Tepki yüzey modeli ve genetik algoritma kullanılarak AISI 316’ nın delinmesinde oluşan çapak yüksekliğinin modellenmesi ve optimizasyonu

Abstract

İmalat sektöründe tam otomatik cihazların kullanımının yaygınlaşması ile birlikte üretim sürecinin modellenmesi büyük önem kazanmıştır. Bununla birlikte optimum üretim şartlarının belirlenmesi, üretimin gelişimi ve ürün kalitesi için önemli bir rol oynamaktadır. Bu çalışmanın amacı, minimum çapak yüksekliğini belirlemede optimum delme parametrelerini bulmak için Tepki yüzey modeli ve Genetik algoritma kullanarak sistematik bir prosedür ortaya koymaktır. Optimum üretim için, üç-düzeyli üç faktörlü tam deneysel tasarım, Tepki Yüzey Yöntemi ve Genetik Algoritma kullanılmaktadır. Delme işlemleri üç ilerleme hızı (0.1, 0.2 ve 0.3 mm/dev), üç kesme hızı (4, 8 ve 12 m/dak) ve farklı uç açısına (90°, 118° ve 135°) sahip HSS matkap takımları kullanılarak yapıldı. Deneyler Box Behnken tasarımı dikkate alınarak yapıldı. Tepki yüzey metodolojisi kullanılarak çapak yüksekliği için bir matematiksel tahmin modeli geliştirilmiştir. Bu matematiksel tahmin modelinden faydalanılarak minimum çapak yüksekliği için optimum delme parametrelerini belirlemede Genetik algoritma kullanıldı. Genetik algoritma optimizasyon sonuçlarında minimum çapak yüksekliğinin 4 m/dak kesme hızı, 0.1 mm/dev ilerleme hızı ve 135° uç açısında oluştuğu görüldü.

Keywords

• Delme, Çapak yüksekliği, Tepki yüzey modeli, Genetik algoritma.

Optimization and modelling of burr height by using response surface methodology and genetic algorithm in drilling AISI 316

Abstract

Drilling is one of the most commonly used industrial machining processes for production of holes in mechanical components. It is also an important machining process employed as finish step in the fabrication of machine parts. Typical problems associated with drilling include rapid tool/drill wear, hole delamination, burr formation, hole geometry, dimensional accuracy and hole surface quality. Two machining parameters are effective in a drill operation, cutting speed and feed rate. Therefore it is vital to evaluate these two parameters in order to achieve the desired hole shape and dimension. Burr formation affects workpiece accuracy and quality in several ways; dimensional distortion on part edge, challenges to assembly and handling caused by burrs in sensitive locations on the workpiece and damage done to the work subsurface from the deformation associated with burr formation. Burr formation is however important as it requires additional manufacturing process like deburring which attracts additional production time and cost. The drilling process produces burrs on both the entrance and the exit surface of a workpiece. An entrance burr forms where the drill undergoes plastic flow. The exit burr is the extension of the material off the exit surface of the workpiece. Since the exit burr is much larger than the entrance burr, most of the burr related problems reported to be associated with the exit burr (Kim, J., Dornfeld, D.A., 2002; Dornfeld, D, 2004). Response surface methodology (RSM) is a collection of mathematical and statistical techniques, which are useful for the modelling and analyzing the engineering problems and developing, improving, and optimizing processes. It also has important applications in the design, development, and formulation of new products, as well as in the improvement of existing product designs, and it is an effective tool for constructing optimization models. Genetic Algorithm (GA), which imitates the evolution mechanism of nature, is used for finding a particular data in a dataset. GA produces everimproving solutions based on the rule ‘the best one survives’. For this purpose, it uses a fitness function that selects the best, and operators like regeneration and mutation to produce new solutions. Another feature of GA is that it involves a group solution. By the way optimum solutions among other ones could be picked and disqualified ones are eliminated. Due to widespread use of highly automated devices in manufacturing, the manufacturing process modelling has gained importance. However, determination of optimal manufacturing conditions has an important role for production development and product quality. The purpose of this study is to demonstrate a systematic procedure by using RSM and GA to find a combination of optimal drilling parameters to obtain low burr height. The three-factor three-level full experimental design, Response surface methodology and Genetic algorithm are used for optimum production. Drillings are performed by using three feed rates (0.1, 0.2 and 0.3 mm/rev), three cutting speeds (5, 10 and 15 m/min) and different point angles (90°, 118° and 135°). The experiments were conducted based on Box-Behnken design. A mathematical prediction model was developed using Response Surface Methodology (RSM) for the burr height. Genetic algorithm is used for selection optimum drilling parameters to obtain minimum burr height by utilizing the mathematical prediction model. The GA optimization results have reveal that the minimum burr height was obtained at 4 m/min cutting speed, 0.1 mm/rev feed rate and 135° point angle.

Keywords

• Drilling, Burr height, Response surface methodology, Genetic algorithm.