薄板粘接质量超声检测模糊式识别方法研究
|
摘要
薄板复合材料以其优越的性能而广泛应用于航空航天领域,在使用过程中由于粘接界面脱粘而造成的灾难性事故时有发生,因此亟需对界面粘接质量进行准确的定量检测,以保证产品质量和使用安全。超声脉冲回波法以缺陷定位准确、适用范围广、操作方便等优点广泛应用于无损检测。
如何对反映粘接质量的超声检测回波信号进行分类识别,是薄板复合材料超声检测的关键也是难点之一。本文用模糊模式识别方法对薄板粘接质量做出定量识别。首先,利用BP神经网络建立了各个特征量对各粘接质量的模糊隶属函数,实验表明,基于BP神经网络建立的隶属函数即方便简单,又符合实际应用的要求。在此基础上,建立已知粘接质量特征量与未知粘接质量特征量的模糊集,设计模糊模式识别算法,该算法选用海明贴近度和算术平均最小值贴近度作为贴近度函数,然后用择近原则法对薄板粘接质量做出定量识别,实验表明该识别方法是准确有效的。隶属函数的建立是实现模糊模式识别的关键,而模糊模式识别算法应用在薄板复合材料的粘接质量识别中,克服了由复合材料内部结构的复杂性及工作环境变化等因素引起的识别难的问题,为专用数字化超声检测仪的设计和实现奠定了基础。
More and more thin composite materials have been applied in industry of aeronautics and astronautics for their superior performance. Disastrous accidents happen in process of working at times for bonding defect of composite material, so it is urgently needed to make accurate detection for bonding interface and insure the quality of products and working safety. Ultrasonic echo method is widely applied in non-destructive detection for its advantage of accurate defect locating, wide application, and convenient operation and so on.
How to make classify and recognize echo signal of ultrasonic detection takes information of interface bonding quality is the key and difficulty of ultrasonic detection of thin composite materials. In this paper, we use fuzzy pattern recognition method to judge bonding quality. Firstly, we establish the fuzzy membership function between each characteristic and bonding quality by BP neural network. Simulation results show that this method is convenient, simple, and it conforms to the practical application. Secondly, we establish the fuzzy subsets of each bonding quality and design a fuzzy pattern recognition algorithm. Then we design a fuzzy pattern recognition algorithm to judge bonding quality, and the algorithm selects hamming approach degree and the arithmetic mean least approach degree. Then we use the nearest principle to recognize bonding quality. Simulation results show that the algorithm is very exact for quantitative recognition of bonding quality. The establishing of membership function is the key of fuzzy pattern recognition. Fuzzy pattern recognition algorithm overcomes the problem that caused by the internal structure of composite material and the complexity of the work of environmental and so on. Fuzzy pattern recognition is applied in bonding quality ultrasonic detection of thin composite plate is very helpful for design and realization of digital ultrasonic detection instrument.
如何对反映粘接质量的超声检测回波信号进行分类识别,是薄板复合材料超声检测的关键也是难点之一。本文用模糊模式识别方法对薄板粘接质量做出定量识别。首先,利用BP神经网络建立了各个特征量对各粘接质量的模糊隶属函数,实验表明,基于BP神经网络建立的隶属函数即方便简单,又符合实际应用的要求。在此基础上,建立已知粘接质量特征量与未知粘接质量特征量的模糊集,设计模糊模式识别算法,该算法选用海明贴近度和算术平均最小值贴近度作为贴近度函数,然后用择近原则法对薄板粘接质量做出定量识别,实验表明该识别方法是准确有效的。隶属函数的建立是实现模糊模式识别的关键,而模糊模式识别算法应用在薄板复合材料的粘接质量识别中,克服了由复合材料内部结构的复杂性及工作环境变化等因素引起的识别难的问题,为专用数字化超声检测仪的设计和实现奠定了基础。
More and more thin composite materials have been applied in industry of aeronautics and astronautics for their superior performance. Disastrous accidents happen in process of working at times for bonding defect of composite material, so it is urgently needed to make accurate detection for bonding interface and insure the quality of products and working safety. Ultrasonic echo method is widely applied in non-destructive detection for its advantage of accurate defect locating, wide application, and convenient operation and so on.
