On application of machine learning techniques for predicting the bending and buckling behavior of FGM nanobeams

Aman Garg , Mohamed-Ouejdi Belarbi , Li Li , Abdelouahed Tounsi

Abstract

The present article aims to carry out a comparative study between various machine learning based algorithms, which can predict the bending and buckling behavior of functionally graded (FG) nanobeams accurately. The algorithm has been developed in the framework of two regression machine learning models namely, Gaussian Process Regression (GPR), and Random Forest (RF). Geometric and material properties are taken as the variables including length-to-thickness ratio, power-law index, and nonlocal parameter. For having random non-biased input dataset, the Sobol sequence has been used. Using these values, maximum deflections and critical buckling loads are obtained. These values along with the corresponding input variables, surrogate models were formulated. It has been observed that the GPR model is able to predict the behavior of FG nanobeams more accurately as compared to the behavior predicted by RF surrogate model even for an unseen dataset.

Key Words

concrete disk; instability; nanocomposite reinforcement; non-classical boundary conditions; stability

Address

Aman Garg — State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China/ Department of Multidisciplinary Engineering, The NorthCap University, Gurugram, Haryana, India – 122017
Mohamed-Ouejdi Belarbi — Laboratoire de Recherche en Génie Civil, LRGC, Université de Biskra, B.P. 145, R.P. 07000, Biskra, Algeria/ Department of Civil Engineering, Lebanese American University, Byblos, Lebanon
Li Li — State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
Abdelouahed Tounsi — Department of Civil and Environmental Engineering, King Fahd University of Petroleum &Minerals, 31261 Dhahran, Eastern Province, Saudi Arabia/ Material and Hydrology Laboratory, University of Sidi Bel Abbes, Faculty of Technology, Civil Engineering Department, 22000 Sidi Bel Abbes, Algeria/ YFL (Yonsei Frontier Lab), Yonsei University, Seoul, Korea

PDF Viewer

Preview is limited to the first 3 pages. Sign in to access the full PDF.

← Back to Volume 17, No. 5