A novel intelligent software-based approach to predict forces and delamination during drilling of fiber-reinforced plastics. (April 2016)

• Record Type: Journal Article
• Authors: Dhawan, Vikas; Debnath, Kishore; Singh, Inderdeep; Singh, Sehijpal
• Is Part Of: Proceedings of the Institution of Mechanical Engineers. Volume 230:Number 2(2016:Apr.)
• Page Start: 603
• Page End: 614
• Publication Date: 2016-04
• Subjects: Composites -- laminates -- drilling -- ANN -- FL and ANFIS; Materials -- Periodicals; Engineering design -- Periodicals; 620.11
• DOI: 10.1177/1464420715583164
• Languages: English
• ISSNs: 1464-4207

Abstract

Drilling of fiber-reinforced plastics (FRPs) results in drilling-induced damage which leads to reduced part life and extensive part rejection. Thus far, there exists no standard handbook or knowledge-based tool that can predict drilling-induced forces and damage. Therefore, the present research initiative is an attempt to develop a software tool based on artificial intelligence which can predict drilling-induced thrust force, torque and delamination factor during drilling of FRPs. The developed intelligent software has a friendly graphic user interface (GUI). The user just interacts through the GUI and fills the input choices, and upon execution, the software predicts the drilling forces and delamination factor. In order to generate the database for the software, drilling experiments have been performed in two different types of composite materials with four different types of drill point geometries of two distinct diameters. The drilling of composite laminate has been conducted at three different levels of spindle speed and feed rate. The software results are based on three different artificial intelligence techniques namely artificial neural network (ANN), fuzzy logic (FL) and adaptive neuro-fuzzy inference system (ANFIS). The values of thrust force, torque and delamination factor for given inputs predicted by the developed tool are in close agreement with the experimental values.