الفهرس | Only 14 pages are availabe for public view |
Abstract Cutting tool temperature is generally classified as the most important technological parameters in machining processes due to their significant impacts on the product quality. A large number of interrelated machining parameters have a great influence on the cutting tool temperature so it is quite difficult to develop a proper theoretical model to describe efficiently and accurately a machining process. In this work, an artificial neural network (ANN) model using MATLAB program for predicting cutting tool temperature and surface roughness during hard turning of alloy steel C45 is proposed. This work is based on an experimental dataset of cutting tool temperature and surface roughness measured during hard turning process. Rotational speed values of 900, 1200 and 1500 rpm and a depth of cut of 1, 1.5 and 2 mm and feed rate values of 0.1, 0.15 and 0.2mm/rev respectively are taken as input parameters of the ANN model. However, the surface roughness and the cutting tool temperature are the outputs. It is found that, the ANN model showed a reasonable agreement with the experimental results, therefore it is considered to be a trusted means of modeling and simulating the turning process. It is found also that increasing the speed of rotation of the turning process increased the cutting tool temperature. The maximum temperature recorded during the process was 110°C at a=2 mm, S=0.2 mm/rev and at N=1500 rpm. Similarly, low surface roughness of 0.72 μm was obtained at a rotational speed of 1500 rpm, depth of cut of 2 mm and feed rate of 0.15 mm/rev. However, high surface roughness of 2.78 μm was obtained at a rotational speed of 900 rpm, depth of cut of 1.5 mm and feed rate of 0.1 mm/rev. In addition to that, increasing the feed rate and rotational speed gave a low level of surface roughness. Finally, it showed that both of the rotational speed and feeding rate have a significant impact on the surface roughness, however, the cutting depth has not a sufficient effect on the average surface roughness. |