Page 49 - 无损检测2025年第一期
P. 49
阮隽宇，等：
基于缺陷漏磁信号特征值的管道缺陷量化分析
of defect profiles from magnetic flux leakage 56（6）：6200315．
measurements using a RBFNN based error adjustment [14] DAI L S，FENG Q S，SUTHERLAND J，et al.
methodology[J]. IET Science，Measurement & Application of MFL on girth-weld defect detection of
Technology，2017，11（3）：262-269． oil and gas pipelines[J]. Journal of Pipeline Systems
[12] KANDROODI M R，SHIRANI F，ARAABI B N， Engineering and Practice，2020，11（4）：47-51．
et al. Defect detection and width estimation in natural gas [15] ZHEN L，BĂRBULESCU A. Comparative analysis of
pipelines using MFL signals[C]//2013 9th Asian Control convolutional neural network-long short-term memory，
Conference （ASCC）．Turkey：IEEE，2013：1-6． sparrow search algorithm-backpropagation neural
[13] PENG X，ANYAOHA U，LIU Z，et al. Analysis of network，and particle swarm optimization-extreme
magnetic-flux leakage （MFL） learning machine models for the water discharge of the
data for pipeline corrosion
assessment[J]. IEEE Transactions on Magnetics，2020， buzău river，Romania[J]. Water，2024，16（2）：289．
19
2025 年 第 47 卷 第 1 期
无损检测
