Coupling Peridynamic Simulations with Data-Driven Approaches for Intelligent Fracture Prediction in Structures

H. N. Yakin; N. A. Hashim; F. Fisol; M. N. Mastor; Q. Halim

doi:10.58915/aset.v5i1.3216

Authors

H. N. Yakin Universiti Teknologi Malaysia
N. A. Hashim Universiti Malaysia Perlis
F. Fisol Universiti Teknologi Malaysia
M. N. Mastor Universiti Teknologi Malaysia
Q. Halim MRANTI Corporation Sdn. Bhd.

DOI:

https://doi.org/10.58915/aset.v5i1.3216

Keywords:

Deep Learning, Fracture Mechanics, Machine Learning, Peridynamics, Structural Health Monitoring

Abstract

Predicting fracture propagation in complex structures remains a significant challenge in computational mechanics. While Peridynamics (PD) has emerged as a robust nonlocal theory capable of naturally handling discontinuities like cracks, its high computational cost often hinders real-time application and large-scale optimization. Conversely, data-driven approaches, particularly Deep Learning (DL), offer rapid inference but often lack physical interpretability and generalizability. This paper proposes a novel hybrid framework, the Peridynamic-Informed Neural Network (PD-Net), which couples high-fidelity peridynamic simulations with a Convolutional Neural Network (CNN) to achieve intelligent, real-time fracture prediction. We utilize a bond-based peridynamic solver to generate a comprehensive dataset of damage evolution under varying loading conditions. While the data-generation process incurs a high initial computational cost, the trained model reduces inference time by an order of magnitude compared to direct numerical simulation, enabling real-time fracture prediction. This work bridges the gap between high-fidelity physics-based modeling and data-driven intelligence, offering a promising path for digital twin applications in structural health monitoring.

References

[1] Jagota, V., Sethi, A. P. S., Kumar, K. Finite element method: An overview. Walailak Journal of Science and Technology (WJST), vol 10, issue 1 (2013) pp.1-8.

[2] Liu, W. K., Li, S., Park, H. S. Eighty years of the finite element method: Birth, evolution, and future. Archives of Computational Methods in Engineering, vol 29, issue 6 (2022) pp.4431-4453.

[3] Li, H. The finite element method. In Graded Finite Element Methods for Elliptic Problems in Nonsmooth Domains (2022) pp.1-12.

[4] Silling, S. A. Reformulation of elasticity theory for discontinuities and long-range forces. Journal of the Mechanics and Physics of Solids, vol 48, issue 1 (2000) pp.175-209.

[5] Gharehbaghi, V. R., Noroozinejad Farsangi, E., Noori, M., Yang, T. Y., Li, S., Nguyen, A., Mirjalili, S. A critical review on structural health monitoring: Definitions, methods, and perspectives. Archives of Computational Methods in Engineering, vol 29, issue 4 (2022) pp.2209-2235.

[6] Cha, Y. J., Ali, R., Lewis, J., Büyükӧztürk, O. Deep learning-based structural health monitoring. Automation in Construction, vol 161 (2024) pp.105328.

[7] Mishra, M., Lourenço, P. B., Ramana, G. V. Structural health monitoring of civil engineering structures by using the internet of things: A review. Journal of Building Engineering, vol 48 (2022) pp.103954.

[8] Zhang, J., Huang, M., Wan, N., Deng, Z., He, Z., Luo, J. Missing measurement data recovery methods in structural health monitoring: The state, challenges and case study. Measurement, vol 231 (2024) pp.114528.

[9] Gordan, M., Sabbagh-Yazdi, S. R., Ismail, Z., Ghaedi, K., Carroll, P., McCrum, D., Samali, B. State-of-the-art review on advancements of data mining in structural health monitoring. Measurement, vol 193 (2022) pp.110939.

[10] Sadhu, A., Peplinski, J. E., Mohammadkhorasani, A., Moreu, F. A review of data management and visualization techniques for structural health monitoring using BIM and virtual or augmented reality. Journal of Structural Engineering, vol 149, issue 1 (2023) pp.03122006.

[11] Kudela, J., Matousek, R. Recent advances and applications of surrogate models for finite element method computations: A review. Soft Computing, vol 26, issue 24 (2022) pp.13709-13733.

[12] Erhunmwun, I. D., Ikponmwosa, U. B. Review on finite element method. Journal of Applied Sciences and Environmental Management, vol 21, issue 5 (2017) pp.999-1002.

[13] Silling, S. A. Introduction to peridynamics. In Handbook of Peridynamic Modeling (2016) pp.63-98.

[14] Madenci, E., Roy, P., Behera, D. Advances in peridynamics. (2022).

[15] Javili, A., Morasata, R., Oterkus, E., Oterkus, S. Peridynamics review. Mathematics and Mechanics of Solids, vol 24, issue 11 (2019) pp.3714-3739.

[16] Huang, X., Hu, T., Jin, Y., Li, S., Yang, D., Zheng, Z. The rationality of using dynamic relaxation method for failure simulation in peridynamics. Computer Methods in Applied Mechanics and Engineering, vol 438 (2025) pp.117847.

[17] Liu, X., Kong, X., Fang, Q., Meng, Y., Peng, Y. Peridynamics modelling of projectile penetration into concrete targets. International Journal of Impact Engineering, vol 195 (2025) pp.105110.

[18] Li, H., Zhang, Z., Wang, L., Gu, X., Zhang, Y., Shao, X. Integration of peridynamics and deep learning for efficient and accurate thermomechanical modeling. Applied Sciences, vol 15, issue 18 (2025) pp.10032.

[19] Kim, W., Youn, B. D. Physics-based digital twin updating and twin-based explainable crack identification of mechanical lap joint. Reliability Engineering & System Safety, vol 253 (2025) pp.110515.

[20] Cheok, E. W. W., Qian, X., Kaps, A., Quek, S. T., Si, M. B. I. A strain-interfaced digital twin solution for corner fatigue crack growth using Bayesian inference. International Journal of Fatigue, vol 191 (2025) pp.108705.

[21] Iskander, M., Shrive, N. Fracture of brittle and quasi-brittle materials in compression: A review of the current state of knowledge and a different approach. Theoretical and Applied Fracture Mechanics, vol 97 (2018) pp.250-257.