Boundary stress distribution and elastic viscous of emerging pavement predicted using an innovative hybrid machine learning technique

Intekab Alam; Sanjay Kumar Sinha; Karishma Desai; Honganur Raju Manjunath

doi:10.31893/multiscience.2024ss0317

Keywords:

Machine learning

elastic viscous

asphalt binder

Stress distribution errors

Prediction

Abstract

Concrete's pumpability is significantly affected by the plastic viscosity of the mix and its surface yield stress. The long-term performance and durability of road infrastructure depend heavily on the capacity to predict the boundary stress distribution and elastic-viscous behavior of developing pavements. This study is concerned with predicting the elastic and viscous behavior of changing pavements using sophisticated predictive modeling approaches. Several techniques frequently need to capture the intricate interdependencies that are a feature of pavement behavior. To overcome this issue, we proposed the hybridization method of dynamic random forest combined with bilateral long short-term memory (DRF-BiLSTM). The purpose of DRF-BiLSTM is to predict the boundary stress distribution and elastic viscous of emerging pavement. Initially, asphalt binder (AB) datasets were collected. The collected dataset is preprocessed using the z-score normalization technique to reduce the effects of size discrepancies by standardizing the data. After preprocessing the data, the short-time fourier transform (STFT) method is used for feature extraction. Predictive results that are superior to those of benchmark models should obtained using experimental data supporting a hybridization of DRF-BLSTM in terms of.
References
1. Dao, D. V., Nguyen, N. L., Ly, H. B., Pham, B. T., & Le, T. T. (2020). Cost-effective approaches based on machine learning to predict dynamic modulus of warm mix asphalt with high reclaimed asphalt pavement. Materials, 13(15), 3272. https://doi.org/10.3390/ma13153272
2. Faroughi, S. A., Roriz, A. I., & Fernandes, C. (2022). A meta-model to predict the drag coefficient of a particle translating in viscoelastic fluids: A machine learning approach. Polymers, 14(3), 430. https://doi.org/10.3390/polym14030430
3. Hosseini, A. S., Hajikarimi, P., Gandomi, M., Nejad, F. M., & Gandomi, A. H. (2021). Optimized machine learning approaches for the prediction of viscoelastic behavior of modified asphalt binders. Construction and Building Materials, 299, 124264. https://doi.org/10.1016/j.conbuildmat.2021.124264
4. Hussain, F., Ali, Y., Irfan, M., Ashraf, M., & Ahmed, S. (2021). A data-driven model for phase angle behaviour of asphalt concrete mixtures based on convolutional neural network. Construction and Building Materials, 269, 121235. https://doi.org/10.1016/j.conbuildmat.2020.121235
5. Ji, B., Bhattarai, S. S., Na, I. H., & Kim, H. (2023). A Bayesian deep learning approach for rheological properties prediction of asphalt binders considering uncertainty of output. Construction and Building Materials, 408, 133671. https://doi.org/10.1016/j.conbuildmat.2023.133671
6. Kadupitiya, J. C. S., & Jadhao, V. (2021). Probing the rheological properties of liquids under conditions of elastohydrodynamic lubrication using simulations and machine learning. Tribology Letters, 69(3), 82. https://doi.org/10.1007/s11249-021-01457-3
7. Lennon, K. R., McKinley, G. H., & Swan, J. W. (2023). Scientific machine learning for modeling and simulating complex fluids. Proceedings of the National Academy of Sciences, 120(27), e2304669120. https://doi.org/10.1073/pnas.2304669120
8. Li, Z., & Scandolo, S. (2022). Elasticity and viscosity of hcp iron at Earth's inner core conditions from machine learning-based large-scale atomistic simulations. Geophysical Research Letters, 49(24), e2022GL101161. https://doi.org/10.1029/2022GL101161
9. Mahmoudabadbozchelou, M., Karniadakis, G. E., & Jamali, S. (2022). NN-PINNs: Non-Newtonian physics-informed neural networks for complex fluid modeling. Soft Matter, 18(1), 172-185. https://doi.org/10.1039/d1sm01298c
10. Nguyen, T. D., Tran, T. H., & Hoang, N. D. (2020). Prediction of interface yield stress and plastic viscosity of fresh concrete using a hybrid machine learning approach. Advanced Engineering Informatics, 44, 101057. https://doi.org/10.1016/j.aei.2020.101057
11. Saleh, P. Y., Jaf, D. K. I., Abdalla, A. A., Ahmed, H. U., Faraj, R. H., Mahmood, W., & Mohammed, A. S. (2023). Prediction of the compressive strength of strain-hardening cement-based composites using soft computing models. Structural Concrete, 24(5), 6761-6777. https://doi.org/10.1002/suco.202200769
12. Sun, Y., He, D., & Li, J. (2021). Research on the fatigue life prediction for a new modified asphalt mixture of a support vector machine based on particle swarm optimization. Applied Sciences, 11(24), 11867. https://doi.org/10.3390/app112411867
13. Xu, K., Tartakovsky, A. M., Burghardt, J., & Darve, E. (2021). Learning viscoelasticity models from indirect data using deep neural networks. Computer Methods in Applied Mechanics and Engineering, 387, 114124. https://doi.org/10.1016/j.cma.2021.114124
14. Yang, Z., Yu, C. H., & Buehler, M. J. (2021). Deep learning model to predict complex stress and strain fields in hierarchical composites. Science Advances, 7(15), eabd7416. https://doi.org/10.1126/sciadv.abd7416
15. Zhang, W., Khan, A., Huyan, J., Zhong, J., Peng, T., & Cheng, H. (2021). Predicting Marshall parameters of flexible pavement using support vector machine and genetic programming. Construction and Building Materials, 306, 124924. https://doi.org/10.1016/j.conbuildmat.2021.124924

