Skip to main content
SpringerLink
Log in

Study on Ultrasonic Detection Pattern Recognition of Natural Gas Steel Pipeline Defects

  • ACOUSTIC METHODS
  • Published:
Russian Journal of Nondestructive Testing Aims and scope Submit manuscript

Abstract

In ultrasonic detection of natural gas steel pipeline corrosion defects, conventional pattern recognition adopts manual feature extraction method, which has the problems of strong subjectivity and low universality. Based on this, a method combining feature extraction with random forest (RF) classification using convolutional neural network (CNN) is proposed. Firstly, the echo signals with different defects obtained in the experiment are de-redundant, then the signal is transformed by continuous wavelet transform to obtain a high-resolution two-dimensional time-frequency map, and then the features of the picture are extracted by convolutional neural network. Finally, the full connection layer of convolutional neural network is used as the input of random forest to establish a random forest classification model. Experiments show that the recognition accuracy of the model for cylinder defects, cone defects and cube defects is 88.6%, which is higher than other models for extracting features manually.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.
Fig. 9.
Fig. 10.
Fig. 11.
Fig. 12.
Fig. 13.
Fig. 14.
Fig. 15.
Fig. 16.

Similar content being viewed by others

REFERENCES

  1. Jianshu Cao, Yang Li, Li Lin, et al., Nondestructive testing technology for natural gas pipeline, NDT Int., 2013, vol. 35, no. 5, pp. 20–25.

    Google Scholar 

  2. Ayesha Khalid, Ali M-Ghazanfar, Khan Dr.-Tariq-Mairaj-Rasool, et al., Assessment and characterization of welded mild steel (E-6013) using ultrasonic testing and Hilbert Huang transform, Russ. J. Nondestr. Test., 2021, vol. 57, no. 5, pp. 401–407.

    Article  Google Scholar 

  3. Donglin Tang, Zibing Wei, Feng Pan, et al., Ultrasonic internal detection of pipeline corrosion based on PCA and SVM, Chin. J. Sens. Transducers, 2018, vol. 31, no. 7, pp. 1040–1045.

    Google Scholar 

  4. Jingpin Jiao, Quan Cheng, Deyu Liu, et al., Research on corrosion grade evaluation method of tank floor based on ultrasonic detection, China Spec. Equip. Safety, 2017, vol. 33, no. 8, pp. 29–34.

    Google Scholar 

  5. Santos, J.-B. and Perdigao, F., Automatic defects classification—A contribution, NDT & E Int., 2001, vol. 34, no. 5, pp. 313–318.

    Article  Google Scholar 

  6. Alicia Romero Ramírez, Mason John-S.-D., and Pearson Neil, Experimental study to differentiate between top and bottom defects for MFL tank floor inspections, NDT & E Int., 2009, vol. 42, no. 1, pp. 16–21.

    Article  Google Scholar 

  7. Zi Zhang, Pan Hong, Wang Xingyu, et al., Machine learning-enriched Lamb wave approaches for automated damage detection, Sensors, 2020, vol. 20, no. 6, p. 1790.

    Article  Google Scholar 

  8. Fuqiang Sun, Wang Ning, He Jingjing, et al., Lamb wave damage quantification using GA-based LS-SVM, Materials, 2017, vol. 10, no. 6, p. 648.

    Article  Google Scholar 

  9. Óscar Martín, Pereda María, Santos José-Ignacio, et al., Assessment of resistance spot welding quality based on ultrasonic testing and tree-based techniques, J. Mater. Process. Technol., 2014, vol. 214, no. 11, pp. 2478–2487

    Article  Google Scholar 

  10. Amirhossein Rahbari, Rébillat Marc, Mechbal Nazih, et al., Unsupervised damage clustering in complex aeronautical composite structures monitored by Lamb waves: An inductive approach, Eng. Appl. Artif. Intell., 2021, p. 97104099.

  11. Govind-K. Sharma, Kumar Anish, Jayakumar T., et al., Ensemble empirical mode decomposition based methodology for ultrasonic testing of coarse grain austenitic stainless steels, Ultrasonics, 2015, vol. 57, pp. 167–178.

    Article  Google Scholar 

  12. Hongguang Yun, Rayhana Rakiba, Pant Shashank, et al., Nonlinear ultrasonic testing and data analytics for damage characterization: A review, Measurement, 2021, vol. 186, p. 110155.

    Article  Google Scholar 

  13. Rui Zhang, Zhao Na, Fu Liuhu, et al., Ultrasonic diagnosis method for stainless steel weld defects based on multi-domain feature fusion, Sens. Rev., 2022, vol. 42, no. 2, pp. 214–229.

  14. Luka Posilović, Medak Duje, Subašić Marko, et al., Generative adversarial network with object detector discriminator for enhanced defect detection on ultrasonic B-scans, Neurocomputing, 2021, vol. 459, pp. 361–369.

