ANFIS-TLBO-based optimization of drilling parameters to minimize burr formation in aluminum 6061

This research paper presents an experimental investigation conducted on a radial drilling machine, focusing on burr formation on aluminum 6061 material under wet conditions. The primary objective is to identify the best drilling parameters that lead to minimal burr height and thickness while also developing an accurate burr prediction model. A total of 27 experimental runs were conducted according to the Taguchi method, involving three main drilling parameters: drill diameter, point angle, and spindle speed. Next, two distinct prediction models for burr height and thickness were developed using Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) based on the experimental data. Key findings reveal the superiority of the ANFIS-based predicted model over the ANN model in terms of predictive accuracy. In the next phase of the work, the developed ANFIS models underwent optimization utilizing the Teaching-Learning-Based Optimization (TLBO) algorithm, culminating in further enhancements. The research identifies optimal values for drill diameter, point angle, and spindle speed, demonstrating their effectiveness in minimizing burr height and thickness. Specifically, the optimal parameters for minimizing burr height were determined as 12 mm for drill diameter, 99.8 degrees for point angle, and 2000 rpm for spindle speed, while for minimizing burr thickness, the optimal values were 8 mm for drill diameter, 111.6 degrees for point angle, and 2000 rpm for spindle speed, respectively. Crucially, the prediction models were validated through new experiments, affirming their reliability and efficacy. This study is notable for its novel merging of ANFIS and TLBO, a combination that is rarely investigated in burr reduction studies. This hybrid approach has shown to be a significant advancement in precision production, providing a potential path for industries to improve efficiency, save costs, and improve product quality through better burr control.