How to make classify and recognize echo signal of ultrasonic detection takes information of interface bonding quality is the key and difficulty of ultrasonic detection of thin composite materials. In this paper, we use fuzzy pattern recognition method to judge bonding quality. Firstly, we establish the fuzzy membership function between each characteristic and bonding quality by BP neural network. Simulation results show that this method is convenient, simple, and it conforms to the practical application. Secondly, we establish the fuzzy subsets of each bonding quality and design a fuzzy pattern recognition algorithm. Then we design a fuzzy pattern recognition algorithm to judge bonding quality, and the algorithm selects hamming approach degree and the arithmetic mean least approach degree. Then we use the nearest principle to recognize bonding quality. Simulation results show that the algorithm is very exact for quantitative recognition of bonding quality. The establishing of membership function is the key of fuzzy pattern recognition. Fuzzy pattern recognition algorithm overcomes the problem that caused by the internal structure of composite material and the complexity of the work of environmental and so on. Fuzzy pattern recognition is applied in bonding quality ultrasonic detection of thin composite plate is very helpful for design and realization of digital ultrasonic detection instrument.
引文
[1]Cawley P.The sensitivity of the mechanical impedance method of nondestructive testing[J],NDTinternational,1987,20(4):209-215.
[2]Akker S,Arman J.Ultrasonic investigation on plane interfaces between polymers[J],Ultrasonics,1997,35(4):287-295.
[3]Tang W,Courouble Irsid B.Lamb waves in mutilayered media[A],Ultrasonics international[C],Le Touquet France,1991:209-215.
[4]Quaftouth M,Xu W J.Evaluation of adhesion by means of high frequency ultrasound[J],Journal de Physique,1992,2:835-838.
[5]Smith A C,Yang H.Ultrasonic study of adhesive bond quality at a steel to rubber interface by using quadrature phase detection techniques[J],Materials Evaluation,1989,27(12):1389-1400.
[6]何毅斌,陈定方.BP网在模糊集隶属函数上的应用研究与仿真[J],武汉化工学院学报,2000,22(4):57-60.
[7]刘瑁,连晋毅.模糊可靠性分析中基于神经网络技术的隶属函数确定方法,科技情报开发与经济[J],2005,15(8):185-186.
[8]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M],电子工业出版设,北京,2005.
[9]冯若.超声手册[M],南京大学出版社,2001.
[10]张海燕 等.小波变换和模糊模式识别技术在金属超声检测缺陷分类中的应用[J],无损检测,2000,22(2):51-54.
[11]张海燕,刘镇清.模糊数学在超声检测中的应用[J],无损检测,2001,23(6),260-263.
[12]陆俭伟,吕干霖.等管材超声检测中缺陷模糊模式识别方法研究[J],声学学报,1996,21(1):20-28.
[13]吕干霖,黎宗潼等.超声检测中缺陷模糊聚类识别[J],声学学报,1996(增刊),21(4):592-600.
[14]吕干霖,黎宗撞,蔡杰.超声检测缺陷模糊识别模型无损检测[J],1996,18(5):121-124.
[15]刘振清 等.强散材料超声检测的模糊检测[J],声学学报,1997,22(5):408-413.
[16]刘玉铭.关于模糊模式识别和中控制的研究与应用,[博士论文],北京:北京师范大学,1999.
[17]温熙,森胡庆,邱静.模式识别与状态监控[M],长沙:国防科技大学出版社,1997.
[18]许晓艺.模糊理论在模式识别领域中的应用[J],华南师范大学学报(自然科学版),1994,(3):91-96.
[19]郭桂容.模糊模式识别[M],国防科技大学出版社,1992.
[20]张跃.模糊数学方法及其应用[M],煤炭工业出版社,1992.
[21]方华.基于模糊模式识别的板壳结构识别,[硕士论文],武汉,武汉理工大学,2003.
[22]徐扬.模糊模式识别[M],西南交通大学出版社,1999.
[23]Jame M,Kelle,Ronald R.Yager,Hossein.Neural network implementation of fuzzy logic[J],Fuzzy sets and systems,1992,45,1-12.
[24]ThouhongWang,Generating fuzzy membership functions:Amonotonic neural network model,Fuzzy sets and systems[J],1994,61,71-81.
[25]Zhigang Li,Shouren Hu,Honyi Lu.Feedforward Neuarl Networks Design By Evolutionary Programming,Proceedings of The Third Word Congress on Expert System,Feb.,Soul,Korea,1996,Ⅱ,31247-1254.
[26]荣吉利.航天器工况和故障的模糊模式识别[J],兵工学报,2003,23(3):374-376.
[27]童树鸿,沈毅,刘志言.基于聚类分析的模糊分类系统构造方法[J],控制与决策,2001,16(1):737-740.
[28]柳朝阳,乔新勇,刘建敏.基于模糊模式识别的柴油机故障诊断研究[J],车用发动机,2001(4):363-38.
[29]杨卫峰,杨树军,宋京伟.基于小波和模糊模式识别的齿轮故障诊断[J],华东交通大学学报,2001,18(2):16-19.
