旋转部件对雷达电磁波的调制,目标回波会产生周期调制特征。常规防空雷达可以提取周期调制特征来分类、识别。由于传统提取方法如复倒谱法、无偏自相关估计、AR功率谱法等或者要求雷达有较高重复频率或者存在提取误差大、计算量大等缺点。本文通过对直升机、螺旋桨飞机和涡扇喷气飞机回波调制特性参数模型的研究,分析了这三类飞机所产生的回波信号特点。提出采用小波分析方法有效获取目标回波的周期调制特征,并详细分析了小波基的选取和几个重要雷达参数对其提取结果的影响并给出相应的仿真试验结论。
在多传感器信息融合方面,本文采用了基于多级神经网络的融合模型。该模型分为传感器子网和融合子网。传感器子网通过多个传感器获得的目标特征信息,实现对各类目标类型的置信度分配。融合子网将结合各传感器子网的置信度对各传感器子网的输出结果进行融合,最终得到对目标类型的判断。本文重点研究了该多级神经网络融合模型中传感器子网的模型和算法。采用了一种基于专家规则的模糊神经网络,网络结构和各个节点都有确切的含义。并改进其算法——将改进的遗传算法与传统后向传播算法结合得到性能更优的GA-BP分类算法并应用该算法对网络进行了训练和检测。
Because of the influences of some inherent performances, such as low repeat frequency, it is always very difficult to apply convention air defense radars to airplane goal automatic sorting and recognition in the target identification research area. At present, massive convention air defense radars are equipped in domestic. Obtaining the breakthrough in the convention air defense radar's target identification will have momentous military and economical significance. Extracting valid airplane goal characteristics exactly and rapidly from the echo and multi-sensor information fusion are two pivotal techniques. The prime tasks of this paper are airplane periodic signature of modulation extraction with wavelet decomposition as well as structuring intellectualized type fusion model and algorithm of target identification.
Because the airplane’s revolving part can have cyclical modulation feature to the radar electromagnetic wave modulation, convention air defense radar could extract periodic signature of modulation to distinguish airplanes of different types effectively. There are some disadvantages in conventional extract methods, such as differential cepstrum analysis, estimate of unbiased autocorrelation, AR power spectrum and so on. Some need high radar repeat frequency, some have biggish error and some have to do a mass of computation. According to the research of modulating feature parameter model of helicopter, propeller-driven aircraft and turbofan jet airplanes’echo, in this paper, we analyze the echo signal feature and put forward the algorithm of extracting target echo's periodic signature of modulation by wavelet analysis. In this paper, we also discuss the question of how to choose appropriate wavelet function and the influence of several radar parameters to the result of extract in detail and give corresponding results and conclusions of simulations.
In the aspect of multi-sensor information fusion, a multistage neural network fusion system based on neural network, fuzzy reasoning and expert system will be used. The neural network includes sensor subnet and fusion subnet. The sensor subnet obtains target feature informations through many sensors and gives the likelihood of every target type. The fusion subnet unifies each sensor's confidence level to fulfill fusion task with the output results of sensor subnet and finally distinguishes the type of target. This paper puts emphasis on the model and algorithm of sensor subnet of the multistage neural network fusion system. The sensor subnet is one kind of fuzzy neural network based on expert rules. The architecture and each node of the network all have accurate meanings. Also in this paper, the algorithm of the sensor subnet will be optimized, the genetic algorithm optimized and back propagation algorithm will be fused to obtain a new algorithm named GA-BP algorithm which has more excellent performances. At last the sensor subnet will be trained and tested with this algorithm.
