Skip to main content
SpringerLink
Log in

Intelligent Quantification of Metal Defects in Storage Tanks Based on Machine Learning

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

Abstract

Wall-climbing robot are seeing increasing adoption to automated remote and in situ inspection of industrial assets, removing the need for hazardous manned access. The ultrasonic dry-coupling detection device installed on the wall-climbing robot detects the defects of the tank wall. Aiming at the difficulty that the ultrasonic A-scan signal obtained by the ultrasonic dry-coupling detection method has waveform cross-aliasing, which makes it difficult to obtain effective information in traditional feature extraction, Herein, we combine the fast Fourier transform, wavelet packet decomposition and empirical mode decomposition techniques to propose a 3D-SFE method performs multi-scale feature extraction on dry coupled signals. At the same time, in view of the difficulty that traditional nondestructive testing models cannot quantify the defect area accurately, we introduce the XGBoost model to better quantify the defect area. Our proposed defect area quantification model based on multi-scale feature extraction achieves 99.9% accuracy on the training set and 81.5% on the test set. Furthermore, we also analyzed the influence of defect characteristics, sample number, defect shape and depth on the model, and then provided certain guiding significance for the detection of tank defects.

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.

REFERENCES

  1. Chang, J.I. and Lin, C.-C., A study of storage tank accidents, J. Loss Prev. Process Ind., 2006, vol. 19, no. 1, pp. 51–59.

    Article  Google Scholar 

  2. Menon, J., Pease, D.A., Rees, R., Duyanovich, L., and Hillsberg, B., IBM Storage Tank—A heterogeneous scalable SAN file system, IBM Syst. J., 2003, vol. 42, no. 2, pp. 250–267.

    Article  Google Scholar 

  3. Gradetsky, V.G. and Knyaz’kov, M.M., Multi-functional wall climbing robot, Adapt. Mobile Rob., 2012, pp. 807–812.

    Book  Google Scholar 

  4. Kalra, L.P., Shen, W., and Gu, J., A wall climbing robotic system for nondestructive inspection of above ground tanks, 2006 Can. Conf. Electr. Comput. Eng. (Ottawa, 2006), pp. 402–405.

    Google Scholar 

  5. Moniri, M.M., Bamdad, M., and Sayyadan, M.Z., A novel design of wall climbing robot for inspection of storage steel tanks, 2015 3rd RSI Int. Conf. Rob. Mechatronics (ICROM) (Tehran, 2015), pp. 557–562.

  6. Maurtua, I., et al., MAINBOT—Mobile robots for inspection and maintenance in extensive industrial plants, Energ. Procedia, 2014, vol. 49, pp. 1810–1819.

    Article  Google Scholar 

  7. Valls Miro, J., Ulapane, N., Shi, L., Hunt, D., and Behrens, M., Robotic pipeline wall thickness evaluation for dense nondestructive testing inspection, J. Field Rob., 2018, vol. 35, no. 8, pp. 1293–1310.

    Article  Google Scholar 

  8. Park, S.H., Kim, J.W., Nam, M.J., and Lee, J.J., Magnetic flux leakage sensing-based steel cable NDE technique incorporated on a cable climbing robot for bridge structures, Adv. Sci. Technol., 2013, vol. 83, Trans. Tech. Publ., pp. 217–222.

    Google Scholar 

  9. Wang, R. and Kawamura, Y., Development of climbing robot for steel bridge inspection, Ind. Rob. Int. J., 2016, vol. 43, no. 4, pp. 429–447.

    Article  Google Scholar 

  10. Aleshin, N.P., et al., Assessing reliability of testing welded joints of steel tank walls using ultrasonic and eddy current methods, Russ. J. Nondestr. Test., 2022, vol. 58, no. 9, pp. 769–778.

    Article  Google Scholar 

  11. Megid, W.A. and Hay, D.R., Image analysis based acoustics approach for tank floor condition evaluation, Russ. J. Nondestr. Test., 2022, vol. 58, no. 7, pp. 563–573.

    Article  Google Scholar 

  12. Salzburger, H.J., Niese, F., and Dobmann, G., EMAT pipe inspection with guided waves, Weld. World, 2012, vol. 56, nos. 5–6, pp. 35–43.

    Article  Google Scholar 

  13. Ding Chao, et al., The research and application of wheeled dry-coupling ultrasonic technology in steel plate thickness measurement, Russ. J. Nondestr. Test., 2023, vol. 59, no. 7, pp. 753–766.

    Article  Google Scholar 

  14. Robinson, A., Drinkwater, B., and Allin, J., Dry-coupled low-frequency ultrasonic wheel probes: application to adhesive bond inspection, NDT & E Int., 2003, vol. 36, no. 1, pp. 27–36.