[30]莫锦秋,周晓军.基于模糊子集理论的无损检测缺陷模式识别[J],中国机械工程,1999,10(6):665-666.
[31]袁群,李斌,耿晔.超声波检测桩基质量的模糊综合分析[J],郑州工业大学学报,1999,20(3):35-38.
[32]刘镇清.超声无损检测与评价中的信号处理及模式识别[J],无损检测,2001,23(1):31-34.
[33]Sugair,A.M.Framework for Evaluating B ids o f Construction Contractors[J],Journal of Management inEngineering,ASCE,1999,15(2):72-78.
[34]LI YAWEI,CHEN SHOUYU,NIE XIANGTIAN.Fuzzy Pattern Recognition Approach to Construction Contractor Selection[J],Fuzzy Optimization and Decision Making,2005,(4):103-118.
[35]Y.S.Tarng,S.S.Yeh and S.C.Juang.Fuzzy Pattern Recognition of Tungsten Inert Gas Weld Quality[J],Int J Adv Manuf Technol,1997,(13):387-392.
[36]佘玉梅,熊汉.模糊模式识别方法研究[J],云南民族学院学报,1998,7(1):14-20.
[37]刚铁,王东华.表面缺陷的超声检测与识别[J],无损探伤,2003,(3):12-15.
[38]王成明,颜云辉,李骏,张尧.模糊神经网络法及其在缺陷模式识别中的应用[J],计算机集成制造系统,2007,13(9):1774-1779.
[39]昧志方,张冰,朱志宇,杨薇.模糊聚类和模糊模式识别在目标识别中的应用[J],电光与控制,2007,7(4):35-38.
[40]李明军,刘怡听,黄先义等.基于模糊模式识别的战场日标识别[J],火力与指挥控制,2005,30(8):57-60.
[41]李鸿吉.模糊数学基础及实用算法[M],科学出版社,北京,2005.
[42]张娜,曾孟佳.模糊模式识别在计算机识别中的应用研究[J],微计算机信息,2004,20(6):54-55.
[43]王晓君,魏书华.模糊理论在基于特征向量的模式识别中的应用[J],计算机工程与应用,2007,43(10):80-83.
[44]Adums R D,Caquley P.A review of defect types and NDT testing techniques for composites and bonded Joints[C],NDT international,1988.
[45]Aussel J D.Split-spectrum processing with finite impulse response filters of constant frequency to band with ratio[J],Ultrasonic,1990,28(4):229-239.
[46]边肇祺,张学工.模式识别[M],清华大学出版社,2004.
[47]徐扬.模糊模式识别[M],西南交通大学出版社,1999.
[48]高志奇.基于小波分析和模糊模式识别的薄板粘接质量超声检测研究,[硕士论文],呼和浩特,内蒙古大学,2006.
[2]Akker S,Arman J.Ultrasonic investigation on plane interfaces between polymers[J],Ultrasonics,1997,35(4):287-295.
[3]Tang W,Courouble Irsid B.Lamb waves in mutilayered media[A],Ultrasonics international[C],Le Touquet France,1991:209-215.
[4]Quaftouth M,Xu W J.Evaluation of adhesion by means of high frequency ultrasound[J],Journal de Physique,1992,2:835-838.
[5]Smith A C,Yang H.Ultrasonic study of adhesive bond quality at a steel to rubber interface by using quadrature phase detection techniques[J],Materials Evaluation,1989,27(12):1389-1400.
[6]何毅斌,陈定方.BP网在模糊集隶属函数上的应用研究与仿真[J],武汉化工学院学报,2000,22(4):57-60.
[7]刘瑁,连晋毅.模糊可靠性分析中基于神经网络技术的隶属函数确定方法,科技情报开发与经济[J],2005,15(8):185-186.
[8]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M],电子工业出版设,北京,2005.
[9]冯若.超声手册[M],南京大学出版社,2001.
[10]张海燕 等.小波变换和模糊模式识别技术在金属超声检测缺陷分类中的应用[J],无损检测,2000,22(2):51-54.
[11]张海燕,刘镇清.模糊数学在超声检测中的应用[J],无损检测,2001,23(6),260-263.
[12]陆俭伟,吕干霖.等管材超声检测中缺陷模糊模式识别方法研究[J],声学学报,1996,21(1):20-28.
[13]吕干霖,黎宗潼等.超声检测中缺陷模糊聚类识别[J],声学学报,1996(增刊),21(4):592-600.
[14]吕干霖,黎宗撞,蔡杰.超声检测缺陷模糊识别模型无损检测[J],1996,18(5):121-124.
[15]刘振清 等.强散材料超声检测的模糊检测[J],声学学报,1997,22(5):408-413.
