Abstract
In nondestructive testing (NDT), geometrical features of a flaw embedded in the material such as its location, length, and orientation are critical factors to assess the severity of the flaw and make post-manufacturing decisions to improve the design. In this study, artificial intelligence (AI) based NDT approach was applied to the ultrasonic oscillograms obtained from virtual ultrasonic NDT to estimate geometrical features of a flaw. First, a numerical model of NDT specimen was constructed using acoustic finite element analysis (FEA) to produce the ultrasonic signals. The model was validated by comparing the simulated signals produced from the numerical model with the experimental data from actual NDT tests. Then, 750 numerical models containing flaws with different locations, lengths, and orientation angles were generated by FEA. Next, the oscillograms produced by the models were divided into 3 datasets: 525 for training, 113 for validation, and 112 for testing. Training inputs of the network were parameters extracted from ultrasonic signals by fitting them to sine functions. Lastly, to evaluate the network performance, outputs of the network including flaw’s location, length, and angle were compared with the desired values for all datasets. Deviations of the outputs from desired values were calculated by a regression analysis. Statistical analysis was also performed by measuring root mean square error (RMSE) and efficiency. RMSE in x-location, y-location, length, and angle estimations are 0.09 mm, 0.19 mm, 0.46 mm, and 0.75°, with efficiencies of 0.9229, 0.9466, 0.9140, and 0.9154, respectively for the testing dataset. Results suggest that the proposed AI-based method has the potential to interpret the oscillograms from ultrasonic NDT to estimate geometrical features of flaws embedded in the material.
Similar content being viewed by others
Abbreviations
- ρ :
-
Matter density
- C :
-
Speed of sound
- p t :
-
Total acoustic pressure
- t :
-
Time
- q d :
-
Dipole domain source
- Q m :
-
Monopole domain source
- x :
-
X_location of the crack
- y :
-
Y_location of the crack
- l :
-
Length of the crack
- θ :
-
Angle of the crack
- MSE :
-
Mean squared error
- n :
-
Number of outputs
- Y i(j):
-
ANN output
- T i(j):
-
Desired output
- m :
-
Number of training samples
- RMSE :
-
Root mean square error
- X d :
-
Desired variable
- X s :
-
Estimated variable
- E :
-
Efficiency
- X d :
-
Average of the desired variable
- NDT:
-
Non-destructive testing
- ANN:
-
Artificial neural network
- RMSE:
-
Root mean square error
- E:
-
Efficiency
- FFNN:
-
Feed forward neural network
- BP:
-
Back propagation
- FFBP:
-
Feed forward back propagation
- MSE:
-
Mean squared error
References
Cartz, L. (1995). Nondestructive testing. Materials Park, OH: ASM International.
R/D Tech Inc. (2007). Introduction to phased array ultrasonic technology applications. Olympus, NDT Waltham, MA.
Matlack, K. H., Kim, J.-Y., Jacobs, L. J., & Qu, J. (2015). Review of second harmonic generation measurement techniques for material state determination in metals. Journal of Nondestructive Evaluation, 34(1), 273.
Mostavi, A., Kamali, N., Tehrani, N., Chi, S.-W., Ozevin, D., & Indacochea, J. E. (2017). Wavelet based hormonics decomposition of ultrasonic signal in assessment of plastic strain in aluminum. Measurement, 106, 66–78.
Reber, K., Beller, M., & Uzelac, N. I. (2002). How do defect assessment methods influence the choice and construction of in-line inspection tools. In 2002 4th international pipeline conference (pp. 2039–2044).
Achenbach, J. D. (2000). Quantitative nondestructive evaluation. International Journal of Solids and Structures, 37(1–2), 13–27.
Charles, J. H. (2003). Handbook of nondestructive evaluation.
http://www.asnt.org © 2019 The American Society for NDT, Inc.
Singh, J. K., & Bhardwaj, S. K. (2015). Non destructive testing of welded metals to enhance the quality of materials. International Journal of Technical Research and Applications, 3(3), 47–51.
Rymarczyk, T., Klosowski, G., & Kozlowski, E. (2018). A non-destructive system based on electrical tomography and machine learning to analyze the moisture of buldings. Sensors, 18(7), 2285.
Simas Filho, E. F., Souza, Y. N., Lopes, J. L., Farias, C. T., & Albuquerque, M. C. (2013). Decision support system for ultrasound inspection of fiber metal laminates using statistical signal processing and neural networks. Ultrasonics, 53, 1104–1111.
Simas Filho, E. F., Silva, M. M., Jr., Farias, P. C., Albuquerque, M. C., Silva, I. C., & Farias, C. T. (2016). Flexible decision support system for ultrasound evaluation of fiber–metal laminates implemented in a DSP. NDT E International, 79, 38–45.