    Article  Google Scholar 

  15. Bourne, S., Newborough, M., and Highgate, D., High frequency ultrasonic wheel probe using hydrophilic polymers as novel solid couplant, Insight, 2001, vol. 43, no. 1, pp. 26–28.

    CAS  Google Scholar 

  16. Brotherhood, C., Drinkwater, B., and Freemantle, R., An ultrasonic wheel-array sensor and its application to aerospace structures, Insight Nondestr. Test. Cond. Monit., 2003, vol. 45, no. 11, pp. 729–734.

    Article  Google Scholar 

  17. Liu, J., Xu, G., Ren, L., Qian, Z., and Ren, L., Defect intelligent identification in resistance spot welding ultrasonic detection based on wavelet packet and neural network, Int. J. Adv. Manuf. Technol., 2017, vol. 90, no. 9, pp. 2581–2588.

    Article  Google Scholar 

  18. Couade, M., et al., Quantitative assessment of arterial wall biomechanical properties using shear wave imaging, Ultrasound Med. & Biol., 2010, vol. 36, no. 10, pp. 1662–1676.

    Article  Google Scholar 

  19. Liu, T., Bao, J., Wang, J., and Zhang, Y., A hybrid CNN-LSTM algorithm for online defect recognition of CO2 welding, Sensors, 2018, vol. 18, no. 12, p. 4369.

    Article  ADS  PubMed  PubMed Central  Google Scholar 

  20. Ding Chao, et al., DHT: dynamic vision transformer using hybrid window attention for industrial defect images classification, IEEE Instrum. & Meas. Mag., 2023, vol. 26, no. 2, pp. 19–28.

    Article  Google Scholar 

  21. Cassels, B., Shark, L.K., Mein, S.J., Nixon, A., Barber, T., and Turner, R., Robust principal component analysis of ultrasonic sectorial scans for defect detection in weld inspection, Conf. Multimodal Sens. Technol. Appl. (Munich, 2019).

  22. Fan, M., Xia, J., Meng, X., and Zhang, K., Single-phase grounding fault types identification based on multi-feature transformation and fusion, Sensors, 2022, vol. 22, no. 9, p. 3521.

    Article  ADS  PubMed  PubMed Central  Google Scholar 

  23. Utkin, L., et al., A weighted random survival forest, Knowl.-Based Syst., 2019, vol. 177, pp. 136–144.

    Article  Google Scholar 

  24. Yan, Y., et al., Research on diagnosis of breast cancer based on ultrasonic radio frequency signals, Nanosci. Nanotechnol. Lett., 2019, vol. 11, no. 8, pp. 1116–1124.

    Article  Google Scholar 

  25. Davidov, V.S. Recognition of incipient defects in the units of ship machinery by vibrodiagnostics based on optimum decision rules, Russ. J. Nondestr. Test., 2019, vol. 55, pp. 185–191.

    Article  Google Scholar 

  26. Ye, Y., Bruzzone, L., Shan, J., Bovolo, F., and Zhu, Q., Fast and robust matching for multimodal remote sensing image registration, IEEE Trans. Geosci. Remote Sens., 2019, vol. 57, no. 11, pp. 9059–9070.

    Article  ADS  Google Scholar 

  27. Rinkevich, A.B. and Perov, D.V., A wavelet analysis of acoustic fields and signals in ultrasonic nondestructive testing, Russ. J. Nondestr. Test., 2005, vol. 41, no. 2, pp. 93–101.

    Article  Google Scholar 

  28. Myakinin, O., et al., The empirical mode decomposition algorithm via fast Fourier transform, in Appl. Digital Image Process. XXXVII, Bellingham: SPIE, 2014, vol. 9217.

    Google Scholar 

  29. Abushanab, W.S., Oil transmissions pipelines condition monitoring using wavelet analysis and ultrasonic techniques, Engineering, 2013, vol. 5, no. 6, pp. 551–555.

    Article  Google Scholar 

  30. Cooley, J.W. and Tukey, J.W., An algorithm for the machine calculation of complex Fourier series, Math. Comput., 1965, vol. 19, no. 90, pp. 297–301.

    Article  MathSciNet  Google Scholar 

  31. Slesarev, D., Defect identification based on wavelet decomposition for MFL non-destructive inspection of steel plates, Insight Nondestr. Test. Cond. Monit., 2021, vol. 63, no. 3, pp. 146–150.

