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.

In recent years, plastic and metal 3D printing has experienced massive development in the professional and hobby spheres, especially for rapid prototyping, reverse engineering, maintenance and quick repairs. However, this technology is limited by a number of factors, with the most common being the cost and availability of the technology but also the lack of information on material properties. This study focuses on investigating the material properties of PLA, PETG, HIPS, PA, ABS and ASA in order to elucidate their behavior in terms of wear and thermal resistance. The research builds on previous studies focusing on the mechanical properties of these materials and includes wear testing and DMA analysis. Weight loss, frictional forces, and frictional work including relative frictional work are recorded as part of this testing. The storage modulus and loss modulus including tan(δ) were then measured using DMA.

In this paper, a practical issue of the application of cubic boron nitride (CBN) cutting tools for the machining of steel 100Cr6 thin-walled bearing rings is addressed. Three geometries of the commercially available CBN cutting inserts were tested at different machining parameters. The effect of geometry was assessed in terms of surface integrity, considering 2D profile parameters, 3D topography of the surface, and residual stresses in the surface layer. The results were sometimes contradictory, since the same cutting inserts provided the largest and the lowest values of the topography parameters, dependent on different cutting conditions. In general, CBN cutting inserts with XCEL geometry ensured the smallest profile parameters Ra and Rz, and the spatial parameters of Smr1 exhibited the largest values among all tested tools, suggesting reduced wear resistance. Residual stresses analysis did not reveal any inacceptable or potentially dangerous surface layer state after machining.

This article discusses the issue of force behavior in a pre-tensioned bolt that is part of a symmetrical flange connection, loaded with an operating load parallel to the bolt axis. The first part describes the issue being dealt with in detail. The next part offers a brief description of the generally known theoretical approach to the solution, and also outlines the limitations of this approach. This part is followed by a theoretical analysis of working load behavior in the bolt of the analyzed device, using Finite Element Method (FEM). In this article, a comparison of several different approaches to the solution can be also found, followed by a description of the experiment preparation and its results. The obtained values also serve as a subject for reverse iterative analysis carried out using ANSYS software. The aim is to find a proper modification to the symmetric calculation model that would be consistent with the results of measurements from technical practice. All results achieved are described in the final part of the article.