Cruz, F. C., Simas Filho, E. F., Albuquerque, M. C., Silva, I. C., Farias, C. T., & Gouvêa, L. L. (2017). Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing. Ultrasonics, 73, 1–8.
Cai, H., Xu, C., Zhou, S., Yan, H., & Yang, L. (2015). Study on the thick-walled pipe ultrasonic signal enhancement of modified S-transform and singular value decomposition. Mathematical Problems in Engineering, 2015, 312620.
Kesharaju, M., & Nagarajah, R. (2015). Feature selection for neural network based defect classification of ceramic components using high frequency ultrasound. Ultrasonics, 62, 271–277.
Lawson, S. W., & Parker, G. A. (2018). Automatic detection of defects in industrial ultrasound images using a neural network. Retrieved November 2, 2018, from https://pdfs.semanticscholar.org/3009/3dc2a6402e14cef4523caa708173d7de1acb.pdf.
Simone, G., et al. (2002). Feature extraction techniques for ultrasonic signal classification. International Journal of Applied Electromagnetics and Mechanics, 15(1–4), 291–294.
Meng, M., et al. (2017). Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks. Neurocomputing, 257, 128–135.
Sarkar, S., et al. (2016). Deep learning for structural health monitoring: A damage characterization application. In Annual conference of the prognostics and health management society.
Sambath, S., Nagaraj, P., Selvakumar, N., Arunachalam, S., & Page, T. (2010). Automatic detection of defects in ultrasonic testing using artificial neural network. International Journal of Microstructure and Materials Properties, 5(6), 561–574.
Ye, J., Ito, S., & Toyama, N. (2018). Computerized ultrasonic imaging inspection: From shallow to deep learning. Sensors, 18(11), 3820.
Le Chau, N., Tran, N. T., & Dao, T. P. (2020). A multi-response optimal design of bistable compliant mechanism using efficient approach of desirability, fuzzy logic, ANFIS and LAPO algorithm. Applied Soft Computing, 94, 106486.
Le Chau, N., & Dao, T. P. (2020). An efficient hybrid approach of improved adaptive neural fuzzy inference system and teaching learning-based optimization for design optimization of a jet pump-based thermoacoustic-Stirling heat engine. Neural Computing and Applications, 32(11), 7259–7273.
Munir, N., Kim, H. J., Song, S. J., & Kang, S. S. (2018). Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments. Journal of Mechanical Science and Technology, 32(7), 3073–3080.
Darmon, M., et al. (2011). Recent advances in semi-analytical scattering models for NDT simulation. In Journal of Physics: Conference Series (Vol. 269. No. 1). IOP Publishing.
Achenbach, J. D., Gautesen, A. K., & McMaken, H. (1982). Rays methods for waves in elastic solids. . New York: Pitman Press.
Ufimtsev, P. Y. (2007). Fundamentals of the physical theory of diffraction. . New York: Wiley.
Darmon, M., et al. (2016). A system model for ultrasonic NDT based on the physical theory of diffraction (PTD). Ultrasonics, 64, 115–127.
Zou, C., et al. (2015). Detection of longitudinal cracks with a serrated columnar phased array transducer: A simulation study. In 2015 International conference on control, automation and robotics. IEEE.
Tian, P. Q., Feng, Y. W., Zhan, S. Z., Zhang, X., & Xue, X. (2020). Numerical simulation of ultrasonic testing reliability of civil aircraft considering the influence of the angle between the sound beam axis and the crack orientation. IOP Conference Series: Materials Science and Engineering., 715(1), 012012.
Owowo, J., & Olutunde Oyadiji, S. (2017). Finite element analysis and experimental measurement of acoustic wave propagation for leakage detection in an air-filled pipe. International Journal of Structural Integrity.
Hornick, K., Stinchcombe, M., & White, H. (1989). Multilayer feed-forward networks are universal approximators. Neural Networks, 2, 359–366.
Sarkar, R., Julai, S., Hossain, S., Chong, W. T., & Rahman, M. (2019). A comparative study of activation function of NAR and NARX neural network for long-term wind speed forecasting in Malaysia. Mathematical Problems in Engineering, 2019, ID 6403081, pp. 1–14.
Acknowledgements
The work was supported by Korea-Canada AI Research for Manufacturing sponsored by Korea Electrotechnology Research Institute (KERI).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lari, S., Qian, Y. & Kwon, HJ. Assessment of Geometrical Features of Internal Flaws with Artificial Neural Network. Int. J. Precis. Eng. Manuf. 22, 777–789 (2021). https://doi.org/10.1007/s12541-021-00515-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12541-021-00515-z