Vol. 20 No. 4 (2023): Journal of Non Destructive Testing and Evaluation (JNDE), Dec 2023
Research Papers

DPAI: In-Situ Process Intelligence using Data-Driven Simulation-Assisted-Physics Aware AI (DPAI) for Simulating Wave Dynamics

PDF
  • Thulsiram Gantala,
  • Krishnan Balasubramaniam

Published 07-12-2023

Keywords

  • DPAI,
  • Ultrasonic Wave simulation,
  • Phased Array,
  • FE,
  • Deep Learning,
  • RNN,
  • ConvLSTM
    • ...More
    Less

How to Cite

Thulsiram Gantala, & Krishnan Balasubramaniam. (2023). DPAI: In-Situ Process Intelligence using Data-Driven Simulation-Assisted-Physics Aware AI (DPAI) for Simulating Wave Dynamics. Journal of Non-Destructive Testing and Evaluation (JNDE), 20(4), 60–69. Retrieved from https://jnde.isnt.in/index.php/JNDE/article/view/68

Copyright (c) 2024 Journal of Non-Destructive Testing and Evaluation (JNDE)

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Abstract

AI models such as convolutional long short-term memory (ConvLSTM) recurrent neural network (RNN) have been shown here to have the capability to simulate ultrasonic wave propagation in the 2-D domain. This DPAI approach uses the Data-driven but simulation-assisted-Physics aware approach to utilizing AI networks. Our DPAI model comprises ConvLSTM with an encoder-decoder structure, which learns a representation of spatio-temporal features from the input sequence datasets. The DPAI model is trained with finite element (FE) time-domain simulation datasets consisting of distributed single and multi-point source excitation in the medium, reflection from the simple boundaries, and phased array steering. Here, this approach, called the DPAI model, is demonstrated for modelling multiple point sources to simulate forward wave propagation, reflection from the boundaries, and phased array beam steering ultrasound wave dynamics in a 2D plane. The trained DPAI model was found to be significantly faster in generating simulations for the time evolution of field values in the elastodynamic problem when compared to the conventional finite element explicit dynamic solvers.

