Машински факултет [Научни радови] / Faculty of Mechanical Engineering [Scientific papers]

Трајни URI за ову колекцију

https://repozitorijum.ues.rs.ba/handle/123456789/48

Потражи

Прегледај Машински факултет [Научни радови] / Faculty of Mechanical Engineering [Scientific papers] по Аутор "Antić, Aco"

Сада се приказује 1 - 2 од 2
  • Сличица
    Ставка
    Characterization of Microstructural Damage and Failure Mechanisms in C45E Structural Steel under Compressive Load
    (MDPI, 2022) Kraišnik, Milija; Čep, Robert; Kourˇil, Karel; Baloš, Sebastian; Antić, Aco; Milutinović, Mladomir
    In this paper, the microstructural damage evolution of a steel with a ferrite–pearlite microstructure (C45E) was investigated during the process of cold upsetting. The development and the accumulation of microstructural damage were analyzed in different areas of samples that were deformed at different strain levels. The scanning electron microscopy (SEM) results showed that various mechanisms of nucleation of microcavities occurred during the upsetting process. In quantitative terms, microcavities were predominantly generated in pearlite colonies due to the fracture of cementite lamellae. In addition, the mechanism of decohesion had a significant influence on the development of a macroscopic crack, since a high level of microcracks, especially at higher degrees of deformation, was observed at the ferrite/pearlite or ferrite/ferrite interfaces. It was found that the distribution of microcavities along the equatorial plane of the sample was not uniform, as the density of microcavities increased with increasing strain level. The influence of stress state, i.e., stress triaxiality, on the nucleation and distribution of microcracks, was also analyzed.
  • Сличица
    Ставка
    Thermal Behavior Modeling Based on BP Neural Network in Keras Framework for Motorized Machine Tool Spindles
    (MDPI, 2022) Košarac, Aleksandar; Cep, Robert; Trochta, Miroslav; Knežev, Miloš; Zivković, Aleksandar; Mlađenović, Cvijetin; Antić, Aco
    This paper presents the development and evaluation of neural network models using a small input–output dataset to predict the thermal behavior of a high-speed motorized spindles. Different neural multi-output regression models were developed and evaluated using Keras, one of the most popular deep learning frameworks at the moment. ANN was developed and evaluated considering the following: the influence of the topology (number of hidden layers and neurons within), the learning parameter, and validation techniques. The neural network was simulated using a dataset that was completely unknown to the network. The ANN model was used for analyzing the effect of working conditions on the thermal behavior of the motorized grinder spindle. The prediction accuracy of the ANN model for the spindle thermal behavior ranged from 95% to 98%. The results show that the ANN model with small datasets can accurately predict the temperature of the spindle under different working conditions. In addition, the analysis showed a very strong effect of type coolant on spindle unit temperature, particularly for intensive cooling with water