Alex Kootsookos

CVD and PVD coating process modelling by using artificial neural networks

Thin-film coating plays a prominent role on the manufacture of many industrial devices. Coating can increase material performance due to the deposition process. Having adequate and precise model that can predict the hardness of PVD and CVD processes is so helpful for manufacturers and engineers to choose suitable parameters in order to obtain the best hardness and decreasing cost and time of industrial productions. This paper proposes the estimation of hardness of titanium thin-film layers as protective industrial tools by using multi-layer perceptron (MLP) neural network. Based on the experimental data that was obtained during the process of chemical vapor deposition (CVD) and physical vapor deposition (PVD), the modeling of the coating variables for predicting hardness of titanium thin-film layers, is performed. Then, the obtained results are experimentally verified and very accurate outcomes had been attained.

Tool vibration prediction and optimisation in face milling of Al 7075 and St 52 by using neural networks and genetic algorithm

Tool vibration generated under unsuitable cutting conditions is an extremely serious problem during face milling as it causes excessive tool wear, noise, tool breakage, and deterioration of the surface quality. In the current study, an artificial neural network (ANN) was used to predict tool vibration stability during face milling for different materials: Al 7075 and St 52. The testing of the ANN after training had a correlation of 99.206% with experimentally determined results. A generic algorithm (GA) was then used to minimise the vibration experienced during face milling and machining was performed using the GA recommended parameters. Measurement of the vibration during machining showed that the GA had a calculated error of 0.124%.

MODELING AND OPTIMIZATION OF THE CUTTING FLUID FLOW AND PARAMETERS FOR INCREASING TOOL LIFE IN SLOT MILLING ON St52

In this paper the CNC machining of St52 was modeled using an artificial neural network (ANN) in the form of a four-layer multi-layer perceptron (MLP). The cutting parameters used in the model were cutting fluid flow, feed rate, spindle speed and the depth of cut and the model output was the tool life. For obtaining more accuracy and spending less time Taguchi design of experiment (DOE) has been used and correlation between the output of the ANN and the experimental results was 96%. Further optimization process has been done by use of a genetic algorithm (GA). After optimization process tool life was increased about 8% equal to 33 min and was corroborated by experimental tests. This demonstrates that the coupling of an ANN with the GA optimization technique is a valid and useful approach to use.