Abstract
For structural integrity assessment, when dealing with problems such as uncertainty quantification, real-time structural health monitoring, and reliability analysis, fracture mechanics parameters, e.g. the energy release rate, are required to be evaluated for a large amount of crack configurations. Using finite element (FE) models directly for this task is generally time consuming. This work follows a machine learning-based method aiming at a fast estimation of the fracture mechanics parameters. Towards this end, the offline data are first created by performing the FE simulations for a set of crack configurations from which these parameters can be extracted and then a machine learning algorithm (e.g. artificial neural network (ANN)) is used to build a surrogate model with the obtained data. Using this surrogate model, the above mentioned tasks can be performed with a significantly reduced computational cost while assuring accurate results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Anderson TL (2017) Fracture mechanics: fundamentals and applications. CRC Press, Boca Raton
Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT’2010. Springer, Berlin, pp 177–186
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge
Hegde J, Rokseth B (2020) Applications of machine learning methods for engineering risk assessment-a review. Safe Sci 122:104, 492
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
Lawrence S, Giles CL, Tsoi AC (1997) Lessons in neural network training: overfitting may be harder than expected. In: AAAI/IAAI. Citeseer, pp 540–545
Leser PE, Hochhalter JD, Warner JE, Newman JA, Leser WP, Wawrzynek PA, Yuan FG (2017) Probabilistic fatigue damage prognosis using surrogate models trained via three-dimensional finite element analysis. Struct Health Monitor 16(3):291–308
Moës N, Dolbow J, Belytschko T (1999) A finite element method for crack growth without remeshing. Int J Numer Meth Eng 46(1):131–150
Quiza R, Davim J (2011) Combining the finite element method and artificial intelligence in manufacturing modeling and optimization, pp 201–239
Shanmuganathan S (2016) Artificial neural network modelling: An introduction. In: Studies in computational intelligence, vol 628. Springer, Berlin, pp 1–14. https://doi.org/10.1007/978-3-319-28495-8_1
Acknowledgements
The support of Thu Dau Mot University for this work within the “Modelling and Simulation in the Digital Age – MaSDA” research program is greatly appreciated.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hoang, TV., Tran, VX., Nguyen, V.D., Nguyen, Q.H., Bui, V.S. (2021). Assessment of Structural Integrity Using Machine Learning. In: Kumar, R., Quang, N.H., Kumar Solanki, V., Cardona, M., Pattnaik, P.K. (eds) Research in Intelligent and Computing in Engineering. Advances in Intelligent Systems and Computing, vol 1254. Springer, Singapore. https://doi.org/10.1007/978-981-15-7527-3_57
Download citation
DOI: https://doi.org/10.1007/978-981-15-7527-3_57
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-7526-6
Online ISBN: 978-981-15-7527-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)