由于飞机旋转部件对雷达电磁波的调制,目标回波会产生周期调制特征。常规防空雷达可以提取周期调制特征来分类、识别。由于传统提取方法如复倒谱法、无偏自相关估计、AR功率谱法等或者要求雷达有较高重复频率或者存在提取误差大、计算量大等缺点。本文通过对直升机、螺旋桨飞机和涡扇喷气飞机回波调制特性参数模型的研究,分析了这三类飞机所产生的回波信号特点。提出采用小波分析方法有效获取目标回波的周期调制特征,并详细分析了小波基的选取和几个重要雷达参数对其提取结果的影响并给出相应的仿真试验结论。
在多传感器信息融合方面,本文采用了基于多级神经网络的融合模型。该模型分为传感器子网和融合子网。传感器子网通过多个传感器获得的目标特征信息,实现对各类目标类型的置信度分配。融合子网将结合各传感器子网的置信度对各传感器子网的输出结果进行融合,最终得到对目标类型的判断。本文重点研究了该多级神经网络融合模型中传感器子网的模型和算法。采用了一种基于专家规则的模糊神经网络,网络结构和各个节点都有确切的含义。并改进其算法——将改进的遗传算法与传统后向传播算法结合得到性能更优的GA-BP分类算法并应用该算法对网络进行了训练和检测。
Because of the influences of some inherent performances, such as low repeat frequency, it is always very difficult to apply convention air defense radars to airplane goal automatic sorting and recognition in the target identification research area. At present, massive convention air defense radars are equipped in domestic. Obtaining the breakthrough in the convention air defense radar's target identification will have momentous military and economical significance. Extracting valid airplane goal characteristics exactly and rapidly from the echo and multi-sensor information fusion are two pivotal techniques. The prime tasks of this paper are airplane periodic signature of modulation extraction with wavelet decomposition as well as structuring intellectualized type fusion model and algorithm of target identification.
Because the airplane’s revolving part can have cyclical modulation feature to the radar electromagnetic wave modulation, convention air defense radar could extract periodic signature of modulation to distinguish airplanes of different types effectively. There are some disadvantages in conventional extract methods, such as differential cepstrum analysis, estimate of unbiased autocorrelation, AR power spectrum and so on. Some need high radar repeat frequency, some have biggish error and some have to do a mass of computation. According to the research of modulating feature parameter model of helicopter, propeller-driven aircraft and turbofan jet airplanes’echo, in this paper, we analyze the echo signal feature and put forward the algorithm of extracting target echo's periodic signature of modulation by wavelet analysis. In this paper, we also discuss the question of how to choose appropriate wavelet function and the influence of several radar parameters to the result of extract in detail and give corresponding results and conclusions of simulations.
In the aspect of multi-sensor information fusion, a multistage neural network fusion system based on neural network, fuzzy reasoning and expert system will be used. The neural network includes sensor subnet and fusion subnet. The sensor subnet obtains target feature informations through many sensors and gives the likelihood of every target type. The fusion subnet unifies each sensor's confidence level to fulfill fusion task with the output results of sensor subnet and finally distinguishes the type of target. This paper puts emphasis on the model and algorithm of sensor subnet of the multistage neural network fusion system. The sensor subnet is one kind of fuzzy neural network based on expert rules. The architecture and each node of the network all have accurate meanings. Also in this paper, the algorithm of the sensor subnet will be optimized, the genetic algorithm optimized and back propagation algorithm will be fused to obtain a new algorithm named GA-BP algorithm which has more excellent performances. At last the sensor subnet will be trained and tested with this algorithm.
