摘要
PE燃气管道的连接质量能直接影响中低压燃气的正常输送,在电熔焊接时产生的结构畸变、冷焊等缺陷会显著削弱管道的力学性能,威胁燃气管网的稳定运行。因此,基于实地采集的PE燃气管道电熔焊接缺陷DR图像数据集,提出了基于DSG-ResNet34模型的缺陷检测方法,以实现对电熔焊接缺陷进行快速精准地检测。该网络模型由主干网络CBAM-ResNet34模块、动态稀疏门控金字塔DSG-FPN、多尺度检测头3个部分组成,首先通过主干网络CBAM-ResNet34结构从通道和空间两个维度提升网络模型对缺陷特征的关注度,然后通过动态稀疏门控金字塔DSG-FPN结构的动态稀疏门控模块、Inception模块、稀疏连接动态融合多尺度缺陷特征,有效保留小目标特征、抑制背景噪声,最后通过多尺度检测头结构将提取到的丰富特征转化为具体的检测结果。DSG-ResNet34模型的缺陷检测准确率最高可达95.5%、P2层精确率最高可达82.7%、小目标召回率最低为85.6%、检测速度可达68 fps、参数量为22.3×10^(6),该模型能快速定位识别孔洞、熔融面夹杂、结构畸变、冷焊这4类典型电熔焊接缺陷,检测性能与速度优于其他网络模型。为PE管道焊接质量智能化检测提供了高精度解决方案,对保障燃气管网安全运行具有重要意义。
The connection quality of PE gas pipelines can directly affect the normal transmission of medium and low-pressure gas.Structural distortion,cold welding and other defects produced by electrofusion welding will significantly weaken the mechanical properties of the pipeline,which will threaten the stable operation of the gas pipeline network.Therefore,based on the DR Image datasets of PE gas pipelines electrofusion welding defects collected on-site,this paper proposes a defect detection method based on the DSG-ResNet34 model to realize rapid and accurate detection of electrofusion welding defects.This network model consists of three parts:the backbone network CBAM-ResNet34 module,the dynamic sparse gating feature pyramid networks DSG-FPN,and the multi-scale detection head.Firstly,the CBAM-ResNet34 structure of backbone network is used to enhance the network model′s attention to defect features from two dimensions of channel and space.Then,the dynamic sparse gating module,Inception module and sparse connection of the dynamic sparse gating pyramid DSG-FPN structure are used to dynamically fuse multi-scale defect features to effectively retain small target features and suppress After controlling the background noise,the multi-scale head structure is used to transform the extracted rich features into concrete detection results.The defect detection accuracy of DSG-ResNet34 model is up to 95.5%,the P2 layer percision is up to 82.7%,the small target′s minimum recall is 85.6%,the detection speed is up to 68 fps,and the parameter number is 22.3×10^(6).This model can quickly locate and identify four typical electrofusion welding defects,namely holes,fused surface inclusion,structural distortion and cold welding,which detection performance and speed are superior to other network models.This study provides a high-precision solution for intelligent testing of PE pipeline welding quality,which is of great significance for ensuring the safe operation of gas pipeline network.The connection quality of PE gas pipelines can directly affect the normal transmission of medium and low-pressure gas.Structural distortion,cold welding and other defects produced by electrofusion welding will significantly weaken the mechanical properties of the pipeline,which will threaten the stable operation of the gas pipeline network.Therefore,based on the DR Image datasets of PE gas pipelines electrofusion welding defects collected on-site,this paper proposes a defect detection method based on the DSG-ResNet34 model to realize rapid and accurate detection of electrofusion welding defects.This network model consists of three parts:the backbone network CBAM-ResNet34 module,the dynamic sparse gating feature pyramid networks DSG-FPN,and the multi-scale detection head.Firstly,the CBAM-ResNet34 structure of backbone network is used to enhance the network model′s attention to defect features from two dimensions of channel and space.Then,the DSG-FPN,which integrates a dynamic sparse gating module,an Inception module,and sparse connections,dynamically fuses multi-scale defect features-effectively preserving small-target features while suppressing background noise.Finally,the multi-scale detection head converts the enriched features into precise detection outputs.The DSG-ResNet34 model achieves a defect detection accuracy of up to 95.5%,with a P2 layer precision of 82.7%and a minimum recall rate of 85.6%for small targets.The detection speed reaches 68 fps,and the model contains 22.3 million parameters.This model can quickly locate and identify four typical electrofusion welding defects:holes,fused surface inclusion,structural distortion and cold welding.Both its detection performance and speed outperform existing models.This study provides a high-precision solution for intelligent testing of PE pipeline welding quality,which is of great significance for ensuring the safe operation of gas pipeline network.
作者
凌晓
刘露
孙宝财
张正棠
徐晓刚
Ling Xiao;Liu Lu;Sun Baocai;Zhang Zhengtang;Xu Xiaogang(School of Petrochemical Engineering,Lanzhou University of Technology,Lanzhou 730000,China;Gansu Province Special Equipment Inspection and Testing Institute,Lanzhou 730000,China)
出处
《仪器仪表学报》
北大核心
2025年第6期228-240,共13页
Chinese Journal of Scientific Instrument
基金
国家自然科学基金(52466003)
甘肃省重点研发计划(23YFGA0059)项目资助。
