基于支持向量机的管道腐蚀超声波内检测
|
摘要
超声波检测是输油管道在线内检测的重要方法之一,由于管道内部检测环境复杂,使超声检测回波信号识别困难,其分类是一个高维分类问题。利用支持向量机在解决小样本、非线性、高维模式识别中特有的优势,直接采用表征超声回波形态的A扫描数据作为特征向量,将特征提取与模式分类统一进行,建立了管道腐蚀超声检测回波信号分类决策函数,实现了管道腐蚀缺陷识别。实验结果表明,该方法可以正确地分类识别管道腐蚀产生的突变界面,基于支持向量机的管道腐蚀超声内检测信号分类识别方法是可行、有效的。
Ultrasonic detection is one of the important ways to inspect the wall-loss defects and cracks in-line for oil pipeline.Because of the complicated condition in pipeline the recognition of ultrasonic detection echoes is difficult.This is a high-dimensional classification problem.An effective method based on support vector machine(SVM),which is suitable for small-sample,non-linear and high-dimensional recognition for classification and recognition of pipeline corrosion defects was presented.The ultrasonic A-scan time-series were considered characteristic vectors.By unifying the characteristics extraction and pattern recognition of pipeline corrosion defects the classified decision function of ultrasonic detection echo signals was established.Experiments showed that the classified recognition of break interfaces of pipelines was accurate and clear and the method was suitable for in-line detection of pipeline corrosion defects.
Ultrasonic detection is one of the important ways to inspect the wall-loss defects and cracks in-line for oil pipeline.Because of the complicated condition in pipeline the recognition of ultrasonic detection echoes is difficult.This is a high-dimensional classification problem.An effective method based on support vector machine(SVM),which is suitable for small-sample,non-linear and high-dimensional recognition for classification and recognition of pipeline corrosion defects was presented.The ultrasonic A-scan time-series were considered characteristic vectors.By unifying the characteristics extraction and pattern recognition of pipeline corrosion defects the classified decision function of ultrasonic detection echo signals was established.Experiments showed that the classified recognition of break interfaces of pipelines was accurate and clear and the method was suitable for in-line detection of pipeline corrosion defects.
引文
[1]Li Zhuxin(李著信),Su Yi(苏毅),L櫣Hongqing(吕宏庆),Meng Haolong(孟浩龙).On-line inspection technology and robot for pipeline·Journal of Logistical Engineering University(后勤工程学院学报),2006,22(4):41-45
[2]Dai Bo(戴波),Sheng Sha(盛沙),Tang Jian(唐建),Tian Xiaoping(田小平).The application of i mproved burg maxi mum entropy method in pipeline inspection·Chinese Journal of Sensors and Actuators(传感技术学报),2007,20(6):1416-1419
[3]Vapnik V N·The Nature of Statistical Learning·New York:Springer-Verlag,1995
[4]Nello Cristianini,John Shawe-Taylor·An Introduction to Support Vector Machines and Other Kernel-based Learning Methods(支持向量机导论).Li Guozheng(李国正),Wang Meng(王猛),Zeng Huajun(曾华军),trans·Beijing:Publishing House of ElectronicsIndustry,2004
[5]Wang Haijun(王海军),Liu Guizhong(刘贵忠).Automatic signal detection based on support vector machine·Acta Seismologica Sinica(地震学报),2007,29(1):85-94
[6]She Chuanfu(佘传伏),Yu Lijun(余立钧),Yao Daomin(姚道敏).Fault diagnosis using support vector machines based on feature selection·Modern Machinery(现代机械),2007(1):22-24
[7]Lu Weiguo(鹿卫国),Dai Yaping(戴亚平),Gao Feng(高峰).A hydroelectric-generator unit fault early warning method based on distribution esti mation·Proceedings ofthe CSEE(中国电机工程学报),2005,25(4):94-98
[8]Vapnik V N·Esti mation of Dependences Based on Empirical Data·New York:Springer-Verlag,1982
[9]Wu Dexin(吴德新),Yang Xiaolin(杨小林).Identification of waveforms and defects in ultrasonic inspection·Nondestructive Testing(无损检测),2007,24(7):312-316
[10]Tang Nan(汤楠),Mu Xiangyang(穆向阳),Xu Juan(徐娟).Study on recognition of corrosion in pipeline based on ultrasonic inspection·China Petroleum Machinery(石油机械),2005,33(11):54-56
[11]Zheng Xianbin(郑贤斌),Chen Guoming(陈国明),Yuan Chaohong(袁超红).A review on processing approaches about defect data ininspection of the oil and gas pipeline·Pressure Vessel Technology(压力容器),2005,22(10):38-43
