Prediction of thrust force of step drill in drilling composite material by Taguchi method and radial basis function network

Among material secondary machining, drilling is the most frequently applied factor to composites needing structure joining. Drill geometry is considered the most important factor that affects drill performance. A major concern in drilling of composite materials is the delamination that occurs in the exit as well as in the entrance planes. The delamination damage caused by the tool thrust is known as one of the major concerns during the drilling process. The thrust force of step drill with drilling parameters (step angle, stage ratio, feedrate and spindle speed) in drilling carbon fiber reinforced plastics (CFRP) laminates were experimentally investigated in this study. The experimental results indicate that the step angle, stage ratio, and feedrate are the most significant factors affecting the overall performance. The optimal combinations, such as A2B2C1D3 (i.e., step angle = 100 ° stage ratio = 0.4 mm/mm, feedrate = 0.01 mm/rev and spindle speed = 1,200 rpm), were used under the adopted drilling condition. An experimental approach to the prediction of thrust force produced by step drill using linear regression analysis of experiments and radial basis function network (RBFN) were proposed in this study. In the confirmation tests, RBFN (errors within 0.3%) has been shown to be a better predictive model than multi-variable linear regression analysis (errors within 28%) for quantitative prediction of drilling-induced thrust force in drilling of composite material.

[1]  C. K. H. Dharan,et al.  Chisel Edge and Pilot Hole Effects in Drilling Composite Laminates , 2002 .

[2]  Frédéric Lachaud,et al.  Experimental analysis of drilling damage in thin carbon/epoxy plate using special drills , 2000 .

[3]  Hong Hocheng,et al.  Taguchi analysis of delamination associated with various drill bits in drilling of composite material , 2004 .

[4]  C. Tsao.  Prediction of flank wear of different coated drills for JIS SUS 304 stainless steel using neural network , 2002 .

[5]  D. C. H. Yang,et al.  Effects of Feedrate and Chisel Edge on Delamination in Composites Drilling , 1993 .

[6]  K. Lee,et al.  Critical thrust force at propagation of delamination zone due to drilling of FRP/metallic strips , 2005 .

[7]  V Karri.  RBF neural network for thrust and torque predictions in drilling operations , 1999, Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300).

[8]  Yuehui Chen,et al.  Thrust force control of drilling system using neural network , 2001, 2001 IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Proceedings (Cat. No.01TH8556).

[9]  K. Krishnamurthy,et al.  A neural network thrust force controller to minimize delamination during drilling of graphite-epoxy laminates , 1996 .

[10]  Surjya K. Pal,et al.  Drill wear monitoring using back propagation neural network , 2006 .

[11]  J. Paulo Davim,et al.  Drilling carbon fiber reinforced plastics manufactured by autoclave: experimental and statistical study , 2003 .

[12]  S. M. Mahdavian,et al.  Experimental studies of step drills and establishment of empirical equations for the drilling process , 2005 .

[13]  C. Sanjay,et al.  Modeling of tool wear in drilling by statistical analysis and artificial neural network , 2005 .

[14]  Pedro Reis,et al.  Study of delamination in drilling carbon fiber reinforced plastics (CFRP) using design experiments , 2003 .

[15]  Suat Tanaydin.  Robust Design and Analysis for Quality Engineering , 1996 .

[16]  C. C. Tsao,et al.  The effect of pilot hole on delamination when core drill drilling composite materials , 2006 .

[17]  Hong Hocheng,et al.  Comprehensive analysis of delamination in drilling of composite materials with various drill bits , 2003 .

[18]  V. Tagliaferri,et al.  Effect of drilling parameters on the finish and mechanical properties of GFRP composites , 1990 .

[19]  W. König,et al.  Machining of Fibre Reinforced Plastics , 1985 .

[20]  David Dornfeld,et al.  Sensor Integration Using Neural Networks for Intelligent Tool Condition Monitoring , 1990 .

[21]  R. Komanduri,et al.  Machining fiber-reinforced composites , 1997 .

[22]  Geok Soon Hong,et al.  On-line cutting state recognition in turning Using a neural network , 1995 .

[23]  K. Chandrashekhara,et al.  A thick composite-beam model for delamination prediction by the use of neural networks , 2000 .

[24]  Keizo Sakuma,et al.  Study on Drilling of Reinforced Plastics (GFRP and CFRP) : Relation between Tool Material and Wear Behavior , 1984 .

[25]  A. Sherif El-Gizawy,et al.  An approach for development of damage-free drilling of carbon fiber reinforced thermosets , 2001 .

[26]  Sung-Lim Ko,et al.  Burr minimizing scheme in drilling , 2003 .

[27]  H. Hocheng,et al.  The effect of chisel length and associated pilot hole on delamination when drilling composite materials , 2003 .

[28]  Jose Mathew,et al.  Investigations into the effect of geometry of a trepanning tool on thrust and torque during drilling of GFRP composites , 1999 .

[29]  S. M. Kulkarni,et al.  Influence of process parameters on cutting force and torque during drilling of glass–fiber polyester reinforced composites , 2005 .