+高级检索
首页 > 过刊浏览>2022年第45卷第7期 >103-111. DOI:10.11835/j.issn.1000-582X.2022.07.011
PDF HTML阅读 XML下载 导出引用 引用提醒
基于压力容器裂纹图像检测及识别算法研究
作者:
中图分类号:

TP183;TP391.4

基金项目:

国家自然科学基金联合资助项目(U1813216);重庆市自然科学基金资助项目(cstc2021jcyi-msxm4008);河南省科技厅基本科研业务费支持项目(2021KY08)。


Image detection and identification algorithm of pressure vessel cracks
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [20]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    压力容器作为一种特种设备,其安全越来越受到重视。为了保障其安全运行,选择压力容器裂纹图像为研究对象,构建检测及识别算法模型。针对算法模型在实际部署时受到内存空间、处理器计算能力等多方面硬件条件的制约问题,提出了基于NewEfficientNet-B0的轻量化方法,结果表明算法模型降低模型参数数量达78%。针对微小裂纹图像识别难度较大问题,提出了改进多尺度预测的方法,测试数据集上达到了81%的检测识别准确率。

    Abstract:

    As a kind of special equipment, the safety of pressure vessels attracts more and more attention. To ensure their safe operation, using the pressure vessel crack image as the research object, this paper constructed an algorithm model for the crack detection and identification. Generally, the algorithm model is constrained by various hardware conditions, such as memory space and processor computing power during actual deployment. Therefore, a lightweight method based on NewEfficientNet-B0 was proposed. The results show that the algorithm model reduces the number of model parameters by 78%. To deal with the difficulty of recognizing tiny crack images, an improved multi-scale prediction method was proposed. The detection and recognition accuracy rate of 81% was achieved on the test data set.

    参考文献
    [1] 李生渊. 锅炉检测的常用技术研究[J]. 决策探索(中), 2019(9):60-61.Li S Y. Research on common technology of boiler inspection[J]. Policy Research & Exploration, 2019(9):60-61. (in Chinese)
    [2] Oliveira H, Correia P L. CrackIT-An image processing toolbox for crack detection and characterization[C]//2014 IEEE International Conference on Image Processing. Paris, France:IEEE, 2014:798-802.
    [3] Kapela R, Sniataƚa P, Turkot A, et al. Asphalt surfaced pavement cracks detection based on histograms of oriented gradients[C]//2015 22nd International Conference Mixed Design of Integrated Circuits & Systems (MIXDES). Torun, Poland:IEEE, 2015:579-584.
    [4] Ai D H, Jiang G Y, Siew Kei L, et al. Automatic pixel-level pavement crack detection using information of multi-scale neighborhoods[J]. IEEE Access, 2018, 6:24452-24463.
    [5] Maeda H, Sekimoto Y, Seto T, et al. Road damage detection and classification using deep neural networks with smartphone images[J]. Computer-Aided Civil and Infrastructure Engineering, 2018, 33(12):1127-1141.
    [6] Li P H, Yang Y F, Grosu R, et al. Driver distraction detection using octave-like convolutional neural network[J]. IEEE Transactions on Intelligent Transportation Systems, 6411, PP(99):1-11.
    [7] Yang F, Zhang L, Yu S J, et al. Feature pyramid and hierarchical boosting network for pavement crack detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(4):1525-1535.
    [8] Cheng J R, Xiong W, Chen W Y, et al. Pixel-level crack detection using U-net[C]//TENCON 2018-2018 IEEE Region 10 Conference. Jeju, Korea (South):IEEE, 2018:462-466.
    [9] 马桂振, 谭云华, 陈太军, 等. 锅炉螺旋水冷壁内裂纹超声检测研究[J]. 锅炉技术, 2021, 52(S1):49-54.Ma G Z, Tan Y H, Chen T J, et al. Study on ultrasonic detection of inner crack of boiler spiral water wall[J]. Boiler Technology, 2021, 52(S1):49-54. (in Chinese)
    [10] Jang J, Liu P P, Kim B, et al. Silicon wafer crack detection using nonlinear ultrasonic modulation induced by high repetition rate pulse laser[J]. Optics and Lasers in Engineering, 2020, 129:106074.
    [11] Wang R, Wu Q, Yu F M, et al. Nonlinear ultrasonic detection for evaluating fatigue crack in metal plate[J]. Structural Health Monitoring, 2019, 18(3):869-881.
    [12] 邢砾文, 姚文凯, 黄莹. 基于深度学习的含未知复合故障多传感器信号故障诊断[J]. 重庆大学学报, 2020, 43(9):93-100.Xing L W, Yao W K, Huang Y. Fault diagnosis of multi-sensor signal with unknown composite fault based on deep learning[J]. Journal of Chongqing University, 2020, 43(9):93-100. (in Chinese)
    [13] 杨祖莨, 丁洁, 刘晋峰. 一种新的结合卷积神经网络的隧道内停车检测方法[J]. 重庆大学学报, 2021, 44(6):49-59.Yang Z L, Ding J, Liu J F. A new tunnel vehicle stopping detection methodology combined with convolutional neural network[J]. Journal of Chongqing University, 2021, 44(6):49-59. (in Chinese)
    [14] 何育欣, 郑伯川, 谭代伦, 等. 基于VGGNet改进网络结构的多尺度大熊猫面部检测[J]. 重庆大学学报, 2020, 43(11):63-71.He Y X, Zheng B C, Tan D L, et al. Multi-scale giant panda face detection based on the improved VGGNet architecture[J]. Journal of Chongqing University, 2020, 43(11):63-71. (in Chinese)
    [15] Ren S Q, He K M, Girshick R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
    [16] Redmon J, Divvala S, Girshick R, et al. You only look once:unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA:IEEE, 2016:779-788.
    [17] Redmon J, Farhadi A. YOLO9000:better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA:IEEE, 2017:6517-6525.
    [19] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA:IEEE, 2016:770-778.
    [20] Tan M X, Le Q V. Efficientnet:Rethinking model scaling for convolutional neural networks[C]//International conference on machine learning. Long Beach, United States:PMLR, 2019:6105-6114.
    [21] Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA:IEEE, 2018:7132-7141.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

张天峰,冉秉东,王楷.基于压力容器裂纹图像检测及识别算法研究[J].重庆大学学报,2022,45(7):103-111.

复制
分享
文章指标
  • 点击次数:441
  • 下载次数: 748
  • HTML阅读次数: 527
  • 引用次数: 0
历史
  • 收稿日期:2022-03-12
  • 在线发布日期: 2022-07-27
文章二维码
您是第11526349 位访问者
主管单位：中华人民共和国教育部
主办单位：重庆大学
地址：重庆市沙坪坝正街174号
电话：
重庆大学学报 ® 2025 版权所有