Training an Artificial Neural Network Based on Results of the Experiment on Machining of Aluminum Alloys 2196, 2043 and 2099 Used in the Aeronautical Industry

The paper presents the cutting tool-life of uncoated and DLC-coated inserts used for machining of aluminum-lithium components used in the structure of Airbus A350 aircraft. Based on the collected data, a feed-forward artificial neural network with two hidden layers was created, trained using the Bayesian Regularization (trainbr) algorithm in MATLAB. The obtained results indicate a high performance of the model, with a low mean square error (MSE) and a correlation coefficient R > 0.98, which reflects an excellent generalization capacity and a close correlation between the actual and estimated values. The regression plot and error analysis confirmed the accuracy of the predictions made by the network. The internal parameters of the algorithm, such as the gradient and μ, provided additional information regarding the optimization process.