基于K-近邻隶属度模糊支持向量机的再造抽油杆损伤等级磁记忆定量识别

doi:10.7623/syxb201511012

石油学报 ›› 2015, Vol. 36 ›› Issue (11): 1427-1432,1456.DOI: 10.7623/syxb201511012

基于K-近邻隶属度模糊支持向量机的再造抽油杆损伤等级磁记忆定量识别

邢海燕, 党永斌, 王犇, 葛桦, 王尊策

东北石油大学机械科学与工程学院黑龙江大庆 163318

收稿日期:2015-06-06 修回日期:2015-09-12 出版日期:2015-11-25 发布日期:2015-12-05
通讯作者: 邢海燕,女,1971年12月生,1993年获哈尔滨工业大学学士学位,2007年获哈尔滨工业大学博士学位,现为东北石油大学机械科学与工程学院教授,主要从事石油机械无损检测与故障诊断方面的研究。Email:xxhhyyhit@163.com
作者简介:邢海燕,女,1971年12月生,1993年获哈尔滨工业大学学士学位,2007年获哈尔滨工业大学博士学位,现为东北石油大学机械科学与工程学院教授,主要从事石油机械无损检测与故障诊断方面的研究。Email:xxhhyyhit@163.com
基金资助:
国家自然科学基金项目(No.11272084,No.11072056,No.11472076)、中国石油科技创新基金项目(2015D-5006-0602)、黑龙江省博士后科研启动基金项目(LBH-Q13035)、黑龙江省应用技术研究与开发计划项目(GA13A402)资助。

Q uantitative MMM identification of damage levels based on KNN FSVM for remanufactured sucker rod

Xing Haiyan, Dang Yongbin, Wang Ben, Ge Hua, Wang Zunce

School of Mechanical Science and Engineering, Northeast Petroleum University, Heilongjiang Daqing 163318, China

Received:2015-06-06 Revised:2015-09-12 Online:2015-11-25 Published:2015-12-05

摘要/Abstract

摘要：

针对磁记忆技术在再造抽油杆损伤等级定量评价中小样本和分散性的难题,从再造抽油杆疲劳损伤实验出发,通过获取损伤演化过程的磁记忆特征规律,提取五维磁记忆特征向量,首次引入基于K-近邻隶属度的模糊支持向量机多分类算法,结合参数组合寻优方法,建立再造抽油杆损伤等级的多分类磁记忆定量识别模型。结果表明:利用K-近邻隶属度将分散性和模糊性加以量化,结合支持向量机的小样本优势,构造的K-近邻隶属度模糊支持向量机多分类磁记忆模型,可以进行再造抽油杆损伤等级的磁记忆定量识别,并进一步进行参数组合寻优,避免了盲目选择固定参数导致模型精度过低,具有较好的抗噪性和鲁棒性,为再造抽油杆损伤等级定量评价提供了一种新的方法。

关键词: 金属磁记忆定量识别, K-近邻隶属度, 模糊支持向量机, 参数组合寻优, 再造抽油杆

Abstract:

Data dispersion and small-and medium-sized samples incur the difficulty in quantitative identification of damage levels for remanufactured sucker rods by applying metal magnetic memory (MMM) technology. To solve the bottleneck, based on the fatigue and damage experiment of remanufactured sucker rods, the MMM characteristic rule of damage evolution is obtained to further extract five dimensional MMM parameters. A new multi-classification algorithm of the fuzzy support vector machine based on the membership degree obtained using k-nearest neighbor method are first put forward in this study. On this basis, the multiple classification MMM model is established for quantitative identification of damage levels for remanufactured sucker rods using parameter combination optimization method. The result shows that this membership degree can be used to quantify the data dispersion and fuzziness, and then a multi-classification MMM model based on the fuzzy support vector machine with the membership degree can be established by utilizing the advantage in solving small sample. This model can perform quantitative identification of the damage level for remanufactured sucker rods; parameter combination optimization is further implemented to avoid the over-low precision caused by blind selection of fixed parameter. It also has better robustness and anti-noise property, providing a new method to quantitatively identify the damage level for remanufactured sucker rods.

