A Performance Evaluation of Precise Micro Turning Process using TOPSIS-GRA-ANN

Precision micro machining is need of manufacturing industries. Multi-objective optimization (MOO) technique has attracted a lot of attention due to its broad applications for precision engineering. To find a fair and precise judgment from multiple number of objectives is a difficult task. The current MOO techniques are shortcomings and are biased toward the best possible outcome. Optimum process parameters ensure higher product quality, safety standards, optimum availability, and machine efficacy in the industry. Simultaneously, the cost of the entire production system of machining operations, such as cutting tool inserts, workpiece material and time has been reduced. The study focuses on optimal decision making for the best process parameters using a hybrid MOO technique. The suggested decision-making framework efficacy is demonstrated by conducting a case study in micro turning of Ti6Al4V using TiAlN coated tungsten carbide inserts. Additionally, the artificial neural network (ANN) model provides a superior prediction with 0.98656 coefficient of determination (R2), closely followed by Hybrid weightless TOPSIS-GRA method. A new hybrid optimization methodology can guide a decision making for reasonable judgment without professional skills, broad experience and weighting the responses and removes the multiple human error in engineering optimization.