基于模型修正和神经网络的复合材料结构健康监测研究
|
摘要
在利用神经网络进行复合材料结构健康监测的研究中,一些学者只从纯数值仿真角度验证了神经网络的模型辨识能力,并没有进行实验验证,而缺少实验依据的纯粹计算机仿真没有足够的说服力;也有一些学者通过实验采集各种损伤情况的特征信息,以此构建训练样本,但是单纯依靠实验方法获取大量训练样本是非常困难的。鉴于上述情况,本文提出借助模型修正技术,结合模态分析实验结果自动校正有限元模型,从而建立一个较为符合实际情况的数学模型,由修正后的有限元模型得到的各种损伤情况下结构的特征信息,以此构建神经网络的训练样本。
本文制备了两个碳纤维增强复合材料试验件,并进行了模态分析实验,测得两个试验件的前五阶弯曲模态频率;根据复合材料结构力学以及边界条件的近似处理建立了复合材料梁结构的有限元模型;由于材料参数和边界条件是有限元建模中存在的主要误差,将遗传算法作为优化工具,结合模态分析实验测得数据分别对材料参数以及边界参数进行了优化修正,修正后的有限元模型具有很高的精度;利用修正后的有限元模型得到复合材料结构含不同脱层损伤的前五阶弯曲模态频率,频率信息经过规格化处理后作为训练样本对混合递阶遗传RBF神经网络进行训练;将实验测得数据送入训练好的混合递阶遗传RBF神经网络进行预测,实现了对复合材料结构脱层损伤的定位和损伤程度的评估。
The research on health monitoring for composite structures based on neural network is comprehensively discussed in this paper. Some researchers have verified the ability of neural network to identify the model from numerical method without any experiments, yet this is not enough. Some other researchers collect features of a variety of structural damages by experiments to obtain samples for training neural network, but the number of samples is not enough. So the model updating method based on modal analysis experiment is used to acquire a more realistic model. Features of various structural damages are derived by the model to form enough samples for training neural network,
Firstly, two carbon fiber reinforced composite beams are fabricated, and their first five flexure modal frequencies are measured by an experiment method. Then, the initial model based on composite structural mechanics is updated by genetic algorithm and frequencies obtained by modal analysis experiment. The material parameters of composite structure are optimized and revised, as well as the boundary condition. Then, samples to train the neural network are obtained by the revised FEM model. Finally, the first five flexure modal frequencies obtained by experiment are input to the neural network to predict the location and extent of demalination.
本文制备了两个碳纤维增强复合材料试验件,并进行了模态分析实验,测得两个试验件的前五阶弯曲模态频率;根据复合材料结构力学以及边界条件的近似处理建立了复合材料梁结构的有限元模型;由于材料参数和边界条件是有限元建模中存在的主要误差,将遗传算法作为优化工具,结合模态分析实验测得数据分别对材料参数以及边界参数进行了优化修正,修正后的有限元模型具有很高的精度;利用修正后的有限元模型得到复合材料结构含不同脱层损伤的前五阶弯曲模态频率,频率信息经过规格化处理后作为训练样本对混合递阶遗传RBF神经网络进行训练;将实验测得数据送入训练好的混合递阶遗传RBF神经网络进行预测,实现了对复合材料结构脱层损伤的定位和损伤程度的评估。
The research on health monitoring for composite structures based on neural network is comprehensively discussed in this paper. Some researchers have verified the ability of neural network to identify the model from numerical method without any experiments, yet this is not enough. Some other researchers collect features of a variety of structural damages by experiments to obtain samples for training neural network, but the number of samples is not enough. So the model updating method based on modal analysis experiment is used to acquire a more realistic model. Features of various structural damages are derived by the model to form enough samples for training neural network,
Firstly, two carbon fiber reinforced composite beams are fabricated, and their first five flexure modal frequencies are measured by an experiment method. Then, the initial model based on composite structural mechanics is updated by genetic algorithm and frequencies obtained by modal analysis experiment. The material parameters of composite structure are optimized and revised, as well as the boundary condition. Then, samples to train the neural network are obtained by the revised FEM model. Finally, the first five flexure modal frequencies obtained by experiment are input to the neural network to predict the location and extent of demalination.
引文
[1]李宏男,李东升.土木工程结构安全性评估、健康监测及诊断述评.地震工程与工程振动, 2002, 22(3): 82~90.