Key words: quantitative metal magnetic memory identification, k-Nearest Neighbor membership, fuzzy support vector machine, parameter combination optimization, remanufactured sucker rod

中图分类号:

TE933.07

邢海燕, 党永斌, 王犇, 葛桦, 王尊策. 基于K-近邻隶属度模糊支持向量机的再造抽油杆损伤等级磁记忆定量识别[J]. 石油学报, 2015, 36(11): 1427-1432,1456.

Xing Haiyan, Dang Yongbin, Wang Ben, Ge Hua, Wang Zunce. Q uantitative MMM identification of damage levels based on KNN FSVM for remanufactured sucker rod[J]. Acta Petrolei Sinica, 2015, 36(11): 1427-1432,1456.

参考文献

[1] 吴则中,钟永海,孟忠良,等.我国抽油杆研制工作的现状及发展方向[J].石油机械,2008,36(2):63-66.
Wu Zezhong,Zhong Yonghai,Meng Zhongliang,et al.The status quo and trend of sucker rod development in China[J].China Petroleum Machinery,2008,36(2):63-66.
[2] 姜怀芳,杨芸,冯搏,等.再制造抽油杆高精度漏磁无损检测系统[J].石油机械,2014,42(1):79-83.
Jiang Huaifang,Yang Yun,Feng Bo,et al.High-precision MFL nondestructive detection system for remanufactured sucker rod[J].China Petroleum Machinery,2014,42(1):79-83.
[3] Dubov A,Dubov A,Kolokolnikov S.Application of the metal magnetic memory method for detection of defects at the initial stage of their development for prevention of failures of power engineering welded steel structures and steam turbine parts[J].Welding in the World,2014,58(2):225-236.
[4] Roskosz M.Metal magnetic memory testing of welded joints of ferritic and austenitic steels[J].NDT & E International,2011,44(3):305-310.
[5] Dubov A,Kolokolnikov S.Assessment of the material state of oil and gas pipelines based on the metal magnetic memory method[J].Welding in the World,2012,56(3/4):11-19.
[6] 张静,樊建春,王培玺,等.套管损伤磁记忆检测信号的量化识别方法[J].石油机械,2012,40(8):24-28.
Zhang Jing,Fan Jianchun,Wang Peixi,et al.Quantitative identification method for magnetic memory detection signal of casing damage[J].China Petroleum Machinery,2012,40(8):24-28.
[7] 张兰,张来斌,樊建春,等.钻杆损伤磁记忆检测软件设计与应用[J].石油机械,2010,38(4):53-56.
Zhang Lan,Zhang Laibin,Fan Jianchun,et al.Design and application of metal magnetic memory testing software for drilling pipe damage[J].China Petroleum Machinery,2010,38(4):53-56.
[8] 于润桥,徐长英.基于金属磁记忆的钻具无损评价技术[J].钢铁研究学报,2011,23(11):59-64.
Yu Runqiao,Xu Changying.Nondestructive evaluation technique for drilling rig based on metal magnetic memory[J].Journal of Iron and Steel Research,2011,23(11):59-64.
[9] 龙飞飞,高果柱,张晓勇,等.柱塞泵螺纹的磁记忆检测技术研究[J].流体机械,2013,41(2):7-11.
Long Feifei,Gao Guozhu,Zhang Xiaoyong,et al.Research on the magnetic memory diagnostic technique of the plunger pump thread[J].Fluid Machinery,2013,41(2):7-11.
[10] 易方,李著信,吕宏庆,等.基于模糊核支持向量机的管道磁记忆检测缺陷识别[J].石油学报,2010,31(5):863-866.
Yi Fang,Li Zhuxin,Lv Hongqing,et al.Defect recognition by metal magnetic memory detection of pipelines based on the fuzzy kernel function SVM[J].Acta Petrolei Sinica,2010,31(5):863-866.
[11] Chaudhuri A.Modified fuzzy support vector machine for credit approval classification[J].AI Communications,2014,27(2):189-121.
[12] 林伟国,王晓东,戚元华,等.管道泄漏信号和干扰信号的数字化判别方法[J].石油学报,2014,35(6):1197-1203.