PDF

References

  1. T Gantala and K. Balasubramaniam, “Automated Defect Recognition for Welds Using Simulation Assisted TFM Imaging with Artificial Intelligence,” J. Nondestr. Eval. NDE4.0, 2021.
  2. S. Shivaprasad, C. V. Krishnamurthy, A Pandala, A. Saini, A. Ramachandran, K Balasubramaniam. Numerical Modelling Methods for Ultrasonic Wave Propagation Through Polycrystalline Materials. Trans Indian Inst Met, vol. 72, pp. 2923–2932, 2019.
  3. D. Dutykh, T. Katsaounis, and D. Mitsotakis, “Finite volume schemes for dispersive wave propagation and runup,” J. of Comp. Physics, vol. 230, Iss. 8, pp. 3035-3061, 2011.
  4. P.H. Wen, “Meshless local Petrov–Galerkin (MLPG) method for wave propagation in 3D poroelastic solids,” Eng. Analysis with Boundary Elements, vol. 34, Iss. 4, pp. 314-323, 2010.
  5. S. Shivaprasad, A Pandala, C. V. Krishnamurthy, K. Balasubramaniam, “Wave localized finite-difference-time-domain modelling of scattering of elastic waves within a polycrystalline material,” The Journal of the Acoustical Society of America, vol. 144, pp.3313, 2018
  6. Y. Lu, S. Peng, X. Cui, D. Li, K. Wang, and Z. Xing, “3D FDTD anisotropic and dispersive modeling for GPR using rotated staggered grid method,” Computers & Geosciences, vol. 136, pp. 104397, 2020
  7. J. L. Rose, " Ultrasonic guided waves in solid media,". Cambridge University Press, 512 p., 2014.
  8. KJ. Bathe, "Finite element procedures, vol. 2," Watertown, MA, USA, 2016.
  9. X. Guo, W. Li, and F. Iorio, "Convolutional neural networks for steady flow approximation", Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discover. Data Min., pp. 481-490, 2016.
  10. Z. Lin, H. Pan, G. Gui, and C. Yan, “Data-driven structural diagnosis and conditional assessment: From shallow to deep learning,” Proc. SPIE Sensors Smart Struct. Technol. Civil, Mech., Aerosp. Syst., vol. 10598. Mar. 2018.
  11. O. Noakoasteen, S. Wang, Z. Peng, and C. Christodoulou, "Physics-Informed Deep Neural Networks for Transient Electromagnetic Analysis," in IEEE Open Journal of Antennas and Propagation, vol. 1, pp. 404-412, 2020, doi: 10.1109/OJAP.2020.3013830.
  12. Balasubramaniam, K., Gantala, T., Purushothaman, P., & Surekha, M. (2022). Simulation Assisted Automatic Defect Recognition (SimADR) for NDE4. 0 Inspection Datasets. Journal of Non-Destructive Testing and Evaluation (JNDE), 19(4), 35-40.
  13. Gantala, T., PL, S., & Balasubramaniam, K. (2023). Automated Defect Recognition (ADR) for Monitoring Industrial Components using Neural Networks with Phased Array Ultrasonic Images. Measurement Science and Technology.
  14. I. Virkkunen, T. Koskinen, O. Jessen-Juhler, and J. Rinta-Aho, “Augmented ultrasonic data for machine learning,” 2019.
  15. J. Vrana and R Singh, " Cyber-Physical Loops as Drivers of Value Creation in NDE 4.0," J Nondestruct Eval 40, pp. 61, 2021.
  16. W. Rawat and Z. Wang, “Deep convolutional neural networks for image classification: A comprehensive review,” Neural Comput., vol. 29, no. 9, pp. 2352–2449, Sep. 2017.
  17. L. von Rueden, S. Mayer, R. Sifa, C. Bauckhage, and J. Garcke, "Combining machine learning and simulation to a hybrid modelling approach: Current and future directions," in: International Symposium on Intelligent Data Analysis, Springer, 2020, pp. 548–560
  18. P. O’Rorke, S. Morris, M. Amirfathi, W. Bond, and D. St Clair, “Machine learning for nondestructive evaluation,” in Machine Learning Processing. Amsterdam, The Netherlands: Elsevier, pp. 620–624, 1991.
  19. J. B. Harley and D. Sparkman, “Machine learning and NDE: Past, present, and future,” AIP Conf. Proc., vol. 2102, no. 1, Art. no. 90001, 2019.
  20. T. Guo, L. Wu, C. Wang, and Z. Xu, "Damage detection in a novel deep-learning framework: a robust method for feature extraction," Structural Health Monitoring 19 (2) (2020) 424–442.
  21. M. Rautela and S. Gopalakrishnan, "Ultrasonic guided wave based structural damage detection and localization using model assisted convolutional and recurrent neural networks," Expert Syst. Appl. (2020) 114189.
  22. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997.
  23. T. W. Hughes, I. A. D. Williamson, M. Minkov and S. Fan, "Wave physics as an analog recurrent neural network", Sci. Adv., vol. 5, no. 12, 2019.
  24. Shi, X.; Chen, Z.;Wang, H.; Yeung, D.Y.;Wong, W.k.;Woo,W.c. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. Adv. Neural Inf. Process. Syst. 2015, 28, 802–810.
  25. Wang, Y.; Gao, Z.; Long, M.;Wang, J.; Philip, S.Y. Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. In Proceedings of the International Conference on Machine Learning, Stockholm Sweden, 10–15 July 2018; pp. 5123–5132.
  26. Su, J.; Byeon, W.; Kossaifi, J.; Huang, F.; Kautz, J.; Anandkumar, A. Convolutional Tensor-Train LSTM for Spatio-temporal Learning. Adv. Neural Inf. Process. Syst. 2020, 33, 13714–13726.
  27. Gantala, T.; Balasubramaniam, K. DPAI: A Data-driven simulation-assisted-Physics learned AI model for transient ultrasonic wave propagation. Ultrasonics 2022, 121, 106671.
  28. Gantala, T., & Balasubramaniam, K. (2023). Optimizing hyperparameters of Data-driven simulation-assisted-Physics learned AI (DPAI) model to reduce compounding error. Ultrasonics, 128, 106863.
  29. Valencia, M.L.; Cantwell, C.D.; Fotiadis, S.; Pignatelli, E.; Bharath, A.A. Simulating SurfaceWave Dynamics with Convolutional Networks. arXiv 2020, arXiv:2012.00718
  30. Fotiadis, S.; Pignatelli, E.; Valencia, M.L.; Cantwell, C.; Storkey, A.; Bharath, A.A. Comparing recurrent and convolutional neural networks for predicting wave propagation. arXiv 2020, arXiv:2002.08981.
  31. Gantala, T., & Balasubramaniam, K. (2022). Implementing data-driven approach for modelling ultrasonic wave propagation using spatio-temporal deep learning (SDL). Applied Sciences, 12(12), 5881.
  32. P. Rajagopal, D. Mickael, A. S. Elizabeth, L. JS. Michael, and C. V. Richard, "On the use of absorbing layers to simulate the propagation of elastic waves in unbounded isotropic media using commercially available finite element packages," NDT and E International, vol. 51, pp. 30-40, 2012.
  33. W. A. Falcon, “PyTorch Lightning,” online https://github.com/PyTorchLightning/pytorch-lightning, vol.3, 2019.
  34. H. Nielsen, " https://towardsdatascience.com/video-prediction-using-convlstm-with-pytorch-lightning-27b195fd21a2," 2018.