Altın Karataş, MeltemGökkaya, HasanAkıncıoğlu, SıtkıBiberci, Mehmet Ali2023-07-262023-07-2620221573-61051573-6113https://doi.org/10.1108/MMMS-04-2022-0071https://hdl.handle.net/20.500.12684/12757Purpose The purpose of this study is to optimize processing parameters to get the smallest average surface roughness (Ra) and delamination damage (F-d) values during drilling via abrasive water jet (AWJ) of the glass fiber-reinforced polymer composite material produced at [0 degrees/90 degrees](s) fiber orientation angles. Design/methodology/approach Drilling experiments were done via AWJ with three-axis computer numerical control (CNC) control system. Machine processing parameters such as water pressure of 3,600, 4,300, 4,800 and 5,300 bar; stand-off distance of 1, 2, 3 and 4 mm; traverse rate of 750, 1,500, 2,000 and 3,000 mm/min; and hole diameters of 8, 10, 12 and 14 mm have been selected. The effects of processing parameters in drilling experiments were investigated in conformity with the Taguchi L-16 orthogonal array and the data obtained were analyzed using Minitab 17 software. The signal/noise (S/N) ratio was taken as a basis for evaluating the test results. Optimum processing conditions were determined by calculating the S/N ratio for both Ra and F-d in conformity with the smaller is better approximation. The effects of processing parameters on Ra and F-d were statistically investigated using analysis of variance, S/N ratio and Taguchi-based gray relational analysis. Ra and F-d were predicted by evaluating with the ANN model and were predicted with the least amount of error. Findings It has been determined that the most effective parameter for Ra and F-d is the water pressure and then the stand-off distance. Originality/value The novel approach is to reduce cost and the time spent by using Taguchi optimization as a result of AWJ drilling the material in this fiber orientation [0 degrees/90 degrees](s).en10.1108/MMMS-04-2022-0071info:eu-repo/semantics/closedAccessGlass Fiber-Reinforced Polymer Composite; Abrasive Water Jet; Taguchi-Based Gray Relational Analysis; Artificial Neural Network (Ann)Prediction; Optimization; Strength; ModelArticle1847347532-s2.0-85135225055WOS:000834723100001Q3Q3