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

How to cite

Alam, I., Sinha, S. K., Desai, K., & Manjunath, H. R. (2024). Boundary stress distribution and elastic viscous of emerging pavement predicted using an innovative hybrid machine learning technique. Multidisciplinary Science Journal, 6, 2024ss0317. https://doi.org/10.31893/multiscience.2024ss0317

[1] Dao, D. V., Nguyen, N. L., Ly, H. B., Pham, B. T., & Le, T. T. (2020). Cost-effective approaches based on machine learning to predict dynamic modulus of warm mix asphalt with high reclaimed asphalt pavement. Materials, 13(15), 3272. https://doi.org/10.3390/ma13153272

[2] Faroughi, S. A., Roriz, A. I., & Fernandes, C. (2022). A meta-model to predict the drag coefficient of a particle translating in viscoelastic fluids: A machine learning approach. Polymers, 14(3), 430. https://doi.org/10.3390/polym14030430

[3] Hosseini, A. S., Hajikarimi, P., Gandomi, M., Nejad, F. M., & Gandomi, A. H. (2021). Optimized machine learning approaches for the prediction of viscoelastic behavior of modified asphalt binders. Construction and Building Materials, 299, 124264. https://doi.org/10.1016/j.conbuildmat.2021.124264

[4] Hussain, F., Ali, Y., Irfan, M., Ashraf, M., & Ahmed, S. (2021). A data-driven model for phase angle behaviour of asphalt concrete mixtures based on convolutional neural network. Construction and Building Materials, 269, 121235. https://doi.org/10.1016/j.conbuildmat.2020.121235

[5] Ji, B., Bhattarai, S. S., Na, I. H., & Kim, H. (2023). A Bayesian deep learning approach for rheological properties prediction of asphalt binders considering uncertainty of output. Construction and Building Materials, 408, 133671. https://doi.org/10.1016/j.conbuildmat.2023.133671

[6] Kadupitiya, J. C. S., & Jadhao, V. (2021). Probing the rheological properties of liquids under conditions of elastohydrodynamic lubrication using simulations and machine learning. Tribology Letters, 69(3), 82. https://doi.org/10.1007/s11249-021-01457-3

[7] Lennon, K. R., McKinley, G. H., & Swan, J. W. (2023). Scientific machine learning for modeling and simulating complex fluids. Proceedings of the National Academy of Sciences, 120(27), e2304669120. https://doi.org/10.1073/pnas.2304669120

[8] Li, Z., & Scandolo, S. (2022). Elasticity and viscosity of hcp iron at Earth's inner core conditions from machine learning-based large-scale atomistic simulations. Geophysical Research Letters, 49(24), e2022GL101161. https://doi.org/10.1029/2022GL101161

[9] Mahmoudabadbozchelou, M., Karniadakis, G. E., & Jamali, S. (2022). NN-PINNs: Non-Newtonian physics-informed neural networks for complex fluid modeling. Soft Matter, 18(1), 172-185. https://doi.org/10.1039/d1sm01298c

[10] Nguyen, T. D., Tran, T. H., & Hoang, N. D. (2020). Prediction of interface yield stress and plastic viscosity of fresh concrete using a hybrid machine learning approach. Advanced Engineering Informatics, 44, 101057. https://doi.org/10.1016/j.aei.2020.101057

[11] Saleh, P. Y., Jaf, D. K. I., Abdalla, A. A., Ahmed, H. U., Faraj, R. H., Mahmood, W., & Mohammed, A. S. (2023). Prediction of the compressive strength of strain-hardening cement-based composites using soft computing models. Structural Concrete, 24(5), 6761-6777. https://doi.org/10.1002/suco.202200769

[12] Sun, Y., He, D., & Li, J. (2021). Research on the fatigue life prediction for a new modified asphalt mixture of a support vector machine based on particle swarm optimization. Applied Sciences, 11(24), 11867. https://doi.org/10.3390/app112411867

[13] Xu, K., Tartakovsky, A. M., Burghardt, J., & Darve, E. (2021). Learning viscoelasticity models from indirect data using deep neural networks. Computer Methods in Applied Mechanics and Engineering, 387, 114124. https://doi.org/10.1016/j.cma.2021.114124

[14] Yang, Z., Yu, C. H., & Buehler, M. J. (2021). Deep learning model to predict complex stress and strain fields in hierarchical composites. Science Advances, 7(15), eabd7416. https://doi.org/10.1126/sciadv.abd7416

[15] Zhang, W., Khan, A., Huyan, J., Zhong, J., Peng, T., & Cheng, H. (2021). Predicting Marshall parameters of flexible pavement using support vector machine and genetic programming. Construction and Building Materials, 306, 124924. https://doi.org/10.1016/j.conbuildmat.2021.124924

Abstract

References

How to cite