[16]刘玉铭.关于模糊模式识别和中控制的研究与应用,[博士论文],北京:北京师范大学,1999.
[17]温熙,森胡庆,邱静.模式识别与状态监控[M],长沙:国防科技大学出版社,1997.
[18]许晓艺.模糊理论在模式识别领域中的应用[J],华南师范大学学报(自然科学版),1994,(3):91-96.
[19]郭桂容.模糊模式识别[M],国防科技大学出版社,1992.
[20]张跃.模糊数学方法及其应用[M],煤炭工业出版社,1992.
[21]方华.基于模糊模式识别的板壳结构识别,[硕士论文],武汉,武汉理工大学,2003.
[22]徐扬.模糊模式识别[M],西南交通大学出版社,1999.
[23]Jame M,Kelle,Ronald R.Yager,Hossein.Neural network implementation of fuzzy logic[J],Fuzzy sets and systems,1992,45,1-12.
[24]ThouhongWang,Generating fuzzy membership functions:Amonotonic neural network model,Fuzzy sets and systems[J],1994,61,71-81.
[25]Zhigang Li,Shouren Hu,Honyi Lu.Feedforward Neuarl Networks Design By Evolutionary Programming,Proceedings of The Third Word Congress on Expert System,Feb.,Soul,Korea,1996,Ⅱ,31247-1254.
[26]荣吉利.航天器工况和故障的模糊模式识别[J],兵工学报,2003,23(3):374-376.
[27]童树鸿,沈毅,刘志言.基于聚类分析的模糊分类系统构造方法[J],控制与决策,2001,16(1):737-740.
[28]柳朝阳,乔新勇,刘建敏.基于模糊模式识别的柴油机故障诊断研究[J],车用发动机,2001(4):363-38.
[29]杨卫峰,杨树军,宋京伟.基于小波和模糊模式识别的齿轮故障诊断[J],华东交通大学学报,2001,18(2):16-19.
[30]莫锦秋,周晓军.基于模糊子集理论的无损检测缺陷模式识别[J],中国机械工程,1999,10(6):665-666.
[31]袁群,李斌,耿晔.超声波检测桩基质量的模糊综合分析[J],郑州工业大学学报,1999,20(3):35-38.
[32]刘镇清.超声无损检测与评价中的信号处理及模式识别[J],无损检测,2001,23(1):31-34.
[33]Sugair,A.M.Framework for Evaluating B ids o f Construction Contractors[J],Journal of Management inEngineering,ASCE,1999,15(2):72-78.
[34]LI YAWEI,CHEN SHOUYU,NIE XIANGTIAN.Fuzzy Pattern Recognition Approach to Construction Contractor Selection[J],Fuzzy Optimization and Decision Making,2005,(4):103-118.
[35]Y.S.Tarng,S.S.Yeh and S.C.Juang.Fuzzy Pattern Recognition of Tungsten Inert Gas Weld Quality[J],Int J Adv Manuf Technol,1997,(13):387-392.
[36]佘玉梅,熊汉.模糊模式识别方法研究[J],云南民族学院学报,1998,7(1):14-20.
[37]刚铁,王东华.表面缺陷的超声检测与识别[J],无损探伤,2003,(3):12-15.
[38]王成明,颜云辉,李骏,张尧.模糊神经网络法及其在缺陷模式识别中的应用[J],计算机集成制造系统,2007,13(9):1774-1779.
[39]昧志方,张冰,朱志宇,杨薇.模糊聚类和模糊模式识别在目标识别中的应用[J],电光与控制,2007,7(4):35-38.
[40]李明军,刘怡听,黄先义等.基于模糊模式识别的战场日标识别[J],火力与指挥控制,2005,30(8):57-60.
[41]李鸿吉.模糊数学基础及实用算法[M],科学出版社,北京,2005.
[42]张娜,曾孟佳.模糊模式识别在计算机识别中的应用研究[J],微计算机信息,2004,20(6):54-55.
[43]王晓君,魏书华.模糊理论在基于特征向量的模式识别中的应用[J],计算机工程与应用,2007,43(10):80-83.
[44]Adums R D,Caquley P.A review of defect types and NDT testing techniques for composites and bonded Joints[C],NDT international,1988.
[45]Aussel J D.Split-spectrum processing with finite impulse response filters of constant frequency to band with ratio[J],Ultrasonic,1990,28(4):229-239.
[46]边肇祺,张学工.模式识别[M],清华大学出版社,2004.
[47]徐扬.模糊模式识别[M],西南交通大学出版社,1999.
[48]高志奇.基于小波分析和模糊模式识别的薄板粘接质量超声检测研究,[硕士论文],呼和浩特,内蒙古大学,2006.