Scholarlink

<p>This study presents a thorough investigation of the mechanical bending characteristics of functionally graded tapered porous rectangular plates (FGTPRP) subjected to bi-sinusoidal loading and an artificial-neural-network (ANN) model to predict the deformation behavior of the plate. This study fills a gap in the existing literature by examining the maximum deformation and mechanical bending factors of the FGTPRP under various considerations. These considerations include different linear and parabolic thickness variations, full or partial elastic foundations, material uncertainty through various porosity distributions, and different combinations of edge restrictions. The mathematical model adopts Rayleigh–Ritz approach along with suitable polynomials, ensuring nearly accurate solutions for static analysis of FGTPRP. These polynomials are capable to handle any combination of mixed edge constraints. Validation against published results and data obtained using the finite element method (ANSYS) ensures the precision and reliability of numerical results and the convergence test highlights the efficiency of the present solution method. The study delves into the influence of parameters such as material property coefficient, porous fraction coefficient, taper fraction, length-to-width ratio, and foundation coefficients on the bending behavior of FGTPRP. Results indicate a significant impact of these parameters on non-dimensional centre deformation and MBFs. Notably, the paper introduces an innovative component of the ANN model to augment the depth of analysis. This ANN model enable predictive capabilities for non-dimensional centre deformation with less than 1% error. The proposed numerical model and ANN predictions offer an efficient means to analyze the mechanical bending behavior of FGTPRP and hold applicability to other functionally graded material structures.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Effect of partial elastic foundation on the bending behavior of functionally graded tapered porous plates utilizing Rayleigh–Ritz approach and deformation prediction with artificial neural network

  • 期刊论文

  • 发表日期：

    2025年1月19日

查看全文
  • Rajat Jain,
  • Mohammad Sikandar Azam

摘要

This study presents a thorough investigation of the mechanical bending characteristics of functionally graded tapered porous rectangular plates (FGTPRP) subjected to bi-sinusoidal loading and an artificial-neural-network (ANN) model to predict the deformation behavior of the plate. This study fills a gap in the existing literature by examining the maximum deformation and mechanical bending factors of the FGTPRP under various considerations. These considerations include different linear and parabolic thickness variations, full or partial elastic foundations, material uncertainty through various porosity distributions, and different combinations of edge restrictions. The mathematical model adopts Rayleigh–Ritz approach along with suitable polynomials, ensuring nearly accurate solutions for static analysis of FGTPRP. These polynomials are capable to handle any combination of mixed edge constraints. Validation against published results and data obtained using the finite element method (ANSYS) ensures the precision and reliability of numerical results and the convergence test highlights the efficiency of the present solution method. The study delves into the influence of parameters such as material property coefficient, porous fraction coefficient, taper fraction, length-to-width ratio, and foundation coefficients on the bending behavior of FGTPRP. Results indicate a significant impact of these parameters on non-dimensional centre deformation and MBFs. Notably, the paper introduces an innovative component of the ANN model to augment the depth of analysis. This ANN model enable predictive capabilities for non-dimensional centre deformation with less than 1% error. The proposed numerical model and ANN predictions offer an efficient means to analyze the mechanical bending behavior of FGTPRP and hold applicability to other functionally graded material structures.