基于深度学习的海上导管架平台损伤检测
DOI:
作者:
作者单位:

1.青岛大学 自动化学院;2.自然资源部 第一海洋研究所

作者简介:

通讯作者:

中图分类号:

TV32

基金项目:

山东省自然科学(DKXZZ202206);国家自然科学(61703221)


Damage Detection of Offshore Jacket Platform Based on Deep Learning
Author:
Affiliation:

1.School of Automation, Qingdao University;2.First Institute of Oceanography, Ministry of Natural Resources

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    导管架平台是海上作业的常用结构物形式,其健康状态决定着海洋开发过程是否安全。针对导管架平台损伤检测过程中损伤敏感特征的提取问题,提出了一种基于深度学习的损伤检测模型。为更好的贴合卷积神经网络的特点,该模型首先将一维时域信号转化为二维灰度图;然后通过卷积神经网络中提取二维灰度图中存在的损伤特征并以此进行损伤检测。通过在导管架平台模型上进行的实验,比较了不同灰度图生成方式对检测结果的影响。最后,损伤检测实验的结果表明,该检测模型对损伤种类的识别准确率分别可以达到99.4%,具备良好的损伤检测能力;对损伤程度的识别准确率为96.3%,能够应用于对导管架平台的损伤预警。

    Abstract:

    Jacket platforms are commonly used structures in offshore operations, and their health status determines the safety of the ocean development process. Aiming at the problem of extracting damage-sensitive features during the damage detection process of jacket platform, a damage detection model based on deep learning is proposed. In order to better fit the characteristics of the convolutional neural network, this model first converts the one-dimensional time domain signal into a two-dimensional grayscale image; then extracts the damage features existing in the two-dimensional grayscale image through the convolutional neural network and This is used for damage detection. Through experiments on the jacket platform model, the effects of different grayscale image generation methods on the detection results were compared. Finally, the results of damage detection experiments show that the detection model can identify damage types with an accuracy of 99.4% , and has good damage detection capabilities; The accuracy of identifying the degree of damage is 96.3%, and it can be applied to damage early warning of jacket platforms.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-01-21
  • 最后修改日期:2024-01-31
  • 录用日期:2024-02-01
  • 在线发布日期:
  • 出版日期: