[1]周飞达,李晋惠,梁明华.基于语义分割的DWTT断口图像识别和评定方法研究[J].石油管材与仪器,2020,6(01):28-31.[doi:10.19459/j.cnki.61-1500/te.2020.01.007]
 ZHOU Feida,LI Jinhui,LIANG Minghua.DWTT Fracture Image Recognition and Evaluation Method Based on Semantic Segmentation[J].Petroleum Tubular Goods & Instruments,2020,6(01):28-31.[doi:10.19459/j.cnki.61-1500/te.2020.01.007]
点击复制

基于语义分割的DWTT断口图像识别和评定方法研究
分享到:

《石油管材与仪器》[ISSN:2096-0077/CN:61-1500/TE]

卷:
6
期数:
2020年01期
页码:
28-31
栏目:
开发设计
出版日期:
2020-02-25

文章信息/Info

Title:
DWTT Fracture Image Recognition and Evaluation Method Based on Semantic Segmentation
文章编号:
2096-0077(2020)01--0028-04
作者:
周飞达1李晋惠1梁明华2
1.西安工业大学计算机科学与工程学院 陕西 西安 710021;2.中国石油集团石油管工程技术研究院 陕西 西安 710077
Author(s):
ZHOU Feida1LI Jinhui1 LIANG Minghua2
1.School of Computer Science and Engineering, Xi′an Technology University, Xi′an, Shaanxi 710021,China; 2.CNPC Tubular Goods Research Institute, Xi′an, Shaanxi 710077,China
关键词:
落锤撕裂断口DeepLabV3+图像语义分割
Keywords:
drop weight tear fracture DeepLabV3+image semantic segmentation
分类号:
TP3
DOI:
10.19459/j.cnki.61-1500/te.2020.01.007
文献标志码:
A
摘要:
对石油管材落锤撕裂断口进行评定,目前采用的方法主要通过游标卡尺等测量工具进行测量和计算,存在对工作人员经验要求高、主观因素影响大、不规则形貌判别困难和效率低等缺点。针对以上问题提出了一种具有空洞卷积的编解码器模型的管材断口图像语义分割方法,首先对采集好的试样断口进行脆性区域的数据集标记,然后利用标记好的数据集对DeepLabV3+网络模型进行训练,该模型可以有效地分割试样断口中的脆性区域。最后对管材试样断口评定的计算方法进行了基于像素级别的改进,在对实验结果进行分析和对比后表明,所提出的方法具有更高稳定性、高准确率和良好分割效果。
Abstract:
When evaluating the petroleum pipe steel drop weight tear fracture, the current method is mainly by measuring with tools such as vernier calipers and calculation. There are disadvantages such as high requirements for staff experience, large influence of subjective factors, difficulty in discriminating irregular morphology and low efficiency. Aiming at these problems, a steel fracture image semantic segmentation method with a codec model with atrous convolution is proposed. Firstly, the data set of the brittle region is marked on the fracture of the collected sample, then the DeepLabV3+ network model is trained by using the marked data set. The model can effectively segment the brittle region in the fracture of the sample. Finally, the calculation method of the fracture evaluation of steel samples was improved based on the pixel level. After analyzing and comparing the experimental results, the proposed method has higher stability, high accuracy and good segmentation effect.

参考文献/References:

[1] 张轶鑫.基于图像分割和模式识别的钢材断口图像分析方法研究[D].哈尔滨:哈尔滨工业大学,2017.
[2] 李亮,曹峰,王亚龙,等. X90管线钢的低温冲击韧性和断口形貌分析[J].金属热处理,2015,58(1):190-193.
[3] 王馨. 钢材落锤撕裂断口形貌研究与DWTT图像分析系统的开发[D].鞍山:辽宁科技大学,2014.
[4] 方健. 基于落锤撕裂试验(DWTT)的钢材动态断裂行为研究[D].沈阳:东北大学,2015.
[5] ZHENG Yang. The Fracture During Dropweight Tear Test of High Performance Pipeline Steel and its Abnormal Fracture Appearance[J].Procedia Materials Science,2014,3.
[6] 冈萨雷斯. 数字图象处理:第三版[M].北京:电子工业出版社,2017.
[7] TOSHIHIKO A,TAISHI F,YASUHIRO S,et al. Evaluation of Prestrain Effect on Abnormal Fracture Occurrence in DropWeight Tear Test for Linepipe Steel with High Charpy Energy[J].Procedia Structural Integrity,2016.
[8] CHEN L, PAPANDREOU G,KOKKINOS I,et al. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs[J].IEEE transactions on pattern analysis and machine intelligence,2018,40(4):834-848.
[9] 袁立,袁吉收,张德政. 基于DeepLab-v3+的遥感影像分类[J].激光与光电子学进展,2019,56(15):236-243.
[10] 刘国栋,方健,张建伟,等. 机器视觉技术在评定DWTT试样断口中的应用[J].理化检验(物理分册),2015,51(4):237-242.

备注/Memo

备注/Memo:
第一作者简介:周飞达,男,1993年生,在读硕士研究生,研究方向是模式识别与图像处理。E-mail:hopegrace@foxmail.com
更新日期/Last Update: 2020-02-25