Pipeline Magnetic Flux Leakage Image Detection Algorithm Based on Multiscale SSD Network

被引:108
|
作者
Yang, Lijian [1 ]
Wang, Zhujun [1 ]
Gao, Songwei [1 ]
机构
[1] Shenyang Univ Technol, Sch Instrumentat Sci & Technol, Shenyang 110870, Peoples R China
关键词
Attention residual module; magnetic flux leakage in pipeline; residual network; SSD network; target detection; OBJECT CLASSIFICATION; DEFECT IDENTIFICATION; CNN; FUSION;
D O I
10.1109/TII.2019.2926283
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In order to solve the problem of low detection accuracy of small targets in the SSD detection algorithm, a pipeline magnetic flux leakage image detection algorithm based on multiscale SSD network is proposed in this paper. The dilated convolution and attention residual module are introduced into the SSD algorithm to fuse the low-resolution high-semantic information feature map with the high-resolution low-semantic information feature map so as to improve the resolution of the low-resolution feature map and provide detailed features for small targets. Finally, the target location and category are obtained by regression algorithm. The experimental results show that the proposed algorithm can automatically identify the location of circumferential weld, spiral weld, and defect of magnetic flux leakage data. Compared with the original SSD algorithm framework, the improved algorithm has higher detection accuracy, 97.62, 18.01 lower false detection rate, 18.36 lower false detection rate, better robustness, and obvious effect on small target detection.
引用
收藏
页码:501 / 509
页数:9
相关论文
共 50 条
  • [1] Image recognition model of pipeline magnetic flux leakage detection based on deep learning
    Xu, Zhenchang
    Liu, Kuirong
    Gu, Bill
    Yan, Luchun
    Pang, Xiaolu
    Gao, Kewei
    [J]. CORROSION REVIEWS, 2023, 41 (06) : 689 - 701
  • [2] The method of the pipeline magnetic flux leakage detection image formation based on the artificial intelligence
    Yang, Lijian
    Shi, Meng
    Gao, Songwei
    [J]. PROCEEDINGS OF 2017 INTERNATIONAL CONFERENCE ON VIDEO AND IMAGE PROCESSING (ICVIP 2017), 2017, : 20 - 24
  • [3] Theory and Application of Magnetic Flux Leakage Pipeline Detection
    Shi, Yan
    Zhang, Chao
    Li, Rui
    Cai, Maolin
    Jia, Guanwei
    [J]. SENSORS, 2015, 15 (12) : 31036 - 31055
  • [4] Data compression technology in pipeline magnetic flux leakage detection
    Yang, Li-Jian
    Zhang, Shuang-Nan
    Gao, Song-Wei
    [J]. Shenyang Gongye Daxue Xuebao/Journal of Shenyang University of Technology, 2010, 32 (04): : 395 - 399
  • [5] On the Algorithm of Analyzing the Features of Magnetic Flux Leakage Signal for Pipeline Defect Based on PCA
    Sun, Yun
    Liu, Jinhai
    Zhang, Huaguang
    Wang, Tingting
    Zheng, Li
    [J]. PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, : 5434 - 5438
  • [6] Research on Magnetic Flux Leakage Detection Method for Subsea Pipeline
    黄作英
    阙沛文
    杨崇倡
    [J]. Journal of Donghua University(English Edition), 2004, (05) : 98 - 101
  • [7] Magnetic flux leakage image classification method for pipeline weld based on optimized convolution kernel
    Yang, Lijian
    Wang, Zhujun
    Gao, Songwei
    Shi, Meng
    Liu, Bangli
    [J]. NEUROCOMPUTING, 2019, 365 : 229 - 238
  • [8] Analysis of Leakage in a Sustainable Water Pipeline Based on a Magnetic Flux Leakage Technique
    Durai, Mathivanan
    Chi-Chuan, Peng
    Lan, Chou-Wei
    Chang, Ho
    [J]. SUSTAINABILITY, 2022, 14 (19)
  • [9] Finite element method in subsea pipeline magnetic flux leakage detection
    Huang, ZY
    Que, PW
    [J]. ICEMI'2003: PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON ELECTRONIC MEASUREMENT & INSTRUMENTS, VOLS 1-3, 2003, : 840 - 844
  • [10] Quantization of pipeline magnetic flux leakage detection signal under load
    Liu T.
    Liu B.
    Feng G.
    Lian Z.
    Yang L.
    [J]. Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument, 2022, 43 (01): : 262 - 273