An improved support vector regression method for quantifying magneticleakage defects in three-axis pipeline
摘 要
为了提高管道漏磁内检测缺陷量化技术的精度,基于三轴漏磁内检测器采集到的缺陷漏磁数据,设计了一系列针对管道轴向、径向以及周向的特征提取方法,为后续进行缺陷的高精度量化提供了数据基础。针对缺陷不同尺寸量化任务下特征冗余的问题,基于近邻成分分析提出一种特征选择方法,该方法能够有效地剔除原始特征集中的无关特征。在基于支持向量回归的漏磁缺陷尺寸量化中,结合改进蝙蝠算法对支持向量回归的参数进行寻优,结果表明,所设计的量化方法能够有效降低时间复杂度,在一定程度上提高缺陷量化的准确性。
Abstract
In order to improve the accuracy of the defect quantification technology for pipeline magnetic flux leakage internal detection, a series of feature extraction methods for pipeline axial, radial and circumferential directions was designed based on the defect magnetic flux data collected by the three-axis magnetic flux leakage internal detector, providing a data basis for the high-precision quantification of subsequent defects. Aiming at the problem of feature redundancy under the task of quantifying defects with different sizes, this paper proposes a feature selection method based on nearest neighbor component analysis, which can effectively eliminate irrelevant features in the original feature set. In the quantization of magnetic flux leakage defects based on support vector regression, this paper combines the improved bat algorithm to optimize the parameters of the support vector regression. The results show that the designed quantization method can effectively reduce time complexity and improve the accuracy of defect quantification to a certain extent.
中图分类号 TG115.28 DOI 10.11973/wsjc202103014
所属栏目 试验研究
基金项目 重点研发计划(2017YFF0108800)
收稿日期 2020/6/18
修改稿日期
网络出版日期
作者单位点击查看
备注胡家铖(1996-),男,研究生,主要研究方向为管道检测与数据分析
引用该论文: HU Jiacheng,JIAO Xiaoliang,ZHENG Li,GANG Bei,LIU Sijiao. An improved support vector regression method for quantifying magneticleakage defects in three-axis pipeline[J]. Nondestructive Testing, 2021, 43(3): 62~68
胡家铖,焦晓亮,郑莉,刚蓓,刘思娇. 一种改进的支持向量回归三轴管道漏磁缺陷量化方法[J]. 无损检测, 2021, 43(3): 62~68
共有人对该论文发表了看法,其中:
人认为该论文很差
人认为该论文较差
人认为该论文一般
人认为该论文较好
人认为该论文很好
参考文献
【1】LANG X M, LI P, HU Z Y, et al. Leak detection and location of pipelines based on LMD and least squares twin support vector machine[J]. IEEE Access, 2017,5:8659-8668.
【2】蹇清平. 基于漏磁检测的油管缺陷量化研究[D].成都:西南石油大学,2015.
【3】崔凯. 基于支持向量机和极限学习机的管道缺陷分类方法研究[D].长春:东北大学,2014.
【4】张少轩. 基于机器学习的缺陷深度反演研究[D].长春:东北大学,2017.
【5】ZHANG Y, YU Z, XU X. An adaptive method for channel equalization in MFL inspection[J]. NDT&E International, 2007, 12(3):27-29.
【6】王婷婷. 金属表面缺陷特征智能提取及特征分析的方法研究[D].长春:东北大学,2017.
【7】王富祥, 冯庆善,张海亮,等.基于三轴漏磁内检测技术的管道特征识别[J].无损检测,2011,33(1):79-84.
【8】杨亮, 徐春风,宋云鹏,等. 基于三轴漏磁检测的管道缺陷量化方法[J].管道技术与设备,2019(4):29-31.
【9】SURHONE L M, TIMPLEDON M T, MARSEKEN S F. Neighbourhood components analysis[J]. Advances in Neural Information Processing Systems, 2004, 17(6):513-520.
【2】蹇清平. 基于漏磁检测的油管缺陷量化研究[D].成都:西南石油大学,2015.
【3】崔凯. 基于支持向量机和极限学习机的管道缺陷分类方法研究[D].长春:东北大学,2014.
【4】张少轩. 基于机器学习的缺陷深度反演研究[D].长春:东北大学,2017.
【5】ZHANG Y, YU Z, XU X. An adaptive method for channel equalization in MFL inspection[J]. NDT&E International, 2007, 12(3):27-29.
【6】王婷婷. 金属表面缺陷特征智能提取及特征分析的方法研究[D].长春:东北大学,2017.
【7】王富祥, 冯庆善,张海亮,等.基于三轴漏磁内检测技术的管道特征识别[J].无损检测,2011,33(1):79-84.
【8】杨亮, 徐春风,宋云鹏,等. 基于三轴漏磁检测的管道缺陷量化方法[J].管道技术与设备,2019(4):29-31.
【9】SURHONE L M, TIMPLEDON M T, MARSEKEN S F. Neighbourhood components analysis[J]. Advances in Neural Information Processing Systems, 2004, 17(6):513-520.
相关信息