Quality Assessment Algorithm of X-Ray Images in Overall Girth Welds Based on Deep Neural Network
Publication: Journal of Pipeline Systems Engineering and Practice
Volume 14, Issue 1
Abstract
Defect recognition and assessment are essential technologies for the safety of pipelines. Recently, deep neural network methods have shown great progress in recognizing pipeline weld defects. However, the current methods cannot achieve online quality assessment for overall girth welds. To solve this problem, this paper proposes a novel quality assessment algorithm for defect recognition and assessment of X-ray girth weld images. First, a two-stage defect classifier based on residual neural network (ResNet) is proposed, which consists of a ResNet18 region classifier and a ResNet50 defect classifier. It can make up for the lack of a single classifier so that the performance and speed of defect recognition can be improved. Second, the feature-extraction calculator is used to extract and calculate the area of the weld defects based on the smallest bounding rectangle method. Third, we propose a quality evaluator based on an improved ensemble learning algorithm and long short-term memory (LSTM), so that the girth welds can be well assessed. Finally, an experiment is conducted using pipeline girth weld X-ray images. The analytic hierarchy process (AHP) method is used to comprehensively assess the level of overall girth-weld defects. The experimental results show that the proposed method is effective in recognizing and evaluating the girth-weld defects of X-ray images. And the accuracy of the quality evaluator can reach 92% for the quality assessment of overall girth welds, compared with manual quality decisions. It effectively achieves online quality assessment for girth welds and has higher evaluation accuracy.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This work was financially supported by the National Natural Science Foundation of China (Grant No. 51575528) and the Science Foundation of China University of Petroleum, Beijing (No. 2462020XKJS01).
References
Agus, K. 2017. “Welding defect classification based on convolution neural network (CNN) and Gaussian Kernel.” In Proc., 2017 Int. Seminar on Intelligent Technology and Its Applications (ISITIA), 261–265. New York: IEEE.
Bastian, B. T. 2019. “Visual inspection and characterization of external corrosion in pipelines using deep neural network.” NDT&E Int. 107 (Oct): 102134. https://doi.org/10.1016/j.ndteint.2019.102134.
Chen, J. 2014. “Improvement of welding heat source models for TIG-MIG hybrid welding process.” J. Manuf. Process. 16 (4): 485–493. https://doi.org/10.1016/j.jmapro.2014.06.002.
Chen, T. G. 2021. “Research on bearing fault diagnosis method based on ensemble methods.” Bull. Sci. Technol. 37: 57–61. https://doi.org/10.13774/j.cnki.kjtb.2021.04.011.
Daniel, B. 2019. “Automated defect classification of Aluminium 5083 TIG welding using HDR camera and neural networks.” J. Manuf. Process 45 (Sep): 603–613. https://doi.org/10.1016/j.jmapro.2019.07.020.
Galos, J. 2021. “Novel non-destructive technique for detecting the weld fusion zone using a filler wire of high x-ray contrast.” NDT&E Int. 124 (Dec): 102537. https://doi.org/10.1016/j.ndteint.2021.102537.
Gang, W. 2002. “Automatic identification of different types of welding defects in radiographic images.” NDT&E Int. 35 (8): 519–528. https://doi.org/10.1016/S0963-8695(02)00025-7.
Günther, J. 2016. “Intelligent laser welding through representation, prediction, and control learning: An architecture with deep neural networks and reinforcement learning.” Mechatronics 34 (Mar): 1–11. https://doi.org/10.1016/j.mechatronics.2015.09.004.
Kim, S. 2021. “Weld-quality prediction algorithm based on multiple models using process signals in resistance spot welding.” Metals 11 (9): 1459. https://doi.org/10.3390/met11091459.
Knaak, C. 2021. “A spatio-temporal ensemble deep learning architecture for real-time defect detection during laser welding on low power embedded computing boards.” Sensors 21 (12): 4205. https://doi.org/10.3390/s21124205.
Lei, Z. L. 2019. “Real-time weld geometry prediction based on multi-information using neural network optimized by PCA and GA during thin-plate laser welding.” J. Manuf. Process 43 (Jul): 207–217. https://doi.org/10.1016/j.jmapro.2019.05.013.
Liang, Y. 2019. “Machine learning of weld joint penetration from weld pool surface using support vector regression.” J. Manuf. Process 41 (May): 23–28. https://doi.org/10.1016/j.jmapro.2019.01.039.
Liu, B. 2018. “Weld defect images classification with VGG16-based neural network.” In Digital TV and wireless multimedia communication. Singapore: Springer.
Liu, X. F. 2017. “Visual sensing of the weld pool geometry from the topside view in keyhole plasma arc welding.” J. Manuf. Process 26 (Apr): 74–83. https://doi.org/10.1016/j.jmapro.2017.01.011.
Lv, N. 2017. “Automated control of welding penetration based on audio sensing technology.” J. Mater. Process. Technol. 250 (Dec): 81–98. https://doi.org/10.1016/j.jmatprotec.2017.07.005.
