Applying SDR with CNN to Identify Weld Defect: A New Processing Method
Publication: Journal of Pipeline Systems Engineering and Practice
Volume 14, Issue 2
Abstract
X-ray weld images are investigated to achieve nondestructive identification of defects in oil and gas pipeline welds. The content mainly includes image filtering and enhancement, weld defect suspected defect region (SDR) segmentation, and defect identification. (1) The x-ray image quality is poor, as shown by a lot of noise and low contrast. Therefore, the mean filtering method is used to filter out the noise, and a nonlinear enhancement using sin function is proposed to improve the contrast between the weld and the background. (2) In the image segmentation, a segmentation method of SDR is proposed. Region of interest (ROI) is first extracted, and then SDRs are segmented using clustering. (3) In defect identification, deep learning networks are used for SDRs. A 6-stage, 10-layer convolutional neural network (CNN) network structure is designed, and the convolutional kernels are set to be and . In the experiments, the proposed method is able to automate the processing of x-ray weld images and improve the processing efficiency. The identification accuracy rate is 98.9%.
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 research is supported by the key R&D plan project of Shaanxi Province. The project number is 2022GY-135. The paper does not involve state secrets and any infringement issues related to intellectual property rights. In this paper, the following items are disclosed in detail, including the academic research process, key research information which can promote scientific research transparency, and the materials with integrity for the publication of academic results.
References
Babu, C. M., G. Prabaharan, and R. Pitchai. 2022. “Efficient detection of glaucoma using double tier deep convolutional neural network.” Pers. Ubiquitous Comput. (Mar). https://doi.org/10.1007/s00779-022-01673-1.
Borkowski, L., C. Sorini, and A. Chattopadhyay. 2022. “Recurrent neural network-based multiaxial plasticity model with regularization for physics-informed constraints.” Comput. Struct. 258 (Jan): 106678. https://doi.org/10.1016/j.compstruc.2021.106678.
Chai, R. S. 2021. “Otsu’s image segmentation algorithm with memory-based fruit fly optimization algorithm.” Complexity 2021 (Mar): 1–11. https://doi.org/10.1155/2021/5564690.
Daum, W., P. Rose, H. Heidt, and J. H. Builtjes. 1987. “Automatic recognition of weld defects in x-ray inspection—Reconnaissance automatique des défauts d’une soudure inspectée aux Rayons X.” Br. J. Nondestr. Test. 29 (2): 79–82.
Gayer, A., A. Saya, and A. Shiloh. 1990. “Automatic recognition of welding defects in real-time radiography.” NDT Int. 23 (3): 131–136. https://doi.org/10.1016/0308-9126(90)90109-2.
Gupta, S., S. Mazumdar, and M. Student. 2013. “Sobel edge detection algorithm.” Int. J. Comput. Sci. Manage. Res. 2 (2): 1578–1583.
Hu, K., S. Liu, Y. Zhang, C. Cao, F. Xiao, W. Huang, and X. Gao. 2020. “Automatic segmentation of dermoscopy images using saliency combined with adaptive thresholding based on wavelet transform.” Multimedia Tools Appl. 79 (21–22): 14625–14642. https://doi.org/10.1007/s11042-019-7160-0.
Kaftandjian, V., O. Dupuis, D. Babot, and Y. M. Zhu. 2003. “Uncertainty modelling using Dempster-Shafer theory for improving detection of weld defects.” Pattern Recognit. Lett. 24 (1–3): 547–564. https://doi.org/10.1016/S0167-8655(02)00276-3.
Lashkia, V. 2001. “Defect detection in X-ray images using fuzzy reasoning.” Image Vis. Comput. 19 (5): 261–269. https://doi.org/10.1016/S0262-8856(00)00075-5.
Liao, T. W., and Y. M. Li. 1998. “An automated radiographic NDT system for weld inspection: Part II—Flaw detection.” NDT&E Int. 31 (3): 183–192. https://doi.org/10.1016/S0963-8695(97)00042-X.
Lin, B. T., and K. M. Huang. 2013. “An adaptive-network-based fuzzy inference system for predicting springback of U-bending.” Trans. Can. Soc. Mech. Eng. 37 (3): 335–344. https://doi.org/10.1139/tcsme-2013-0023.
Liu, M. Y., Y. P. Chen, L. He, Y. Zhang, and J. Xie. 2021. “LF-YOLO: A lighter and faster yolo for weld defect detection of X-ray image.” Preprint, submitted October 28, 2021. https://arxiv.org/abs/2110.15045.
Liu, W., S. Shan, H. Y. Chen, R. Wang, J. Sun, and Z. Zhou. 2022a. “X-ray weld defect detection based on AF-RCNN.” Welding World 66 (6): 1165–1177. https://doi.org/10.1007/s40194-022-01281-w.
