Physics-Informed Neural Network for Bending Analysis of Twodimensional Functionally Graded Nano-Beams Based on Nonlocal Strain Gradient Theory

Loading...
Thumbnail Image

Date

2025

Journal Title

Journal ISSN

Volume Title

Publisher

Univ Tehran, Danishgah-i Tihran

Open Access Color

OpenAIRE Downloads

OpenAIRE Views

Research Projects

Organizational Units

Organizational Unit
Automotive Engineering
(2009)
Having started education in 2009, the Atılım university Department of Automotive Engineering offers an academic environment at international standards, with its education in English, a contemporary curriculum and ever-better and ever-developing laboratory opportunities. In addition to undergraduate degree education, the graduate program of multi-disciplinary mechanical engineering offers the opportunity for graduate and doctorate degree education automotive engineering. The Atılım University Automotive Engineering has been selected to be the best in Turkey in 2020 in the field of automotive engineering with studies in energy efficiency, motor performance, active/ passive automotive security and vehicle dynamics conducted in the already-existing laboratories of its own. Our graduates are employed at large-scale companies that operate in Turkey, such as Isuzu, Ford Otosan, Hattat, Honda, Hyundai, Karsan, Man, Mercedes-Benz, Otokar, Renault, Temsa, Tofaş, Toyota, Türk Traktör, Volkswagen (to start operation in 2020). In addition, our graduates have been hired at institutions such as Tübitak, Tai, Aselsan, FNSS, Ministry of National Defence, Tcdd etc. or at supplier industries in Turkey. Due to the recent evolution undergone by the automotive industry with the development of electric, hybrid and autonomous vehicle technologies, automotive engineering has gained popularity, and is becoming ever more exhilarating. In addition to combustion engine technologies, our students also gain expertise in these fields. The “Formula Student Car” contest organized since 2011 by the Society of Automotive Engineers (SAE) where our Department ranked third globally in 2016 is one of the top projects conducted by our department where we value hands-on training. Our curriculum, updated in 2020, focuses on computer calculation and simulation courses, as well as laboratory practice, catered to modern automotive technologies.

Journal Issue

Events

Abstract

This paper presents the bending analysis of two-dimensionally functionally graded (2D FG) nano-beams using a physics-informed neural network (PINN) approach. The material properties of the nanobeams vary along their length and thickness directions, governed by a power-law function. Hamilton's principle, combined with the nonlocal strain gradient theory (NSGT) and Euler-Bernoulli beam theory, is employed to derive the governing equation for the bending analysis of 2D FG nanobeams. Due to the incorporation of size dependency and the variation of material properties in two dimensions, the governing equation becomes a high-order variable- coefficient differential equation, which is challenging, if not impossible, to solve analytically. In this study, the applicability of PINN for solving such high-order complex differential equations is investigated, with potential applications in nanomechanical engineering. In the PINN approach, a deep feedforward neural network is utilized to predict the mechanical response of the beam. Spatial coordinates serve as inputs, and a loss function is formulated based on the governing equation and boundary conditions of the problem. This loss function is minimized through the training process of the neural network. The accuracy of the PINN results is validated by comparing them with available reference solutions. Additionally, the effects of material distribution, power-law index (in both length and thickness directions), nonlocal strain gradient parameters, and material length scale parameters are investigated. This study demonstrates the versatility of the PINN approach as a robust tool for solving high-order differential equations in structural mechanics.

Description

Keywords

Physics Informed Neural Networks, Two-Dimensional Fg Nano-Beams, Bending Analysis, Nonlocal Strain Gradient Theory

Turkish CoHE Thesis Center URL

Fields of Science

Citation

WoS Q

N/A

Scopus Q

Q3

Source

Volume

56

Issue

1

Start Page

222

End Page

248

Collections