CHINESE JOURNAL OF ENERGETIC MATERIALS
+高级检索
基于深度学习的PBX裂纹像素级识别方法
作者:
作者单位:

1.中国工程物理研究院化工材料研究所, 四川 绵阳 621999;2.兰州大学核科学与技术学院, 甘肃 兰州 730000

作者简介:

通讯作者:

基金项目:

国家自然科学基金资助(12105267)


PBX Crack Pixel Level Recognition Method based on Deep Learning
Author:
Affiliation:

1.Institute of Chemical Materials, CAEP, Mianyang 621999, China;2.School of Nuclear Science and Technology, Lanzhou University, Lanzhou 730000, China

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
    摘要:

    高聚物粘结炸药(Polymer Bonded Explosive, PBX)内部裂纹对其性能及可靠性具有明显影响,裂纹的精确识别是PBX内部质量检测的关键。针对PBX内部裂纹识别,基于U-Net和SegNet两种像素级图像识别网络,建立了5种深度学习网络,对比研究了网络连接方式和预训练模型对裂纹识别的影响。基于CT获取的PBX裂纹图建立了数据集,对5种网络进行了训练,采用准确率(A)、F1值(F1)和平均交并比(MIoU)指标对网络进行了评估,在此基础上选择细节识别性能最优的网络用于PBX裂纹的识别和量化分析。结果表明,针对裂纹像素级识别,U-Net型网络优于Seg-Net型网络,网络中Concatenate操作比Pooling Indices操作保留更多图像细节信息,采用预训练模型MobileNet和ResNet可以提高网络训练速度,但导致其裂纹像素级识别性能降低。利用建立的识别方法开展PBX裂纹识别研究,实现了对PBX裂纹的像素级识别,裂纹检出率0.9570,单像素识别准确率为0.9936,MIoU为0.9873,相对裂纹面积为0.7585。

    Abstract:

    The performance and dependability of PBX are significantly impacted by internal cracks. Accurate crack identification and quantitative analysis are crucial to evaluate the performance of PBX. Currently, the ability to identify and quantitatively analyze internal cracks of PBX needs to be further improved. Consequently, research on a deep learning-based method for PBX crack identification was conducted. Based on the popular deep learning networks, five different deep learning network structures were designed. This study aimed to compare the effects of network type, connection style, and pre-trained models on the recognition of PBX cracks. Internal crack images of PBX were obtained by CT technique. The training dataset of network was constructed using these crack images. The crack dataset was used to train five different types of networks. The performance of five networks was assessed based on Accuracy, F1, and MIoU. Select an outstanding network for PBX crack recognition and training based on the findings. The results indicate that, U-Net outperforms Seg-Net in pixel-level crack recognition and the Concatenate operation preserves more features compared to the Pooling Indices method. The pre-trained model (MobileNet and ResNet) can improve the training speed of the network, but its crack pixel-level recognition performance is reduced. The proposed method was applied to identify PBX crack, achieving pixel-level recognition. The results include a crack detection rate of 0.9570, a single pixel recognition accuracy of 0.9936, an MIoU of 0.9873, and a relative crack area of 0.7585, demonstrating superiority over traditional image segmentation methods.

    参考文献
    相似文献
    引证文献
文章指标
  • PDF下载次数:
  • HTML阅读次数:
  • 摘要点击次数:
  • 引用次数:
引用本文

吕亮亮,张伟斌,李公平,等.基于深度学习的PBX裂纹像素级识别方法[J].含能材料, 2024, 32(5):545-553. DOI:10.11943/CJEM2023212.
LV Liang-liang, ZHANG Wei-bin, LI Gong-ping, et al. PBX Crack Pixel Level Recognition Method based on Deep Learning[J]. Chinese Journal of Energetic Materials, 2024, 32(5):545-553. DOI:10.11943/CJEM2023212.

复制
历史
  • 收稿日期: 2023-10-08
  • 最后修改日期: 2023-12-14
  • 录用日期: 2023-12-11
  • 在线发布日期: 2023-12-12
  • 出版日期: 2024-05-25