[2]欧进萍.重大工程结构的累积损伤与安全度评定.中国科协第9次“青年科学家论坛”报告文集,北京:清华大学出版社, 1996.
[3]谢强,薛松涛.土木工程结构健康监测的研究现状与进展.中国科学基金, 2001(5): 285~288.
[4] Buhl H. High performance material in aerospace. Berlin, Springer, 1992.
[5] Flower HM. High performance materials in aerospace. London, Chapman & Hall, 1995.
[6] Hoskin BC, Baker AA. Composite material for aircraft structures. New York, American Institute of Aeronautics and Astronautics, 1986.
[7] A Johnson, H F Lam. Structural health monitoring benchmark problem using simulated data. Journal of Engineering Mechanics, ASCE January 2004: 3-15.
[8] Houser G W, Bergman L A. Structural control: past, present and future. Journal of Engineering Mechanics, 1997, 123 (9): 897~971.
[9] Jeong-Beom Ihn, Fukuo Chang. Built in diagnostics for monitoring crack growth in aircraft structures. Proceedings of the international workshop on structural health monitoring held at Stanford University, 2001:285~295.
[10] Wang Q, Varadan VK. Wave propagation in piezoelectric coupled plated by use of inter digital transducer. Part 2: Wave excitation by inter digital transducer, International journal of solids and structures, 2002, 39: 1131~1144.
[11]胡自力,熊克,杨红.基于智能材料结构的几种损伤评价方法.航空学报, Jan.2002, 23(1): 1~5.
[12]唐守锋,熊克,梁大开.用于结构健康监测的智能夹层研究进展.实验力学, 2005, 20(2): 226~234.
[13]王小永,钱华.先进复合材料中的主要缺陷与无损检测技术评价.无损探伤, 2006, 30(4): 1.
[14]沈真.复合材料损伤与断裂的研究进展.复合材料及结构力学进展(第二册),武汉:武汉工业大学出版社, 1992: 29~97.
[15] Serge Abrate. Impact on laminated: Recent advances. Applied Mechanics Review, 1994, 47 (11):517~546.
[16] Laksson K L. On multiple delamination buckling and growth in composite plates. International Journal of Solids Structures, 1991, 27 (13): 1623~1637.
[17] M.H.SHEN, J.E.GRADY. Free vibration of delaminated beams. AIAA 1992 (30) , 1361~1370.
[18] A.K.PANDEY, M.BISWAS, M.M.SAMMAN. Damage detection from changes in curvature mode shapes. Journal of Sound and Vibration, 1991, (145): 321~332.
[19] S. H. Diaz Valdes, C. Soutis. Delamination Detection on Composite Laminates from Variations of Their Modal Characteristics. Journal of Sound and Vibration, 1999, 228 (1), 1~9.
[20] Seths Kessler, S.Mark Speaking, Manro J. Atalla, et al. Damage Detection in Composite Materials using frequency response Methods. Composites, Part B, 2002: 87~95.
[21] Y.J.Yan, L.H.Yam. Detection of Delamination damage in Composite plates using energy spectrum of Structural Dynamics Responses Decomposed by Wavelet Analysis. Computers and Structures, 2004, 82: 347~358.
[22]董聪.基于动力特性的结构损伤定位方法,力学与实践, 1999, 21: 62~63.
[23]罗松男,曹志远,傅衣铭.复合材料脱层梁的屈曲分析.力学季刊, 2001.9, 22(3):322~328.
[24]罗松男,曹志远,傅衣铭.复合材料梁的脱层识别.复合材料学报, 2002.10, 19(5): 90~94.
[25]史治宇,罗绍湘,张令弥.结构破损定位的单元模态应变能变化率法.振动工程学报, 1998.9, 11(3): 356~360.
[26]王志华,程载斌,张向东.对结构多位置损伤定位分析方法的探讨.太原理工大学学报, 2004.5, 35(3): 289~293.
[27]肖成锋,富明慧.复合材料层合梁脱层分析的高阶模型.中山大学学报(自然科学版), 2004.5, 43(3): 113~116.
[28]徐颖娣,袁慎芳,彭鸽.二维结构损伤的主动lamb波定位技术研究.航空学报, 2004.9, 25(5): 476~479.
[29]李正强,郑世杰.基于HHGA-RBF神经网络的复合材料结构脱层损伤监测研究.宇航学报, 2008.1, 29(1): 347~351.
[30]耿浩,王睿,高芳清.模态变化对钢桁架模型桥的损伤检测研究.桥梁建设, 1998, 2: 67~70.
[31]董聪,丁辉,高嵩.结构损伤识别和定位的基本原理与方法,中国铁道科学, 1999.9, 2(03), 89~94.
[32]郑明刚,刘天雄,朱继梅.曲率模态在桥梁状态监测中的应用.振动与冲击, 2000, 19(2): 81~83.
[33]秦权,张卫国.悬索桥的损伤识别.清华大学学报, 1998, 38(12): 44~47.
[34] Cawley, Adams R D. The location of defects in structures from measurements of natural frequencies. Journal of Strain Anal, 1979, 14 (2): 49~55
[35] Scott W Doebling, et al. Damage Identification and Health Monitoring of Structural and Mechanical Systems from Changes in their Vibration Characteristics: A Literature Review, 2000, 10~59.
[36] Lai Wuxing, Peter W. Tse, Zhang Guicai, et al. Classification of gear faults using cumulants and the radial basis function network. Mechanical Systems and Signal Processing, 2004, 18: 381~389.
[37]张德文.计算结构模型修正技术.研究生内部教材,航空航天工业部第七零二研究所, 1992.
[38] P. Cawley, R.D. Adams. The Location of Defects in Structures from Measurements of Natural Frequencies. Journal of Strain Analysis, 1979, 14 (2).
[39] P. Cawley, R.D. Adams. A Vibration Technique for Non-Destructive Testing of Fiber Composite Structures, Journal of Composite Material, April 1979, 13.
[40] P. Cawley, R.D. Adams. A Vibration Technique for Non-Destructively Assessing the Integrity of Structures. Journal of Mechanical Engineering Science, 1978, 20 (2).
[41]姜绍飞,周广师,刘红兢.考虑不确定性因素的结构损伤检测方法.沈阳建筑工程学院学报, 2002, 18(2): 85~87.
[42] A.S. ISLAM, K.C. CRALG. Damage detection in composite structures using piezoelectric materials. Smart Materials and Structures, 1994.3, 318~328.
[43] Rhim J, Lee S W. A neural network approach for damage detection and identification of structures. Computational Mechanics, 1995, 16 (6): 437~443.
[44] Hanagud S, Luo H. Damage Detection and Health Monitoring Based on Structural Dynamics. Structural Health Monitoring, Current Status and Perspectives, 1997: 715~726.
[45] Luo H, Hanagud S. Dynamic Learning Rate Neural Networks Training and Composite Structural Damage Detection. AIAA, 1997, 35 (9): 1552~1527.
[46] Jenq ST, Lee WD. Identification of Hole Defect for GFPR Woven Laminates Using Neural Network Scheme. Structural Health Monitoring, Current Status and Perspectives, 1997: 741~751.
[47] Maseras-Gutierrez M, Staszewske W. Detection of Impacts in Composite Materials Using Piezoceramic Sensors and Neural Networks. Smart Structures and Materials 1999: Smart Structures and Integrated Systems, Proceedings of SPIE, 1998, 3329: 491~497.
[48] Catelsni M., Fort A. Fault Diagnosis of Electronic Analog Circuit Using a Radial BasisFunction Network Classifier. Measurement, 2000, 28: 147~158.
[49] Zang C., Imregun M. Structural damage using artificial neural networks and measured FRF data reduced via principal component projection. Journal of Sound and Vibration, 2001, 242 (5): 813~827.
[50] Haywood J, Staszewski WJ, Worden K. Impact Location in Composite Structures Using Smart Sensor Technology and Neural Networks. The 3rd International Workshop on Structural Health Monitoring, 2001: 1466~1475.
[51] Watkins S E, Sanders G W, Akhavan F. Modal analysis using fiber optic sensors and neural networks for prediction of composite beam delemination. Smart Material and Structures, 2002, (11): 489~495.
[52] Chen Q, Chan Y W, worden K. Structural fault diagnosis and isolation using neural networks based on response only data. Computers & Structures, 2003, 81: 2165~2172.
[53] Reddy R K, Ganguli R. Structural damage detection in a helicopter rotor blade using radial basis function neural networks. Smart Materials and Structures, 2003, 12: 232~241.
