Kancharakuntla, Sri Bindhu (2016) A new approach in modelling machinability of fibre polymer composites using artificial neuron networks. Coursework Masters thesis, University of Southern Queensland. (Unpublished)
Abstract
Artificial Neural Networks (ANN) is an advanced application for predicting the machinability parameters. ANN technology is utilised for solving various complex non-linear and mathematical engineering problems. During the training of the model, ANN modifies itself to set up a pattern between inputs and outputs through the hidden layers. In the present work, artificial neural networks (ANN) model will be developed using MATLAB to predict machinability of Fibre Polymer Composites (neat epoxy, date/epoxy and glass/epoxy). The experimental database is collected from previous e experimental works will be used to train the models. Some of the data is used to evaluate the prediction performance of the developed models. The Input parameters considered are Drill diameter (mm), Drilling speed (rpm), time (sec) and Feed rate (mm/rev) and the output parameters are Hole Accuracy, Delamination, Torque, Trust Force, Machining Power and Specific Cutting Pressure. Several models were developed for two hidden layers using different combinations of transfer functions of purelin-tansig and varying number of neurons until 40. Several models were developed by considering different number of input parameters to reduce the error percentage. The prediction of the results is also performed on different parameters other than experimental data.
|
Statistics for this ePrint Item |
| Item Type: | Thesis (Non-Research) (Coursework Masters) |
|---|---|
| Item Status: | Live Archive |
| Additional Information: | Current UniSQ staff and students can request access to this thesis. Please email research.repository@unisq.edu.au with a subject line of SEAR thesis request and provide: Name of the thesis requested and Your name and UniSQ email address. |
| Faculty/School / Institute/Centre: | Current - Faculty of Health, Engineering and Sciences - No Department (1 Jul 2013 -) |
| Supervisors: | Yousif, Belal |
| Qualification: | Master of Engineering Sciences (Mechanical Engineering) |
| Date Deposited: | 16 Jul 2026 22:44 |
| Last Modified: | 16 Jul 2026 22:44 |
| Uncontrolled Keywords: | Artificial Neural Networks, ANN, machinability parameters, MATLAB, Fibre Polymer Composites, |
| URI: | https://sear.unisq.edu.au/id/eprint/53264 |
Actions (login required)
 |
Archive Repository Staff Only |
