Delamination analysis in high speed drilling of carbon fiber reinforced plastics (CFRP) using artificial neural network model S.R. Karnik a , V.N. Gaitonde b, * , J. Campos Rubio c , A. Esteves Correia d , A.M. Abrão c , J. Paulo Davim e a Department of Electrical and Electronics Engineering, B.V.B. College of Engineering and Technology, Hubli 580 031, Karnataka, India b Department of Industrial and Production Engineering, B.V.B. College of Engineering and Technology, Hubli 580 031, Karnataka, India c Department of Mechanical Engineering, Federal University of Minas Gerais, Av. Antônio Carlos, 6627 – Pampulha, Belo Horizonte MG, CEP: 31.270-901, Brazil d Department of Mechanical Engineering and Industrial Management, School of Technology, Polytechnic Institute of Viseu, Campus de Repeses, 3504-510 Viseu, Portugal e Department of Mechanical Engineering, University of Aveiro, Campus Santiago, 3810-193 Aveiro, Portugal article info Article history: Received 1 February 2007 Accepted 27 March 2008 Available online 7 April 2008 Keywords: High speed drilling Carbon fiber reinforced plastics (CFRP) Delamination Artificial neural network (ANN) abstract The carbon fiber reinforced plastics (CFRP) are highly promising materials for the applications in aeronau- tical and aerospace industries. The delamination is a major problem associated with the drilling fiber reinforced composite materials, which reduce the structural integrity of the material. The present work focuses on the analysis of delamination behavior as a function of drilling process parameters at the entrance of the CFRP plates. The delamination analysis in high speed drilling is performed by developing an artificial neural network (ANN) model with spindle speed, feed rate and point angle as the affecting parameters. A multilayer feed forward ANN architecture, trained using error-back propagation training algorithm (EBPTA) is employed for this purpose. Drilling experiments are conducted as per full factorial design using cemented carbide (grade K20) twist drills that serve as input–output patterns for ANN train- ing. The ANN model so developed is validated by presenting training and new testing input patterns. The validated ANN model is then used to generate the direct and interaction effect plots to analyze the delam- ination behavior. The simulation results illustrate the effectiveness of the ANN models to analyze the effects of drilling process parameters on delamination factor. The analysis also demonstrates the advan- tage of employing higher speed in controlling the delamination during drilling. Ó 2008 Elsevier Ltd. All rights reserved. 1. Introduction The carbon fiber reinforced plastic (CFRP) materials are alterna- tive to stainless steel and other materials especially in corrosive industrial applications such as oil, gas and process industries. These composites are highly promising materials for the applica- tions in aeronautical and aerospace industries including rocket exit nozzles, nose caps, pistons for internal combustion engines and fu- sion devices. The CFRP components are superior to other materials mainly due to high strength-to-weight and stiffness-to-weight ra- tios, high damping and good corrosive resistance properties [1]. The CFRP composites are generally fabricated by various pro- cesses such as hand lay-up, filament winding etc., and then sub- jected to machining to facilitate the dimensional control for easy assembly and functional aspects. Nevertheless, the composite materials have particular characteristics, which drive their machining behavior, the mechanisms involved while cutting com- posite materials have been regarded as considerably distinct from those observed when cutting homogeneous materials [2]. The cut- ting tool action during machining damages the workpiece surface. In addition to that the aesthetic issues and the risk of mechanical failures also increase substantially [3]. Drilling is one of the most common machining processes used to install fasteners for assembly of laminates. The delamination is a major problem associated with the drilling of fiber reinforced composite materials apart from reducing the structural integrity of the materials. The delamination also results in poor assembly tolerance and has the potential for long-term performance deteri- oration. The key for solving this problem lies in reducing the thrust force when drilling. Two mechanisms of delamination associated with drilling FRP composites are known as peel-up at the drill en- trance and push-out at the drill exit [4]. It is estimated that the drilling-associated the delamination accounts for 60% of all part rejections during final assembly of an aircraft in an aircraft indus- tries [5]. Thus, it is necessary to develop an accurate model to ana- lyze the effects of various drilling process parameters on delamination. Further, the model so developed can be utilized to predict the delamination for the selected process parameters dur- ing drilling. Several techniques have been employed to measure the delam- ination after drilling composites, such as optical microscopy, 0261-3069/$ - see front matter Ó 2008 Elsevier Ltd. All rights reserved. doi:10.1016/j.matdes.2008.03.014 * Corresponding author. Tel.: +91 836 2378272; fax: +91 836 2374985. E-mail address: gaitondevn@yahoo.co.in (V.N. Gaitonde). Materials and Design 29 (2008) 1768–1776 Contents lists available at ScienceDirect Materials and Design journal homepage: www.elsevier.com/locate/matdes