[54] X Fang, H Luo, J Tang. Structures damage detection using neural network with learning rate improvement. Computers and Structures, 2005, 83: 2150~2160.
[55]吴耀军,陶宝琪.基于小波神经网络的复合材料损伤诊断.航空学报, 1997, 18(2): 252~256.
[56]周智,林丽川.结构损伤的神经网络定位研究.中南工业大学学报, 1994.4, 30(2): 126~128.
[57]瞿伟廉,陈超,魏文辉.基于应变模态的钢结构构件焊缝损伤定位方法的研究.世界地震工程, 2002.6, 18(2): 1~8.
[58]刘利锋,郑世杰.基于智能元件和神经网络的复合材料损伤监测.测试技术学报, 2003, 17(4): 350~353.
[59]梁大开,谢建宏,张为宋.基于小波神经网络的智能复合材料损伤定位的仿真研究.测控技术, 2004, 23(9): 8~10.
[60]曾神昌,麦汉超.结构健康监测系统中的频率响应方法.强度与环境, 2004, 34(1): 29~34.
[61]彭鸽,袁慎芳.复合材料结构损伤的小波神经网络辨识研究.宇航学报, 2005, 26(5): 625~629,667.
[62]王宏涛,刘利锋,郑世杰.基于模态分析和BP神经网络的复合材料脱层损伤监测研究.中国机械工程, 2005, 16(3): 239~242, 248.
[63]郑丕谔,马艳华. RBF神经网络的递阶遗传训练新方法.控制与决策, 2000, 15(2): 165~168.
[64] Martin T. Hagan, Howard B. Demuth, Mark H. Beale.神经网络设计[戴葵等译].北京,机械工业出版社, 2002: 1~89
[65]党建武.神经网络技术及应用.北京,中国铁道出版社, 1999: 9~23.
[66]闻新,周露,王丹力. MATLAB神经网络应用设计.北京,科学出版社, 2000: 135~176.
[67]李红江,胡照文,郑哲文. RBF神经网络的一种新的学习方法.长沙电力学院出版社(自然科学版), 2002.2, 15(1): 39~42.
[68]蔡四维.复合材料结构力学.人民交通出版社, 1987: 68~70.
[2]欧进萍.重大工程结构的累积损伤与安全度评定.中国科协第9次“青年科学家论坛”报告文集,北京:清华大学出版社, 1996.
[3]谢强,薛松涛.土木工程结构健康监测的研究现状与进展.中国科学基金, 2001(5): 285~288.
[4] Buhl H. High performance material in aerospace. Berlin, Springer, 1992.
[5] Flower HM. High performance materials in aerospace. London, Chapman & Hall, 1995.
[6] Hoskin BC, Baker AA. Composite material for aircraft structures. New York, American Institute of Aeronautics and Astronautics, 1986.
[7] A Johnson, H F Lam. Structural health monitoring benchmark problem using simulated data. Journal of Engineering Mechanics, ASCE January 2004: 3-15.
[8] Houser G W, Bergman L A. Structural control: past, present and future. Journal of Engineering Mechanics, 1997, 123 (9): 897~971.
[9] Jeong-Beom Ihn, Fukuo Chang. Built in diagnostics for monitoring crack growth in aircraft structures. Proceedings of the international workshop on structural health monitoring held at Stanford University, 2001:285~295.
[10] Wang Q, Varadan VK. Wave propagation in piezoelectric coupled plated by use of inter digital transducer. Part 2: Wave excitation by inter digital transducer, International journal of solids and structures, 2002, 39: 1131~1144.
[11]胡自力,熊克,杨红.基于智能材料结构的几种损伤评价方法.航空学报, Jan.2002, 23(1): 1~5.
[12]唐守锋,熊克,梁大开.用于结构健康监测的智能夹层研究进展.实验力学, 2005, 20(2): 226~234.
[13]王小永,钱华.先进复合材料中的主要缺陷与无损检测技术评价.无损探伤, 2006, 30(4): 1.
[14]沈真.复合材料损伤与断裂的研究进展.复合材料及结构力学进展(第二册),武汉:武汉工业大学出版社, 1992: 29~97.
[15] Serge Abrate. Impact on laminated: Recent advances. Applied Mechanics Review, 1994, 47 (11):517~546.
[16] Laksson K L. On multiple delamination buckling and growth in composite plates. International Journal of Solids Structures, 1991, 27 (13): 1623~1637.