    Article  Google Scholar 

  15. Long Bai, Le Bourdais Florian, Miorelli Roberto, et al., Ultrasonic defect characterization using the scattering matrix: A performance comparison study of Bayesian inversion and machine learning schemas, IEEE Trans. Ultrason. Ferroelectr. Freq. Cont., 2021, vol. 68, no. 10, pp. 3143–3155.

    Article  Google Scholar 

  16. Tian-Tian Zhu, Bo Song, Jie Mao, et al., Intelligent analysis method of WELD PAUT data based on deep learning, J. Beijing Univ. Aeronaut. Astronaut., 2021, pp. 1–14.

  17. Chenglong Shi, Fangfang Shi, and Bixing Zhang, Defect type analysis using DEEP neural network and wavelet packet transform, Acta Acust. Sin., 2016, vol. 41, no. 4, pp. 499–506.

    Google Scholar 

  18. Alexander Bowler, Pound Michael, and Watson Nicholas, Convolutional feature extraction for process monitoring using ultrasonic sensors, Comput. & Chem. Eng., 2021, vol. 155, p. 107508.

    Article  CAS  Google Scholar 

  19. Shifeng Guo, Feng Haowen, Feng Wei, et al., Automatic quantification of subsurface defects by analyzing laser ultrasonic signals using convolutional neural networks and wavelet transform, IEEE Trans. Ultrason. Ferroelectr. Freq. Cont., 2021, vol. 68, no. 10, pp. 3216–3225.

    Article  Google Scholar 

  20. Issam Hammad, Simpson Ryan, Tsague Hippolyte-Djonon, et al., Using deep learning to automate the detection of flaws in nuclear fuel channel UT scans, IEEE Trans. Ultrason. Ferroelectr. Freq. Cont., 2022, vol. 69, no. 1, pp. 323–329.

    Article  Google Scholar 

  21. Nauman Munir, Kim Hak-Joon, Song Sung-Jin, et al., Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments, J. Mech. Sci. Technol., 2018, vol. 32, no. 7, pp. 3073–3080.

    Article  Google Scholar 

  22. Pushpa Pandey, Rai Akshay, and Mitra Mira, Explainable 1-D convolutional neural network for damage detection using Lamb wave, Mech. Syst. Signal Process., 2022, vol. 164, p. 108220.

    Article  Google Scholar 

  23. Lei Su, Zha Zheyu, Lu Xiangning, et al., Using BP network for ultrasonic inspection of flip chip solder joints, Mech. Syst. Signal Proces., 2013, vol. 34, nos. 1–2, pp. 183–190.

    Article  Google Scholar 

  24. Dazhong Li and Jie Zhao, Defect signal recognition based on EMD and GA-SVM in ultrasonic detection, Chin. Meas. Test., 2016, vol. 42, no. 1, pp. 102–106.

    Google Scholar 

  25. Jinhai Liu, Mingrui Fu, and Jianhua Tang, MFL inner detection based defect recognition method, Chin. J. Sci. Instrum., 2016, vol. 37, no. 11, pp. 2572–2581.

    Google Scholar 

  26. Dazhong Li and Jie Zhao, Ultrasonic signal endpoint detection based on FOA-SVM, Chin. Meas. Test., 2016, vol. 42, no. 5, pp. 103–106, 123.

  27. Yan, Y., Liu, D., Gao, B., et al., A deep learning-based ultrasonic pattern recognition method for inspecting girth weld cracking of gas pipeline, IEEE Sens. J., 2020, vol. 20, no. 14, pp. 7997–8006.

    Article  Google Scholar 

  28. Nitish Srivastava, Hinton Geoffrey, Krizhevsky Alex, et al., Dropout: A simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 2014, vol. 15, pp. 1929–1958.

    Google Scholar 

  29. Jing Liu, Xu Guocheng, Ren Lei, et al., Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural network, Int. J. Adv. Manuf. Technol., 2017, vol. 90, nos. 9–12, pp. 2581–2588.

    Article  Google Scholar 

  30. Yaguo Lei, He Zhengjia, and Zi Yanyang, Application of an intelligent classification method to mechanical fault diagnosis, Exp. Syst. Appl., 2009, vol. 36, no. 6, pp. 9941–9948.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Mechanical Engineering, Southwest Petroleum University, 610500, Chengdu, China

    HaiBo Liang, Yi Wang & Hai Yang

Authors
  1. HaiBo Liang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yi Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hai Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to HaiBo Liang, Yi Wang or Hai Yang.

Ethics declarations

The authors declare that they have no conflicts of interest.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liang, H., Wang, Y. & Yang, H. Study on Ultrasonic Detection Pattern Recognition of Natural Gas Steel Pipeline Defects. Russ J Nondestruct Test 58, 903–916 (2022). https://doi.org/10.1134/S1061830922100333

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1061830922100333

Keywords:

Search

Navigation