引文
1孙文峰.雷达目标识别技术评述.雷达与对抗. 2001, (3):1~8
2王晓丹.王积勤.雷达目标识别技术综述.现代雷达. 2003, (5):22~26
3 George Linde. Use of Wideband Waveforms for Target Recognition with Surveillance Radars. Proceedings of IEEE International Radar Conference. 2000:128~133
4丁建江,张贤达.低分辨雷达目标智能识别的最新进展.现代雷达. 2002, (3):1~4
5 R. Hynesr. Doppler Spectra of S Band and X Band Signals. Supplement to IEEE Trans. on AES. 1976, 3(6):356~365
6 M. Jean. Studies Relating to the Detailed Structure of Aircraft Echoes. Atlanta:IEEE ICR. 1984:275~280
7 G. G. Fliss, D. L. Mensa. Instrumentation for RCS Measurements of Modulation Spectral of Aircraft Blades [A]. Proceedings of the IEEE National Radar Conference[C]. Los Angeles:IEEE AES Society. 1986:95~98
8 J. Martin, B. Mulgrew. Analysis of the Theoretical Return Signal from Aircraft Blades [A]. Proceedings of IEEE International Conference on Radar [C]. Washington. 1990:569~572
9 J. Martin, B. Mulgrew. Analysis of the Effects of Blade Pitch on The Radar Return Signal from Rotating Aircraft Blades [A]. Proceedings of IEEE International Conference on Radar [C]. London:IEEE ICR. 1992: 446~449
10 S. Y. Yang, S. M. Yeh. Electromagnetic Backscattering from Aircraft Propeller Blades [J ]. IEEE Trans. on Magnetics. 1997, 33 (3):1432~1435
11 Y. S. Sun, N. H. Myung. Analysis of electromagnetic scattering by a rotating rotor with flat blades [A]. Proceedings of IEEE ICCS - 94[C]. Singapore: IEEE ICCS. 1994:1044~1048
12 I. Tardy, G. P. Pisu. P. Chabrat. Computational and experimental analysis of the scattering by rotating fans [J]. IEEE Trans. on AP. 1996, 44 (10):1414~1421
13 H. Luo, P. K. Huang, X J Xu. Doppler Modulated Features Modeling and Radar Target Recognition [A]. Proceedings of SPIE, Vol. 3069 [C]. Washington:International Society for Optical Engineering . 1997:486~493
14 V. C. Chen. Radar Signatures of Rotor Blades [A]. Proceedings of SPIE, 4391[C]. Washington:International Society for Optical Engineering. 2001:63~70
15 D B Barry, P C Dowdy. Pulse Doppler Signature of a Rotary-wing Aircraft [J]. IEEE AES System Magazine. 1991, 6(5):28~31
16 M. R. Bell, R. A. Grubbs. JEM Modeling and Measurement for Radar Target Classification [J]. IEEE Trans. on AES. 1993, 29(11):73~87
17朱张帆,丁建江,阮崇籍.基于小波分析的JEM特征提取与应用.雷达与对抗. 2006, (1):39~42
18杨万海.多传感器数据融合及其应用.西安电子科技大学出版社. 2004:46~98
19张乃尧,阎平凡.神经网络与模糊控制.清华大学出版社. 2004:102~120
20孙宝深,时银水,朱岩.基于模糊神经网络的目标识别.电光与控制. 2005, 3(6):50~54
21曲晓慧,安钢.数据融合方法技术及展望.船舶电子工程2003, (2):2~5
22陈绍顺,王君.基于前向型神经网络的空袭目标类型识别模型.现代防御技术. 2002, 30(2):57~60
23李方社,王宝树.神经网络技术在数据融合中的应用.西安电子科技大学学报. 1998, 25(60):790~793
24 Bogdan Gabrys, Andrzej Bargiela. General Fuzzy Min-Max Neural Network for Clustering and Classification. IEEE Trans. On Neural Network. 2000, 11(3): 769~783
25 Yan-Qing Zhang, Fu-lai Chung. A Fuzzy Neural Tree with Heuristic Backprogapation Learning. IEEE. 2002:553~558
26邹慧,管振辉.侦察机识别库的一种设计方案.船舶电子对抗. 1997, (3): 10~13
27王平安,姜宁.专家系统在电子对抗中的应用.航天电子对抗. 2000, (4): 46~48
28 Motohide Umano, Itsuo Hatono, Hiroyuki Tamura. Fuzzy Expert System Shells. IEEE. 1994:219~225
29 Hideyuki, Osamu. The Recognition of Facial Expression Based on Fuzzy Expert System. IEEE. 1998:565~568
