A Comparative Study on Prediction of Cutting Force using Artificial Neural Network and Genetic Algorithm during Machining of Ti-6Al-4V

The purpose of this comparative study is to improve the predictive accuracy cutting force during turning Ti-6Al-4V on a lathe machine. By optimizing machining process parameters such as speed, feed rate, and depth cut, in can be improved significantly. Cutting one crucial characteristics that must monitored order enhance tool life surface finish workpiece. This paper based experimental dataset forces collected titanium alloy under Minimum Quantity Lubrication (MQL) condition. To predict forces, two machine learning techniques are explored. Firstly, black-box model called an Artificial Neural Network (ANN) proposed force. Using Levenberg-Marquardt algorithm, two-layered feedforward neural network built MATLAB second implemented was Genetic Algorithm (GA), white-box model. GA optimization technique which Darwinian theories. It probabilistic method searching, unlike most other search algorithms, require definite inputs. symbolic regression HeuristicLab, developed estimate anticipated values for both models were compared. Since ANN had fewer errors, it ascertained particular preferable optimization.