Predictive Modelling of Delamination Factor and Cutting Forces in the Machining of GFRP Composite Material Using ANN

Drilling is one of the key machining operations in the hole creation processes. Compared with the machining processes, such as milling, turning, the drilling operation is largely used in the composite materials processing. Delamination is a critical problem found during drilling operation. It causes structural reliability and poor assembly tolerance as well as the potential for long-term performance decline. As a result, drilling of any material requires dimensional stability and interface quality. This study involves drilling operation in a GFRP composite material. It has selected and used the feed-forward back propagation as the algorithm with trainglm, learngdm, MSE and transig as the training, learning, performance and transfer functions, respectively. Four input parameters were taken as four nodes in the input layer and thrust force and delamination as two nodes in the output layer. 4-9-2-2 neural network structure for composite material helped in the best way to compare actual values and an artificial neural network (ANN) predictive model for thrust force and delamination in drilling operation. ANN gives very good performance for the delamination factor and the cutting force.