30高尚,刘铭.基于MATLAB模糊逻辑工具箱的目标类型识别.航空计算技术. 2002, 32(1): 52~54
31王振.基于有源无源特征的飞机目标识别研究.哈尔滨工业大学硕士论文. 2006:49~57
32 Christiaan Pemeel, Jean-Michel Renders, Marc Acheroy. Optimization of Fuzzy Systems Using Genetic Algorithms and Neural Networks. IEEE Trans. On Fuzzy systems. 1995, 3(3):300~311
33 Ric C.C.Tsang, Daniel S.Yeung. Optimizing Fuzzy Knowledge Base by Genetic Algorithms and Neural Networks. IEEE. 1999, 367~37
34 Fu-Lai Chung, ji-Cheng Duan. On Multistage Fuzzy Neural Network Modeling. IEEE Trans. On Fuzzy systems. 2000, 8(2):125~141
35 Shi-Feng Juang, Chin-Teng Lin. An On-Line self-Constructing Neural Fuzzy Inference Network and Its Applications. IEEE Trans. On Fuzzy Systems. 1998, 6(1):12~32
36王崇骏,于汶滁,陈兆乾,谢俊元.一种基于遗传算法的BP神经网络算法及其应用.南京大学学报. 2003, 9(5):439~464
37贺素良,王湘中,喻寿益.遗传算法及神经网络融合技术的研究.计算机工. 2003, 5(7):17~19
38温泉彻,彭宏.一种自适应遗传BP神经网络模型研究及应用.计算机仿真. 2006, (12):160~162
39 J. Martin, B. Mulgrew, Analysis of the Effects of Blade Pitch on the Radar Return Signal from Rotating Aircraft Blades, 1992 IEE International Radar Conference, London (UK), IEE Conference Publication 365. 1992, 446~449
40丁建江,张贤达,吕金建.常规雷达飞机回波调制特性的建模.系统工程与电子技术. 2003, 25(11):1407~1410
41 Albert Boggess, Francis J. Narcowic.小波与傅里叶分析基础.电子工业出版社. 2004: 144~169
42 Y. Meyer, R. Coifman.《小波与算子》第1卷小波,世界图书出版社. 1992, (6):1~4
43汪新凡.小波基选择极其优化.株洲工学院学报. 2003, 17(5):33~35
44房文静,范宜仁,邓少贵,李霞.测井多尺度方法中最优小波基的选取.煤田地质与勘探. 2006, 34(4):71~73
45周盛.航空螺旋桨与桨扇.国防工业出版社. 1994
46孙增圻.智能控制理论与技术.清华大学出版社. 1997, 345~372
47 David E Goldberg.Genetic Algorithms in Search Optimization and MachineLearning [M]. Goldberh. 1989
48田莹,苑玮琦.遗传算法在图像处理中的应用.中国图像图形学报. 2007, 12(3):389~396
49李陶深.人工智能.重庆大学出版社. 2002:246~264
50张葛祥,胡来招,金炜东.基于熵特征的雷达辐射源信号识别.电波科学学报. 2005, 20(4):440~445
2王晓丹.王积勤.雷达目标识别技术综述.现代雷达. 2003, (5):22~26
3 George Linde. Use of Wideband Waveforms for Target Recognition with Surveillance Radars. Proceedings of IEEE International Radar Conference. 2000:128~133
4丁建江,张贤达.低分辨雷达目标智能识别的最新进展.现代雷达. 2002, (3):1~4
5 R. Hynesr. Doppler Spectra of S Band and X Band Signals. Supplement to IEEE Trans. on AES. 1976, 3(6):356~365
6 M. Jean. Studies Relating to the Detailed Structure of Aircraft Echoes. Atlanta:IEEE ICR. 1984:275~280
7 G. G. Fliss, D. L. Mensa. Instrumentation for RCS Measurements of Modulation Spectral of Aircraft Blades [A]. Proceedings of the IEEE National Radar Conference[C]. Los Angeles:IEEE AES Society. 1986:95~98
8 J. Martin, B. Mulgrew. Analysis of the Theoretical Return Signal from Aircraft Blades [A]. Proceedings of IEEE International Conference on Radar [C]. Washington. 1990:569~572
9 J. Martin, B. Mulgrew. Analysis of the Effects of Blade Pitch on The Radar Return Signal from Rotating Aircraft Blades [A]. Proceedings of IEEE International Conference on Radar [C]. London:IEEE ICR. 1992: 446~449
10 S. Y. Yang, S. M. Yeh. Electromagnetic Backscattering from Aircraft Propeller Blades [J ]. IEEE Trans. on Magnetics. 1997, 33 (3):1432~1435
11 Y. S. Sun, N. H. Myung. Analysis of electromagnetic scattering by a rotating rotor with flat blades [A]. Proceedings of IEEE ICCS - 94[C]. Singapore: IEEE ICCS. 1994:1044~1048
12 I. Tardy, G. P. Pisu. P. Chabrat. Computational and experimental analysis of the scattering by rotating fans [J]. IEEE Trans. on AP. 1996, 44 (10):1414~1421
