Cutting Forces and Temperature Optimization in Turning using a Predictive Machining Theory, ANN, and MOGA

Abstract

To minimise stresses on the tool and workpiece, such as wear, thermal effect, workpiece stresses, cutting power, etc., the cutting force and the heat in the cutting area should be minimised. This work aims to introduce an artificial intelligence tool, more precisely the neural network, to achieve optimized cutting conditions. Oxley cutting modelling in conjunction with Johnson-Cook of an AISI 1045 material is converted to an artificial neural network model which will be used to determine a fitness function to be optimized. The Artificial Neural Network is constructed based on the training data collected from the predictive model of Oxley and JC, the choice of the most accurate ANN of minimal MSE= 0.001108 is based on a specific method of tuning the hyperparameters which result in an architecture; two hidden layers, 25 neurons for each hidden layer, a sigmoid activation function, a trainlm learning algorithm, and a learning rate of 0.01. A multi-objective optimization is performed using the MATLAB tool to obtain the optimum values for cutting velocity Vc, advance f, penetration depth ap, and cutting angle of the tool. It is found that the neural network is a more rapid calculation of cutting conditions such as shear zone forces, shear zone temperatures, and others. contrary to the Oxley and JC mathematical model which will require a lot of calculations. The optimum values for cutting conditions are 208 mm/min for cutting speed, 0.06mm/rev for f, 0.38 for ap, and 10° for clearance angle.