基于卷积神经网络X射线环焊缝缺陷检测  

X-ray circumferential weld defect detection based on convolutional neural network

作　　者：张龙飞 高炜欣[1,2,3] 冯小星 Zhang Longfei;Gao Weixin;Feng Xiaoxing(Xi’an Shiyou University,Xi’an 710065,China;Shaanxi Key Laboratory of Measurement and Control Technology for Oil and Gas Wells,Xi’an 710065,China;Key Laboratory of Photoelectric Gas/Oil Logging and Detecting,Ministry of Education,Xi’an 710065,China)

机构地区：[1]西安石油大学,西安710065 [2]陕西省油气井测控技术重点实验室,西安710065 [3]光电油气测井与检测教育部重点实验室,西安710065

出　　处：《焊接》2022年第3期26-34,共9页Welding & Joining

基　　金：陕西省重点研发计划项目(2020GY-179);陕西省自然科学基金(2020JQ-788);西安石油大学研究生创新与实践能力培养项目(YCS21213193)。

摘　　要：针对工业X射线焊缝图像对比度低、缺陷模糊且相对面积较小及难以识别的问题,设计了结合卷积神经网络的识别框架。根据缺陷图像特点,设计了对应的神经网络结构、卷积模板及池化模板的大小。在分析确定神经网络结构的基础上,卷积神经网络的灵敏度和训练算法也在文中一并给出。通过实例对神经网络结构进行了有效性的验证,缺陷检测准确率达97%,误报率仅为3%。同时,对适用于卷积神经网络进行识别的X射线焊缝图像进行了分析,发现灰度直方图有效信息跨度范围在50之上的卷积神经网络可以有效识别。文中所设计的神经络对X射线焊缝缺陷图像的识别可行、有效。Aiming at the problems of low contrast of industrial X-ray weld images,fuzzy defects and relatively small areas,and they were difficult to identify,a recognition framework combined with convolutional neural networks was designed.According to the characteristics of the defect image,the size of the corresponding neural network structure,convolution template and pooling template were designed.Based on the analysis and determination of the neural network structure,the sensitivity and training algorithm of the convolutional neural network were also given in the article.The effectiveness of the neural network structure was verified through examples,the defect detection accuracy rate was 97%and the false alarm rate was only 3%.At the same time,the X-ray weld image suitable for the recognition of the convolutional neural network was analyzed,it was found that the convolutional neural network with the effective information span of the gray histogram above 50 could be effectively identified.It showed that the neural network designed in this paper was feasible and effective in the recognition of X-ray weld defect images.

关 键 词：X射线 缺陷识别 卷积神经网络 灵敏度 

分 类 号：TG441.7[金属学及工艺—焊接]