Search

This article presents an investigation of the use of machine learning methodologies for the prediction of surface roughness in milling operations, using sensor data as the primary source of information. The sensors, which included current transformers, a microphone, and displacement sensors, captured comprehensive machining signals at a frequency of 10 kHz. The signals were subjected to preprocessing using the Savitzky-Golay filter, with the objective of isolating relevant moments of active material machining and reducing noise. Two machine learning models, namely Elastic Net and neural networks, were employed for the prediction purposes. The Elastic Net model demonstrated effective handling of multicollinearity and reduction in the data dimensionality, while the neural networks, utilizing the ReLU activation function, exhibited the capacity to capture complex, nonlinear patterns. The models were evaluated using the coefficient of determination (R²), which yielded values of 0.94 for Elastic Net and 0.95 for neural networks, indicating a high degree of predictive accuracy. These findings illustrate the potential of machine learning to optimize manufacturing processes by facilitating precise predictions of surface roughness. Elastic Net demonstrated its utility in reducing dimensionality and selecting features, while neural networks proved effective in modeling complex data. Consequently, these methods exemplify the efficacy of integrating data-driven approaches with robust predictive models to improve the quality and efficiency of surface.

In this investigation, an AA2519-T62 FSW butt joint was subjected to shot peening with an air pressure of p = 0.6 MPa, a processing time of t = 10 min (per side), and a steel ball diameter of d k = 1.5 mm. In order to evaluate the impact of shot peening on the low-cycle behavior, the samples were tested with coefficient R = 0.1 at total strain amplitudes of 0.35%, 0.4%, and 0.5%. The shot-peened welds are characterized by a higher value of stress amplitude, a lower value of plastic strain amplitude, and their fatigue life increased slightly. The cyclic strength coefficient and the cyclic strain hardening exponent were reduced by 45% and 55%, respectively, as the result of the surface layer hardening. The shot peening process had no noticeable effect on the character of crack initiation and propagation. Almost in all cases, the cracking started in the area under the weld face, located close to the boundary between the thermo-mechanically affected zone and the stir zone at the advancing side. Only at the heaviest loadings (ε ac = 0.5%) were cracks initiated in the heat-affected zone at the retreating side. Despite the introduction of small cracks in the stir zone, their presence did not affect the decohesion character of the welded joint. Overall, it was observed that there is a minimal, positive impact of shot peening on the properties of the investigated joints.

This study aims to quantify and assess qualitatively the impact of modeling simplifications used to represent inertial and aerodynamic loads on the stresses and structural deformations of a centrifugal compressor in operation. The research object is the compressor of the high-pressure line of the DGEN 380 bypass turbine engine. Based on the virtual dynamometer WESTT CS/BV, the gas-dynamic parameters at the entrance to the centrifugal compressor and after the stage are determined. These values were used as initial parameters for numerical flow analysis. As part of the numerical strength analyses, a series of several load configurations were carried out: spin only, spin and inlet pressure normally applied on the working surface of the rotor blade, spin and outlet pressure normally applied on the working surface of the rotor blade, and one-way fluid-structure interaction analysis taking into account the aerodynamic loads with and without spinning. Based on the simulations, the level of similarity of a given load configuration with the last analysis, adopted as the reference, was determined. It was observed that in terms of the stress state, the rotational analysis taking into account the pressure on both sides of the blade gives satisfactory results, but the strain values are overestimated. The results obtained and the method of evaluation of compressor results can be used in research in the area of aviation, automotive, and refrigeration industries., (© 2022. The Author(s).)

Industry 4.0 corresponds to the Fourth Industrial Revolution, resulting from technological innovation and research multidisciplinary advances. Researchers aim to contribute to the digital transformation of the manufacturing ecosystem both in theory and mainly in practice by identifying the real problems that the industry faces. Researchers focus on providing practical solutions using technologies such as the Industrial Internet of Things (IoT), Artificial Intelligence (AI), and Edge Computing (EC). On the other hand, universities educate young engineers and researchers by formulating a curriculum that prepares graduates for the industrial market. This research aimed to investigate and identify the industry's current problems and needs from an educational perspective. The research methodology is based on preparing a focused questionnaire resulting from an extensive recent literature review used to interview representatives from 70 enterprises operating in 25 countries. The produced empirical data revealed (1) the kind of data and business management systems that companies have implemented to advance the digitalization of their processes, (2) the industries' main problems and what technologies (could be) implemented to address them, and (3) what are the primary industrial needs and how they can be met to facilitate their digitization. The main conclusion is that there is a need to develop a taxonomy that shall include industrial problems and their technological solutions. Moreover, the educational needs of engineers and researchers with current knowledge and advanced skills were underlined.

Currently, medicine uses typical industrial structure techniques, including reverse engineering, data processing, 3D-CAD modeling, 3D printing, and coordinate measurement techniques. Taking this into account, one can notice the applications of procedures used in the aviation or automotive industries based on the structure of Industry 4.0 in the planning of operations and the production of medical models with high geometric accuracy. The procedure presented in the publication shortens the processing time of tomographic data and increases the reconstruction accuracy within the hip and knee joints. The procedure allows for the partial removal of metallic artifacts from the diagnostic image. Additionally, numerical models of anatomical structures, implants, and bone cement were developed in more detail by averaging the values of local segmentation thresholds. Before the model manufacturing process, additional tests of the PLA material were conducted in terms of its strength and thermal properties. Their goal was to select the appropriate type of PLA material for manufacturing models of anatomical structures. The numerical models were divided into parts before being manufactured using the Fused Filament Fabrication technique. The use of the modifier made it possible to change the density, type of filling, number of counters, and the type of supporting structure. These treatments allowed us to reduce costs and production time and increase the accuracy of the printout. The accuracy of the manufactured model geometry was verified using the MCA-II measuring arm with the MMDx100 laser head and surface roughness using a 3D Talyscan 150 profilometer. Using the procedure, a decrease in geometric deviations and amplitude parameters of the surface roughness were noticed. The models based on the presented approach allowed for detailed and meticulous treatment planning.

This article presents advances in the methodology of rapid various probe configurations comparison for the five-axis, tilting-head machine tools in conjunction with master artifacts. The research was performed in a direct context of automated machining of large, complex jet engine cases made from 17-4PH and 321 stainless steel materials. The aim of the study was to investigate whether all probe configurations have comparable measurement capability for use in manufacturing environment conditions. Based on the preliminary stage of the study, the T1 main straight probe achieved acceptable results of repeatability and reproducibility, lower than 10%, except for the reference diameter measurement of MT#2, where 15.4% R&R was achieved, conditionally accepted. For the straight probe configuration, error lower than 10 μm was achieved for the true position measurement and error ±10 μm for the reference diameter measurement, in relation to the vertical and horizontal head position, with the exception of the T9 and T5 MT#2 probe configuration, where higher error was noticed. The obtained results of the T5 MT#2 and T9 probes were supplemented with additional tests, which are also included. For the custom styli probes, the T4 and T6 configurations, unacceptable error, higher than 0.30 mm, was observed for the Y axis position. Depending on the shop floor and machine tool condition, variability of the results was also observed. Hence, the collected data and research helped to determine the mutual measurement errors and determine the application limitations of probes for an adaptive process flow.