In this present study, the effect of drilling parameters and carbide drill bits in drilling of Al 5083 H116 alloy was investigated. The drilling tests were carried out using various carbide drill bits at 40, 80, 120, 160 m/min cutting speeds and 0.025, 0.050, 0.075, 0.100 feed rates. The experimental design was performed using the Taguchi’s L16 orthogonal array. The drilling tests were carried out without using coolant and it was aimed to minimize the thrust force, drill bit temperature and burr formation at the hole exit. Simultaneous optimization was performed using Taguchi-based Grey Relational Analysis (GRA). Using the data obtained from the drilling tests, mathematical models with Response Surface Methodology (RSM) and predicted values with Artificial Neural Networks (ANN) were obtained. It was observed that there was a significant increase in thrust force and burr height with increasing feed rate. In addition, the drill bit temperature was adversely affected by the increasing values of the cutting speed. The most effective control factors according to the analysis of variance were found to be the feed rate with 99.9 % for thrust force, cutting speed with 91.54 % for drill bit temperature and feed rate with 79.78 % for burr height. As a result of GRA, the feed rate with a value of 0.3612 was determined as the most important control factor, moreover, according to RSM results, the optimum parameters were 40 m/min cutting speed, 0.025 mm/rev feed rate and drill bit 1. The reliability of the developed mathematical model was confirmed with determination coefficients of 99.1 % for the thrust force, 98.8 % for the drill bit temperature and 99.7 % for the burr height. With ANN, a prediction success rate of 99.8 % for thrust force, 99.8 % for drill bit temperature and 99.6 % for burr height was achieved.

在本研究中，研究了钻孔参数和硬质合金钻头对 Al 5083 H116 合金钻孔的影响。使用各种硬质合金钻头以 40、80、120、160 m/min 的切削速度和 0.025、0.050、0.075、0.100 的进给速率进行钻孔测试。实验设计是使用田口的 L16 正交阵列进行的。钻孔测试是在不使用冷却液的情况下进行的，目的是最大限度地减少推力、钻头温度和孔出口处的毛刺形成。使用基于田口的灰色关联分析 (GRA) 进行同步优化。使用从钻井测试中获得的数据，获得了采用响应面方法 (RSM) 的数学模型和采用人工神经网络 (ANN) 的预测值。据观察，随着进给速度的增加，推力和毛刺高度显着增加。此外，钻头温度受到切削速度增加值的不利影响。根据方差分析发现，最有效的控制因素是推力的进给率为 99.9%，钻头温度的切削速度为 91.54%，毛刺高度的进给率为 79.78%。作为 GRA 的结果，值为 0.3612 的进给速率被确定为最重要的控制因素，此外，根据 RSM 结果，最佳参数为 40 m/min 切削速度、0.025 mm/rev 进给速率和钻头1.推力的确定系数为99.1%，98，证实了所开发数学模型的可靠性。8 % 的钻头温度和 99.7 % 的毛刺高度。使用人工神经网络，推力预测成功率为 99.8%，钻头温度预测成功率为 99.8%，毛刺高度预测成功率为 99.6%。