[12]Ling Changrong(凌昌荣),Liu Guixiong(刘桂雄),Chen Tiequn(陈铁群).Recognition of defects in ultrasonic testing based on integrated neural networks·Modern Manufacturing Engineering(现代制造工程),2006(4):98-100
[13]Liu Xu(刘旭),Xia Jindong(夏金东),Wu Miao(吴淼).Study on wavelet denoise and characteristic extraction of echo signal to flaw classification in ultrasonic testing·Journal of China University of Mining&Technology(中国矿业大学学报),2001,30(3):248-251
[14]Mathias M Adankon,Mohamed Cheriet·Opti mizing resources in model selection for support vector machine·Pattern Recognition,2007,40:953-963
[15]Yuan Shengfa,Chu Fulei·Fault diagnosis based on support vector machines with parameter opti mization by artificial i mmunization algorithm·Mechanical Systems and Signal Processing,2007,21:1318-1330
[16]Lin Shengliang(林生梁),Liu Zhi(刘志).Parameter selection in SVM with RBF kernel function·Journal of Zhejiang University of Technology(浙江工业大学学报),2007,35(2):163-167
[17]Dong Chunxi(董春曦),Rao Xian(饶鲜),Yang Shaoquan(杨绍全),Xu Songtao(徐松涛).Method for selecting the parameters of support vector machines·Systems Engineering and Electronics(系统工程与电子技术),2004,26(3):1117-1120
[2]Dai Bo(戴波),Sheng Sha(盛沙),Tang Jian(唐建),Tian Xiaoping(田小平).The application of i mproved burg maxi mum entropy method in pipeline inspection·Chinese Journal of Sensors and Actuators(传感技术学报),2007,20(6):1416-1419
[3]Vapnik V N·The Nature of Statistical Learning·New York:Springer-Verlag,1995
[4]Nello Cristianini,John Shawe-Taylor·An Introduction to Support Vector Machines and Other Kernel-based Learning Methods(支持向量机导论).Li Guozheng(李国正),Wang Meng(王猛),Zeng Huajun(曾华军),trans·Beijing:Publishing House of ElectronicsIndustry,2004
[5]Wang Haijun(王海军),Liu Guizhong(刘贵忠).Automatic signal detection based on support vector machine·Acta Seismologica Sinica(地震学报),2007,29(1):85-94
[6]She Chuanfu(佘传伏),Yu Lijun(余立钧),Yao Daomin(姚道敏).Fault diagnosis using support vector machines based on feature selection·Modern Machinery(现代机械),2007(1):22-24
[7]Lu Weiguo(鹿卫国),Dai Yaping(戴亚平),Gao Feng(高峰).A hydroelectric-generator unit fault early warning method based on distribution esti mation·Proceedings ofthe CSEE(中国电机工程学报),2005,25(4):94-98
[8]Vapnik V N·Esti mation of Dependences Based on Empirical Data·New York:Springer-Verlag,1982
[9]Wu Dexin(吴德新),Yang Xiaolin(杨小林).Identification of waveforms and defects in ultrasonic inspection·Nondestructive Testing(无损检测),2007,24(7):312-316
[10]Tang Nan(汤楠),Mu Xiangyang(穆向阳),Xu Juan(徐娟).Study on recognition of corrosion in pipeline based on ultrasonic inspection·China Petroleum Machinery(石油机械),2005,33(11):54-56
[11]Zheng Xianbin(郑贤斌),Chen Guoming(陈国明),Yuan Chaohong(袁超红).A review on processing approaches about defect data ininspection of the oil and gas pipeline·Pressure Vessel Technology(压力容器),2005,22(10):38-43
[12]Ling Changrong(凌昌荣),Liu Guixiong(刘桂雄),Chen Tiequn(陈铁群).Recognition of defects in ultrasonic testing based on integrated neural networks·Modern Manufacturing Engineering(现代制造工程),2006(4):98-100
[13]Liu Xu(刘旭),Xia Jindong(夏金东),Wu Miao(吴淼).Study on wavelet denoise and characteristic extraction of echo signal to flaw classification in ultrasonic testing·Journal of China University of Mining&Technology(中国矿业大学学报),2001,30(3):248-251
[14]Mathias M Adankon,Mohamed Cheriet·Opti mizing resources in model selection for support vector machine·Pattern Recognition,2007,40:953-963
[15]Yuan Shengfa,Chu Fulei·Fault diagnosis based on support vector machines with parameter opti mization by artificial i mmunization algorithm·Mechanical Systems and Signal Processing,2007,21:1318-1330
[16]Lin Shengliang(林生梁),Liu Zhi(刘志).Parameter selection in SVM with RBF kernel function·Journal of Zhejiang University of Technology(浙江工业大学学报),2007,35(2):163-167
[17]Dong Chunxi(董春曦),Rao Xian(饶鲜),Yang Shaoquan(杨绍全),Xu Songtao(徐松涛).Method for selecting the parameters of support vector machines·Systems Engineering and Electronics(系统工程与电子技术),2004,26(3):1117-1120
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心