Dalal, Deepak (2016) Using Neural Network to solve mechanics problems. Coursework Masters thesis, University of Southern Queensland. (Unpublished)
Abstract
This project is concerned with the development of symmetric versions of integrated radial basis function networks (SIRBFNs) for numerical solution of ordinary differential equations (ODEs) and partial differential equations (PDEs) governing the behaviour of mechanics problems. The proposed method yields the system matrix that is sysmmetric, which significantly reduces the computer memory storage requirement over the usual RBF methods, and allows one to use effective solvers for linear algebraic equations for an efficient solutiuon. Numerical verification is condutced in elliptic differential problems. Accurate results and high rates of convergence with respect to grid refinement are obtained with the proposed method.
|
Statistics for this ePrint Item |
| Item Type: | Thesis (Non-Research) (Coursework Masters) |
|---|---|
| Item Status: | Live Archive |
| Faculty/School / Institute/Centre: | Historic - Faculty of Health, Engineering and Sciences - School of Mechanical and Electrical Engineering (1 Jul 2013 - 31 Dec 2021) |
| Supervisors: | Mai-Duy, Nam |
| Qualification: | Master of Engineering Sciences (Mechanical) |
| Date Deposited: | 23 Mar 2026 05:12 |
| Last Modified: | 23 Mar 2026 05:12 |
| Uncontrolled Keywords: | Mechanics problems; Differentional equations; Integrated radial basis function network; symmetric system matrices |
| URI: | https://sear.unisq.edu.au/id/eprint/53193 |
Actions (login required)
 |
Archive Repository Staff Only |