Liu, Z. B., H. X. Lu, X. P. Pan, M. Xu, R. Lan, and X. Luo. 2022b. “Diagnosis of Alzheimer’s disease via an attention-based multi-scale convolutional neural network.” Knowl.-Based Syst. 238 (Feb): 107942. https://doi.org/10.1016/j.knosys.2021.107942.
Madhavan, M., and G. Gopakumar. 2022. “DBNLDA: Deep Belief Network based representation learning for lncRNA-disease association prediction.” Appl. Intell. 52 (5): 5342–5352. https://doi.org/10.1007/s10489-021-02675-x.
Mery, D., and M. A. Berti. 2003. “Automatic detection of welding defects using texture features.” Insight Nondestr. Test. Cond. Monit. 45 (10): 676–681. https://doi.org/10.1784/insi.45.10.676.52952.
Nacereddine, N., A. B. Goumeidane, and D. Ziou. 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.
Paraschiakos, S., C. R. de Sá, J. Okai, P. E. Slagboom, M. Beekman, and A. Knobbe. 2022. “A recurrent neural network architecture to model physical activity energy expenditure in older people.” Data Min. Knowl. Discovery 36 (1): 477–512. https://doi.org/10.1007/s10618-021-00817-w.
Patil, R. V., Y. P. Reddy, and A. M. Thote. 2020. “Multi-class weld defect detection and classification by support vector machine and artificial neural network.” In Vol. 206 of Smart innovation, systems and technologies, 429–438. Singapore: Springer.
Priya, M. S., and G. M. Kadhar Nawaz. 2017. “Multilevel image thresholding using OTSU’s algorithm in image segmentation.” Int. J. Sci. Eng. Res. 8 (5): 101–105.
Raj, S., S. Tripathi, and K. C. Tripathi. 2022. “ArDHO-deep RNN: Autoregressive deer hunting optimization based deep recurrent neural network in investigating atmospheric and oceanic parameters.” Multimedia Tools Appl. 81 (6): 7561–7588. https://doi.org/10.1007/s11042-021-11794-z.
Sathiyadhas, S. S., A. Soosai, and C. V. Maria. 2022. “A network intrusion detection system in cloud computing environment using dragonfly improved invasive weed optimization integrated Shepard convolutional neural network.” Int. J. Adapt. Control Signal Process. 36 (5): 1060–1076. https://doi.org/10.1002/acs.3386.
Shang, J. Z., W. P. An, Y. Liu, B. Han, and Y. Guo. 2020. “Oil pipeline weld defect identification system based on convolutional neural network.” KSII Trans. Internet Inf. Syst. 14 (3): 1086–1103.
Sohn, I. 2021. “Deep belief network-based intrusion detection techniques: A survey.” Expert Syst. Appl. 167 (Apr): 114170. https://doi.org/10.1016/j.eswa.2020.114170.
Valavanis, I., and D. Kosmopoulos. 2010. “Multiclass defect detection and classification in weld radiographic images using geometric and texture features.” Expert Syst. Appl. 37 (12): 7606–7614. https://doi.org/10.1016/j.eswa.2010.04.082.
Weixin, G., H. Yeheng, and M. Xiangyang. 2012. “Study on sub-arc X-ray welding image defect segmentation algorithm and defect model.” Trans. China Weld. Inst. 33 (4): 37–41.
Yang, D. M., Y. R. Cui, Z. Y. Yu, and H. Yuan. 2022. “Deep learning based steel pipe weld defect detection.” Appl. Artif. Intell. 35 (15): 1237–1249. https://doi.org/10.1080/08839514.2021.1975391.
Yang, J., W. M. Bao, Y. M. Liu, X. Li, J. Wang, and Y. Niu. 2021. “A pairwise graph regularized constraint based on deep belief network for fault diagnosis.” Digital Signal Process. 108 (Jan): 102868. https://doi.org/10.1016/j.dsp.2020.102868.
Yu, L. C., S. H. He, X. S. Liu, M. Ma, and X. Xiang. 2022. “Engineering-oriented bridge multiple-damage detection with damage integrity using modified faster region-based convolutional neural network.” Multimedia Tools Appl. 81 (13): 18279–18304. https://doi.org/10.1007/s11042-022-12703-8.
Zaidia, S. S. A., M. S. Ansari, A. Aslam, N. Kanwal, M. Asghar, and B. Lee. 2022. “A survey of modern deep learning-based object detection models.” Digital Signal Process. 126 (11): 103514. https://doi.org/10.48550/arXiv.2104.11892.
Information & Authors
Information
Published In
Journal of Pipeline Systems Engineering and Practice
Volume 14 • Issue 2 • May 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: May 17, 2022
Accepted: Oct 20, 2022
Published online: Jan 4, 2023
Published in print: May 1, 2023
Discussion open until: Jun 4, 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.