Lin Weiguo,Wang Xiaodong,Qi Yuanhua,et al.Digital identification method for pipeline leak and interference signal[J].Acta Petrolei Sinica,2014,35(6):1197-1203.
[13] 沈跃,张亨,张令坦,等.基于自适应滤波的钻井液连续压力波信号噪声抑制[J].石油学报,2014,35(2):353-358.
Shen Yue,Zhang Heng,Zhang Lingtan,et al.Eliminating noise of drilling fluid continuous pressure wave signals based on the self-adaptive filtering method[J].Acta Petrolei Sinica,2014,35(2):353-358.
[14] 肖燕彩,张清.基于模糊支持向量机的变压器故障诊断[J].北京交通大学学报,2012,36(1):117-121.
Xiao Yancai,Zhang Qing.Research of transformer fault diagnosis based on fuzzy support vector machines[J].Journal of Beijing Jiaotong University,2012,36(1):117-121.
[15] 戴花,王建平.模糊支持向量机在人脸识别中的应用[J].计算机工程与应用,2012,48(6):158-161.
Dai Hua,Wang Jianping.Application of face recognition used fuzzy support vector machine[J].Computer Engineering and Applications,2012,48(6):158-161.
[16] 罗忠运.基于希尔伯特一黄变换和模糊支持向量机的输电线路故障分类方法研究[D].成都:西南交通大学,2014.
Luo Zhongyun.Transmission line faults classification method based on Hilbert-Huang transform and fuzzy support vector machine[D].Chengdu:Southwest Jiaotong University,2014.
[17] Wu Zhenning,Zhang Huaguang,Liu Jinhai.A fuzzy support vector machine algorithm for classification based on a novel PIM fuzzy clustering method[J]. Neurocomputing,2014,125:119-124.
[18] 郭丽娟,孙世宇,段修生.支持向量机及核函数研究[J].科学技术与工程,2008,8(2):487-490.
Guo Lijuan,Sun Shiyu,Duan Xiusheng.Research for support vector machine and kernd function[J].Science Technology and Engineering,2008,8(2):487-490.
[19] Ashkezari A D,Ma Hui,Saha T K,et al.Application of fuzzy support vector machine for determining the health index of the insulation system of in-service power transformers[J].IEEE Transactions on Dielectrics and Electrical Insulation,2013,20(3):965-973.
[20] 许翠云.模糊支持向量机的研究及其在基因分类中的应用[D].南京:南京林业大学,2013.
Xu Cuiyun.Research of fuzzy support vector machine and its application of gene classification[D].Nanjing:Nanjing Forestry University,2013.
[21] SY/T 5643-2010抽油杆维护和使用推荐做法[S].国家能源局,2010.
SY/T 5643-2010 Recommended practice for the care and handling of sucker rod[S].National Energy Administration,2010.
[22] 王凯.基于多分类支持向量机的有杆抽油泵故障诊断研究[J].西安石油大学学报:自然科学版,2010,25(1):91-95.
Wang Kai.Study on the fault diagnosis of rod-pumping unit based on multi-class support vector machines[J].Journal of Xi'an Shiyou University:Natural Science Editon,2010,25(1):91-95.
[23] 邢海燕,徐敏强,李建伟,等.磁记忆检测技术及工程应用[M].北京:中国石化出版社,2011.
Xing Haiyan,Xu Minqiang,Li Jianwei,et al.Metal magnetic memory testing technology and engineering application[M].Beijing:China Petrochemical Press,2011.
[24] Zhang Ying,Su Hongye,Liu Ruilan,et al.Fuzzy support vector regression model of 4-CBA concentration for industrial PTA oxidation process[J].Chinese Journal of Chemical

Engineering,2005,13(5):642-648.

基于K-近邻隶属度模糊支持向量机的再造抽油杆损伤等级磁记忆定量识别

Q uantitative MMM identification of damage levels based on KNN FSVM for remanufactured sucker rod

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价