[17] M.H.SHEN, J.E.GRADY. Free vibration of delaminated beams. AIAA 1992 (30) , 1361~1370.
[18] A.K.PANDEY, M.BISWAS, M.M.SAMMAN. Damage detection from changes in curvature mode shapes. Journal of Sound and Vibration, 1991, (145): 321~332.
[19] S. H. Diaz Valdes, C. Soutis. Delamination Detection on Composite Laminates from Variations of Their Modal Characteristics. Journal of Sound and Vibration, 1999, 228 (1), 1~9.
[20] Seths Kessler, S.Mark Speaking, Manro J. Atalla, et al. Damage Detection in Composite Materials using frequency response Methods. Composites, Part B, 2002: 87~95.
[21] Y.J.Yan, L.H.Yam. Detection of Delamination damage in Composite plates using energy spectrum of Structural Dynamics Responses Decomposed by Wavelet Analysis. Computers and Structures, 2004, 82: 347~358.
[22]董聪.基于动力特性的结构损伤定位方法,力学与实践, 1999, 21: 62~63.
[23]罗松男,曹志远,傅衣铭.复合材料脱层梁的屈曲分析.力学季刊, 2001.9, 22(3):322~328.
[24]罗松男,曹志远,傅衣铭.复合材料梁的脱层识别.复合材料学报, 2002.10, 19(5): 90~94.
[25]史治宇,罗绍湘,张令弥.结构破损定位的单元模态应变能变化率法.振动工程学报, 1998.9, 11(3): 356~360.
[26]王志华,程载斌,张向东.对结构多位置损伤定位分析方法的探讨.太原理工大学学报, 2004.5, 35(3): 289~293.
[27]肖成锋,富明慧.复合材料层合梁脱层分析的高阶模型.中山大学学报(自然科学版), 2004.5, 43(3): 113~116.
[28]徐颖娣,袁慎芳,彭鸽.二维结构损伤的主动lamb波定位技术研究.航空学报, 2004.9, 25(5): 476~479.
[29]李正强,郑世杰.基于HHGA-RBF神经网络的复合材料结构脱层损伤监测研究.宇航学报, 2008.1, 29(1): 347~351.
[30]耿浩,王睿,高芳清.模态变化对钢桁架模型桥的损伤检测研究.桥梁建设, 1998, 2: 67~70.
[31]董聪,丁辉,高嵩.结构损伤识别和定位的基本原理与方法,中国铁道科学, 1999.9, 2(03), 89~94.
[32]郑明刚,刘天雄,朱继梅.曲率模态在桥梁状态监测中的应用.振动与冲击, 2000, 19(2): 81~83.
[33]秦权,张卫国.悬索桥的损伤识别.清华大学学报, 1998, 38(12): 44~47.
[34] Cawley, Adams R D. The location of defects in structures from measurements of natural frequencies. Journal of Strain Anal, 1979, 14 (2): 49~55
[35] Scott W Doebling, et al. Damage Identification and Health Monitoring of Structural and Mechanical Systems from Changes in their Vibration Characteristics: A Literature Review, 2000, 10~59.
[36] Lai Wuxing, Peter W. Tse, Zhang Guicai, et al. Classification of gear faults using cumulants and the radial basis function network. Mechanical Systems and Signal Processing, 2004, 18: 381~389.
[37]张德文.计算结构模型修正技术.研究生内部教材,航空航天工业部第七零二研究所, 1992.
[38] P. Cawley, R.D. Adams. The Location of Defects in Structures from Measurements of Natural Frequencies. Journal of Strain Analysis, 1979, 14 (2).
[39] P. Cawley, R.D. Adams. A Vibration Technique for Non-Destructive Testing of Fiber Composite Structures, Journal of Composite Material, April 1979, 13.
[40] P. Cawley, R.D. Adams. A Vibration Technique for Non-Destructively Assessing the Integrity of Structures. Journal of Mechanical Engineering Science, 1978, 20 (2).
[41]姜绍飞,周广师,刘红兢.考虑不确定性因素的结构损伤检测方法.沈阳建筑工程学院学报, 2002, 18(2): 85~87.
[42] A.S. ISLAM, K.C. CRALG. Damage detection in composite structures using piezoelectric materials. Smart Materials and Structures, 1994.3, 318~328.