    Article  CAS  Google Scholar 

  32. Bettayeb, F., Haciane, S., and Aoudia, S., Improving the time resolution and signal noise ratio of ultrasonic testing of welds by the wavelet packet, NDT & E Int., 2005, vol. 38, no. 6, pp. 478–484.

    Article  Google Scholar 

  33. Voznesenskii, A., et al., Denoising algorithm based on EMD with adaptive adjustment of coefficients, 2019 IEEE Conf. Russ. Young Res. Electr. Electron. Eng. (EIConRus) (St. Petersburg–Moscow, 2019).

  34. Feng, W., Zhou, X., Zeng, X., and Yang, C., Ultrasonic flaw echo enhancement based on empirical mode decomposition, Sensors, 2019, vol. 19, no. 2, p. 236.

    Article  ADS  PubMed  PubMed Central  Google Scholar 

  35. Lee, K., Feature extraction schemes for ultrasonic signal processing, in 5th Int. Conf. Comput. Sci. Convergence Inform. Technol. (Seoul, 2010), pp. 366–372.

  36. Islam, M., Sohaib, M., Kim, J., and Kim, J.-M., Crack classification of a pressure vessel using feature selection and deep learning methods, Sensors, 2018, vol. 18, no. 12, p. 4379.

    Article  ADS  PubMed  PubMed Central  Google Scholar 

  37. Zhang, Z., Wang, Y., and Wang, K., Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network, J. Intel. Manuf., 2013, vol. 24, no. 6, pp. 1213–1227.

    Article  Google Scholar 

  38. De Lathauwer, L., De Moor, B., and Vandewalle, J., A multilinear singular value decomposition, SIAM J. Matrix Anal. Appl., 2000, vol. 21, no. 4, pp. 1253–1278.

    Article  MathSciNet  Google Scholar 

  39. Krautkrämer, J. and Krautkrämer, H., Ultrasonic Testing of Materials, Berlin: Springer, 2013.

    Google Scholar 

  40. Bentler, P.M. and Bonett, D.G., Significance tests and goodness of fit in the analysis of covariance structures, Psychol. Bull., 1980, vol. 88, no. 3, p. 588.

    Article  Google Scholar 

  41. Chen, T. and Guestrin, C., XGBoost: A scalable tree boosting system, 25th ACM SIGKDD Int. Conf. Knowl. Discovery Data Min. (San Francisco, 2016), pp. 785–794.

  42. McNamara, M.E., Zisser, M., Beevers, C.G., and Shumake, J., Not just “big” data: Importance of sample size, measurement error, and uninformative predictors for developing prognostic models for digital interventions, Behav. Res. Ther., 2022, p. 104086.

  43. Coates, A., Ng, A., and Lee, H., An analysis of single-layer networks in unsupervised feature learning, in 14th Int. Conf. Artif. Intel. Stat. (Ft. Lauderdale, 2011), pp. 215–223.

  44. Al Iqbal, M.R., Rahman, S., Nabil, S.I., and Chowdhury, I.U.A., Knowledge based decision tree construction with feature importance domain knowledge, in 2012 7th Int. Conf. Electr. Comput. Eng. (Dhaka, 2012), pp. 659–662.

  45. Dudarin, P., Samokhvalov, M., and Yarushkina, N., An approach to feature space construction from clustering feature tree, Artif. Intel. 16th Russ. Conf. RCAI 2018 (Moscow, 2018).

Download references

Funding

This work was supported by School Project (no. 2023ZR009) of Chengdu Technological University, Technology Planning Project (no. 2022MK115) of State Administration of Market Supervision and Administration and Innovative Entrepreneurial Project (no. CXCY-2021-22) of China Occupational Safety and Health Association.

Author information

Authors and Affiliations

  1. School of Intelligent Manufacturing, Chengdu Technological University, 611730, Chengdu, China

    Chao Ding

  2. Sichuan Special Equipment Inspection Institute, 610100, Chengdu, Sichuan, China

    Yuanyuan He, Yamei Li & Pingjie Wang

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

    Donglin Tang, Yunliang Zhao, Sheng Rao & Chao Qin

Authors
  1. Chao Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuanyuan He
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Donglin Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yamei Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Pingjie Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yunliang Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Sheng Rao
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Chao Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yuanyuan He.

Ethics declarations

The authors of this work declare that they have no conflicts of interest.

Additional information

Publisher’s Note.

Pleiades Publishing remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ding, C., He, Y., Tang, D. et al. Intelligent Quantification of Metal Defects in Storage Tanks Based on Machine Learning. Russ J Nondestruct Test 59, 1207–1222 (2023). https://doi.org/10.1134/S1061830923600685

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1061830923600685

Keywords:

Search

Navigation