9Implementation of FEM and Machine Learning Algorithms in the Design and Manufacturing of Laminated Composite Plate
Sidharth Patro1, Trupti Ranjan Mahapatra1*, Romeo S. Fono Tamo2, Allu Vikram Kishore Murty3, Soumya Ranjan Parimanik1 and Debadutta Mishra1
1Department of Production Engineering, Veer Surendra University of Technology, Odisha, India
2Department of Mechanical, Aerospace and Biomedical Engineering, University of Tennessee, TN, USA
3AIML Architect, Bengaluru, Karnataka, India
Abstract
In this paper, a coupled finite element method (FEM) and supervised machine learning (SML) scheme has been proposed and implemented for predicting the static deflection in laminated composite plate for subsequent design and synthesis. To do away with the time, cost and need of repeatability associated with experimental data, a well-established nonlinear higher-order FE model using full geometrical nonlinearity in Green-Lagrange sense has been used to compute the central deflection values of laminated composite plates. Desired responses are acquired via a self-developed MATLAB computer code as per Taguchi’s experimental design considering the lay-up scheme, aspect ratio, thickness ratio and the support conditions of the laminated composite plate structure as the controllable factors under five different uniformly distributed load parameters. This numerically prepared dataset has been utilized to find the best performing regression model using ANN and Supervised Regression Methodologies ...
Get Intelligent Manufacturing Management Systems now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.