13 H. Luo, P. K. Huang, X J Xu. Doppler Modulated Features Modeling and Radar Target Recognition [A]. Proceedings of SPIE, Vol. 3069 [C]. Washington:International Society for Optical Engineering . 1997:486~493
14 V. C. Chen. Radar Signatures of Rotor Blades [A]. Proceedings of SPIE, 4391[C]. Washington:International Society for Optical Engineering. 2001:63~70
15 D B Barry, P C Dowdy. Pulse Doppler Signature of a Rotary-wing Aircraft [J]. IEEE AES System Magazine. 1991, 6(5):28~31
16 M. R. Bell, R. A. Grubbs. JEM Modeling and Measurement for Radar Target Classification [J]. IEEE Trans. on AES. 1993, 29(11):73~87
17朱张帆,丁建江,阮崇籍.基于小波分析的JEM特征提取与应用.雷达与对抗. 2006, (1):39~42
18杨万海.多传感器数据融合及其应用.西安电子科技大学出版社. 2004:46~98
19张乃尧,阎平凡.神经网络与模糊控制.清华大学出版社. 2004:102~120
20孙宝深,时银水,朱岩.基于模糊神经网络的目标识别.电光与控制. 2005, 3(6):50~54
21曲晓慧,安钢.数据融合方法技术及展望.船舶电子工程2003, (2):2~5
22陈绍顺,王君.基于前向型神经网络的空袭目标类型识别模型.现代防御技术. 2002, 30(2):57~60
23李方社,王宝树.神经网络技术在数据融合中的应用.西安电子科技大学学报. 1998, 25(60):790~793
24 Bogdan Gabrys, Andrzej Bargiela. General Fuzzy Min-Max Neural Network for Clustering and Classification. IEEE Trans. On Neural Network. 2000, 11(3): 769~783
25 Yan-Qing Zhang, Fu-lai Chung. A Fuzzy Neural Tree with Heuristic Backprogapation Learning. IEEE. 2002:553~558
26邹慧,管振辉.侦察机识别库的一种设计方案.船舶电子对抗. 1997, (3): 10~13
27王平安,姜宁.专家系统在电子对抗中的应用.航天电子对抗. 2000, (4): 46~48
28 Motohide Umano, Itsuo Hatono, Hiroyuki Tamura. Fuzzy Expert System Shells. IEEE. 1994:219~225
29 Hideyuki, Osamu. The Recognition of Facial Expression Based on Fuzzy Expert System. IEEE. 1998:565~568
30高尚,刘铭.基于MATLAB模糊逻辑工具箱的目标类型识别.航空计算技术. 2002, 32(1): 52~54
31王振.基于有源无源特征的飞机目标识别研究.哈尔滨工业大学硕士论文. 2006:49~57
32 Christiaan Pemeel, Jean-Michel Renders, Marc Acheroy. Optimization of Fuzzy Systems Using Genetic Algorithms and Neural Networks. IEEE Trans. On Fuzzy systems. 1995, 3(3):300~311
33 Ric C.C.Tsang, Daniel S.Yeung. Optimizing Fuzzy Knowledge Base by Genetic Algorithms and Neural Networks. IEEE. 1999, 367~37
34 Fu-Lai Chung, ji-Cheng Duan. On Multistage Fuzzy Neural Network Modeling. IEEE Trans. On Fuzzy systems. 2000, 8(2):125~141
35 Shi-Feng Juang, Chin-Teng Lin. An On-Line self-Constructing Neural Fuzzy Inference Network and Its Applications. IEEE Trans. On Fuzzy Systems. 1998, 6(1):12~32
36王崇骏,于汶滁,陈兆乾,谢俊元.一种基于遗传算法的BP神经网络算法及其应用.南京大学学报. 2003, 9(5):439~464
37贺素良,王湘中,喻寿益.遗传算法及神经网络融合技术的研究.计算机工. 2003, 5(7):17~19
38温泉彻,彭宏.一种自适应遗传BP神经网络模型研究及应用.计算机仿真. 2006, (12):160~162
39 J. Martin, B. Mulgrew, Analysis of the Effects of Blade Pitch on the Radar Return Signal from Rotating Aircraft Blades, 1992 IEE International Radar Conference, London (UK), IEE Conference Publication 365. 1992, 446~449
40丁建江,张贤达,吕金建.常规雷达飞机回波调制特性的建模.系统工程与电子技术. 2003, 25(11):1407~1410
41 Albert Boggess, Francis J. Narcowic.小波与傅里叶分析基础.电子工业出版社. 2004: 144~169
42 Y. Meyer, R. Coifman.《小波与算子》第1卷小波,世界图书出版社. 1992, (6):1~4
43汪新凡.小波基选择极其优化.株洲工学院学报. 2003, 17(5):33~35
44房文静,范宜仁,邓少贵,李霞.测井多尺度方法中最优小波基的选取.煤田地质与勘探. 2006, 34(4):71~73
45周盛.航空螺旋桨与桨扇.国防工业出版社. 1994
46孙增圻.智能控制理论与技术.清华大学出版社. 1997, 345~372
47 David E Goldberg.Genetic Algorithms in Search Optimization and MachineLearning [M]. Goldberh. 1989
48田莹,苑玮琦.遗传算法在图像处理中的应用.中国图像图形学报. 2007, 12(3):389~396
49李陶深.人工智能.重庆大学出版社. 2002:246~264
50张葛祥,胡来招,金炜东.基于熵特征的雷达辐射源信号识别.电波科学学报. 2005, 20(4):440~445