Analysis of surface finish in drilling of composites using neural networks

Loading...
Thumbnail Image
Authors
Madiwal, Shashidhar
Advisors
Bahr, Behnam
Issue Date
2006-07
Type
Thesis
Keywords
Composite materials , Drilling , Artificial Neural Network
Research Projects
Organizational Units
Journal Issue
Citation
Abstract

Composite materials are widely used in the aerospace industry because of their high strength-to-weight ratio. Although they have many advantages, their inhomogeneity and anisotropy pose problems. Because of these properties, machining of composites, unlike conventional metal working, needs more investigation. Conventional drilling of composites is one such field that requires extensive study and research. Among various parameters that determine the quality of a drilled hole, surface finish is of vital importance. The surface finish of a drilled hole depends on speed, feed-rate, material of the work piece, and geometry of the drill bit. This project studied the effect of speed and feed on surface finish and also the optimization of these parameters. Experiments were conducted based on Design of Experiment (DOE) and qualitative verification using Artificial Neural Network (ANN). Relevant behavior of surface finish was also studied. In this project, holes were drilled using a conventional twist drill at different cutting speeds (2,000 to 5,000 rpm) and feed rate was varied from 0.001 to 0.01 ipr for solid carbon fiber laminate (composite material). The other material drilled is BMS 8-276 form 3 (toughened resin system). Also five different drill bits were used to conduct experiments on BMS 8-276 form 3. Speed values were 5,000, 3,000, and 2,000 rpm and feed rates were 0.004, 0.006, and 0.01 ipr. The effect of speed, feed rate, and different drill geometries was analyzed with respect to surface finish in the drilled composites.

Table of Contents
Description
Thesis (M.S.)--Wichita State University, College of Engineering, Dept. of Mechanical Engineering.
"July 2006."
Includes bibliographic references (leaves 79-81).
Publisher
Journal
Book Title
Series
PubMed ID
DOI
ISSN
EISSN