基于Faster R-CNN的海底管道智能检测方法  

Intelligent detection method for submarine pipelines based on Faster R-CNN

作　　者：俞进 唐建华 神祥凯 刘金海[3] YU Jin;TANG Jianhua;SHEN Xiangkai;LIU Jinhai(China National Offshore Oil Corporation,Beijing 100010,China;Energy Development Equipment Technology Co.,Ltd.,China National Offshore Oil Corporation,Tianjin 300452,China;School of Information Science and Engineering,Northeastern University,Shenyang Liaoning 110819,China)

机构地区：[1]中国海洋石油集团有限公司,北京100010 [2]中海油能源发展装备技术有限公司,天津300452 [3]东北大学信息科学与工程学院,辽宁沈阳110819

出　　处：《中国安全科学学报》2023年第6期80-87,共8页China Safety Science Journal

基　　金：国家自然科学基金资助(61973071);辽宁省自然科学基金资助(2019-KF-03-04)。

摘　　要：为提高海底管道缺陷及组件的检测精度并实现智能化海底管道安全检测,提出一种基于快速区域卷积神经网络(Faster R-CNN)的海底管道智能检测方法。首先,通过基值校正和分段映射-伪彩色化方法,将漏磁检测信号转化为伪彩色图,以增强漏磁信号的关键特征;其次,基于多模态数据增强来提升检测模型的泛化能力;然后,基于多模态数据增强后的样本训练改进的Faster R-CNN网络,建立最优的智能检测模型;最后,以试验场和渤海在役管道为例,验证所提方法的有效性。结果表明:所提方法的平均检测精度可达93.8%,相较原始的Faster R-CNN算法提高8%,且平均交并比达到0.75,能够精准地实现海底油气管道多目标检测,保障海底管道的安全运行。In order to improve the detection accuracy of submarine pipeline defects and components and to realize intelligent submarine pipeline safety detection,a Faster R-CNN-based intelligent detection method for submarine pipelines was proposed.Firstly,the key features of the signals were enhanced by converting the signals into a pseudo-color map through basis value correction and segmentation mapping-pseudo-colorization methods.Secondly,the generalization capability of the detection model was improved based on multimodal data enhancement.Then,the improved Faster R-CNN network was trained based on the samples after multimodal data enhancement to establish the optimal intelligent detection model.Finally,the effectiveness of the proposed method was verified by using the test site and the Bohai Sea in service as examples.The results show that the average detection accuracy of the proposed method can reach 93.8%,which is 8%better than the original Faster R-CNN algorithm,and the average intersection over union reaches 0.75,which can accurately achieve the multi-target detection of submarine oil and gas pipelines and ensure the safe operation of submarine pipelines.

关 键 词：快速区域卷积神经网络(Faster R-CNN) 海底管道 智能检测 漏磁内检测 多目标检测 

分 类 号：X937[环境科学与工程—安全科学]