Prediction of end milling process parameters using artificial neural network

• Published in: Materials today : proceedings Vol. 38; pp. 3168 - 3176
• Main Authors: Parmar, Jignesh G., Dave, K.G., Gohil, A.V., Trivedi, H.S.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2021
• Subjects: Artificial neural network; Design of experiments; End milling process; Prediction; Artificial neural network; End milling process; Design of experiments; Prediction
• ISSN: 2214-7853; 2214-7853
• DOI: 10.1016/j.matpr.2020.09.644

In this research, the artificial neural network (ANN) model have been trained and developed using a mathematical model for prediction of performance evaluation criteria of end milling process, such as material removal rate, machining time, tool life, cutting force, torque and power. Input process variables of end milling and mechanical properties of used material have been considered in ANN model. MATLAB R2015a has been utilized for training and testing of ANN model. Feed forward back propagation network has been used with 5 input neurons, 6 hidden layers, 10 neurons in each hidden layer and 6 output neurons. Experimentation work has been carried out for validation of ANN model. In current research AISI1020 steel material and solid carbide end milling cutter have been selected as work material and cutting tool respectively. A good agreement has been found between the results of ANN model and experimentation. It reveals that developed artificial neural network model can efficiently utilize to predict the multi-response parameters of the end milling process with any selected materials without experimentation cost and time.