Miao, X. Y., and H. Zhao. 2022. “Regulating control of in-pipe intelligent isolation plugging tool based on adaptive dynamic programming.” J. Pipeline Syst. Eng. Pract. 13 (2): 04022003. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000635.
Nafaa, N. 2019. “Unsupervised weld defect classification in radiographic images using multivariate generalized Gaussian mixture model with exact computation of mean and shape parameters.” Comput. Ind. 108 (Jun): 132–149. https://doi.org/10.1016/j.compind.2019.02.010.
Neury, B. 2017. “Automated detection of welding defects in pipelines from radiographic images DWDI.” NDT&E Int. 86 (Mar): 7–13. https://doi.org/10.1016/j.ndteint.2016.11.003.
Pan, H. 2020. “A new image recognition and classification method combining transfer learning algorithm and mobile net model for welding defects.” IEEE Access 8 (Jun): 119951–119960. https://doi.org/10.1109/ACCESS.2020.3005450.
Rajashekar, R. 2016. “Development of a model for friction stir weld quality assessment using machine vision and acoustic emission techniques.” J. Mater. Process. Technol. 229 (Mar): 265–274. https://doi.org/10.1016/j.jmatprotec.2015.09.030.
Ranjan, R. 2016. “Classification and identification of surface defects in friction stir welding: An image processing approach.” J. Manuf. Process 22 (Apr): 237–253. https://doi.org/10.1016/j.jmapro.2016.03.009.
Sangeetha, D. 2019. “FPGA implementation of cost-effective robust Canny edge detection algorithm.” J. Real-Time Image Process. 16 (4): 957–970. https://doi.org/10.1007/s11554-016-0582-2.
Shao, J. X. 2012. “Automatic weld defect detection based on potential defect tracking in real-time radiographic image sequence.” NDT&E Int. 46 (Mar): 14–21. https://doi.org/10.1016/j.ndteint.2011.10.008.
Shen, Q. M. 2009. “Automatic classification of weld defects in radiographic images.” NDT&E Int. 52 (3): 134–139. https://doi.org/10.1784/insi.2010.52.3.134.
Sun, J. 2019. “An effective method of weld defect detection and classification based on machine vision.” IEEE Trans. Ind. Inf. 15 (12): 6322–6333. https://doi.org/10.1109/TII.2019.2896357.
Sung, W. P. 2004. “Quantity analysis for welding performance in manufacturing processes.” Int. J. Adv. Manuf. Technol. 23 (9): 707–711. https://doi.org/10.1007/s00170-003-1651-9.
Wang, J. R. 2021. “Summary of research on application of deep learning in weld defect detection.” Mech. Electr. Eng. Technol. 50. https://doi.org/10.3969/j.issn.1009-9492.2021.03.012.
Wu, Y. Z. 2019. Research on data-driven defects identification and evaluation of weld image. Shanghai, China: Shanghai Jiao Tong Univ.
Xu, G. Y. 2011. “Study of welding defect recognition algorithm based on selective ensemble learning.” J. China Univ. Mining Technol. 40 (6): 949–953.
Yan, Y. 2020. “A deep learning-based ultrasonic pattern recognition method for inspecting girth weld cracking of gas pipeline.” IEEE Sensors J. 20 (14): 7997–8006. https://doi.org/10.1109/JSEN.2020.2982680.
Yang, L. 2018. “A welding quality detection method for arc welding robot based on 3D reconstruction with SFS algorithm.” Int. J. Adv. Manuf. Technol. 94 (1): 1209–1220. https://doi.org/10.1007/s00170-017-0991-9.
Yang, L. 2021a. “An automatic welding defect location algorithm based on deep learning.” NDT&E Int. 120 (Jun): 102435. https://doi.org/10.1016/j.ndteint.2021.102435.
Yang, L. 2021b. “Weld defect classification in radiographic images using unified deep neural network with multi-level features.” J. Intell. Manuf. 32 (2): 459–469. https://doi.org/10.1007/s10845-020-01581-2.
Zhang, Y. X. 2019. “Welding defects detection based on deep learning with multiple optical sensors during disk laser welding of thick plates.” J. Manuf. Syst. 51 (Apr): 87–94. https://doi.org/10.1016/j.jmsy.2019.02.004.
Information & Authors
Information
Published In
Journal of Pipeline Systems Engineering and Practice
Volume 14 • Issue 1 • February 2023
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Mar 13, 2022
Accepted: Oct 27, 2022
Published online: Dec 9, 2022
Published in print: Feb 1, 2023
Discussion open until: May 9, 2023
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Zhouyu Yan, Hong Zhao, Xingyuan Miao, Boxuan Gao, Design and Trajectory Optimization of a Large-Diameter Steel Pipe Grinding Robot, Journal of Pipeline Systems Engineering and Practice, 10.1061/JPSEA2.PSENG-1581, 15, 3, (2024).