[43] Rhim J, Lee S W. A neural network approach for damage detection and identification of structures. Computational Mechanics, 1995, 16 (6): 437~443.
[44] Hanagud S, Luo H. Damage Detection and Health Monitoring Based on Structural Dynamics. Structural Health Monitoring, Current Status and Perspectives, 1997: 715~726.
[45] Luo H, Hanagud S. Dynamic Learning Rate Neural Networks Training and Composite Structural Damage Detection. AIAA, 1997, 35 (9): 1552~1527.
[46] Jenq ST, Lee WD. Identification of Hole Defect for GFPR Woven Laminates Using Neural Network Scheme. Structural Health Monitoring, Current Status and Perspectives, 1997: 741~751.
[47] Maseras-Gutierrez M, Staszewske W. Detection of Impacts in Composite Materials Using Piezoceramic Sensors and Neural Networks. Smart Structures and Materials 1999: Smart Structures and Integrated Systems, Proceedings of SPIE, 1998, 3329: 491~497.
[48] Catelsni M., Fort A. Fault Diagnosis of Electronic Analog Circuit Using a Radial BasisFunction Network Classifier. Measurement, 2000, 28: 147~158.
[49] Zang C., Imregun M. Structural damage using artificial neural networks and measured FRF data reduced via principal component projection. Journal of Sound and Vibration, 2001, 242 (5): 813~827.
[50] Haywood J, Staszewski WJ, Worden K. Impact Location in Composite Structures Using Smart Sensor Technology and Neural Networks. The 3rd International Workshop on Structural Health Monitoring, 2001: 1466~1475.
[51] Watkins S E, Sanders G W, Akhavan F. Modal analysis using fiber optic sensors and neural networks for prediction of composite beam delemination. Smart Material and Structures, 2002, (11): 489~495.
[52] Chen Q, Chan Y W, worden K. Structural fault diagnosis and isolation using neural networks based on response only data. Computers & Structures, 2003, 81: 2165~2172.
[53] Reddy R K, Ganguli R. Structural damage detection in a helicopter rotor blade using radial basis function neural networks. Smart Materials and Structures, 2003, 12: 232~241.
[54] X Fang, H Luo, J Tang. Structures damage detection using neural network with learning rate improvement. Computers and Structures, 2005, 83: 2150~2160.
[55]吴耀军,陶宝琪.基于小波神经网络的复合材料损伤诊断.航空学报, 1997, 18(2): 252~256.
[56]周智,林丽川.结构损伤的神经网络定位研究.中南工业大学学报, 1994.4, 30(2): 126~128.
[57]瞿伟廉,陈超,魏文辉.基于应变模态的钢结构构件焊缝损伤定位方法的研究.世界地震工程, 2002.6, 18(2): 1~8.
[58]刘利锋,郑世杰.基于智能元件和神经网络的复合材料损伤监测.测试技术学报, 2003, 17(4): 350~353.
[59]梁大开,谢建宏,张为宋.基于小波神经网络的智能复合材料损伤定位的仿真研究.测控技术, 2004, 23(9): 8~10.
[60]曾神昌,麦汉超.结构健康监测系统中的频率响应方法.强度与环境, 2004, 34(1): 29~34.
[61]彭鸽,袁慎芳.复合材料结构损伤的小波神经网络辨识研究.宇航学报, 2005, 26(5): 625~629,667.
[62]王宏涛,刘利锋,郑世杰.基于模态分析和BP神经网络的复合材料脱层损伤监测研究.中国机械工程, 2005, 16(3): 239~242, 248.
[63]郑丕谔,马艳华. RBF神经网络的递阶遗传训练新方法.控制与决策, 2000, 15(2): 165~168.
[64] Martin T. Hagan, Howard B. Demuth, Mark H. Beale.神经网络设计[戴葵等译].北京,机械工业出版社, 2002: 1~89
[65]党建武.神经网络技术及应用.北京,中国铁道出版社, 1999: 9~23.
[66]闻新,周露,王丹力. MATLAB神经网络应用设计.北京,科学出版社, 2000: 135~176.
[67]李红江,胡照文,郑哲文. RBF神经网络的一种新的学习方法.长沙电力学院出版社(自然科学版), 2002.2, 15(1): 39~42.
[68]蔡四维.复合材料结构力学.人民交通出版社, 1987: 68~70.