Optimization of turning process using artificial intelligence technology

In the current work, some experiments were performed based on a design of experiment (DOE) technique called full factorial design. The experimental results are discussed in statistical analysis, and the system was modeled using the artificial neural network (ANN) and subsequently optimized by a genetic algorithm (GA). The statistical analysis shows that the main effects and some 2-interaction effects affect the surface roughness and flank wear. The results show that the feed rate, nose radius, and approach angle have a significant effect on the flank wear and the surface roughness, but the cutting velocity has a significant effect on the flank wear alone. The optimum values of cutting parameters were identified and the resultant optimum values of flank wear and surface roughness were found to be in good agreement with the results of a validation experiment under a similar condition. The optimized values showed a significant reduction in roughness and flank wear.