Manufacturing Technology Journal, 2025 (vol. 25), issue 4
AI-Integrated Thermal Prediction and Multi-Criteria Optimization in Cylindrical Grinding Using Machine Learning and Genetic Algorithms
Maya M. Charde, Yogesh J. Bhalerao, Lenka Cepova, Sharadchandra N. Rashinkar, B. Swarna
Manufacturing Technology 2025, 25(4):432-447 | DOI: 10.21062/mft.2025.053 
The paper focuses on the application of machine learning techniques and optimization algorithms in predictions and controls of grinding temperature variations. The major thrust of investigation has been on how the different input conditions such as feed, depth of cut, and cooling conditions influence grinding temperatures and the effectiveness of these conditions on the control of their thermal effects. Three machine learning models: Random Forest (RF), Gradient Boosting (GB), and Artificial Neural Networks (ANN) were then used to develop prediction models for the grinding temperature on both face and shoulder of the workpiece. Out of all the models,...
Research on Stator Thermal Fault Detection of Steam Turbine Generator Based on Improved Transformer and Gaussian Mixture Model
Fengqin Cheng, Weinan Zheng
Manufacturing Technology 2025, 25(4):448-454 | DOI: 10.21062/mft.2025.051
This study proposes a multi-stage intelligent diagnostic approach integrating Physics-Guided Normalization (LPGN), enhanced Transformer networks, and Gaussian Mixture Models (GMM) for thermal fault detection in turbine generator stators. The methodology sequentially performs the following steps: (1) enhances localized anomaly features in temperature data through LPGN, (2) efficiently extracts temporal patterns via the optimized Transformer architecture, and (3) achieves unsupervised fault classification using GMM. Experimental results demonstrate the proposed method's superiority over conventional ARIMA and LSTM models across multiple evaluation metrics,...
Improving Strength and Ductility in Mg–Y–Zn alloy via Pre-deformation Prior to Extrusion
Drahomír Dvorský, Yoshihito Kawamura, Shin-Ichi Inoue, Jiří Kubásek, David Nečas, Luděk Heller, Esther De Prado, Jan Duchoň, Petr Svora, Miroslav Čavojský, Dalibor Vojtěch
Manufacturing Technology 2025, 25(4):455-459 | DOI: 10.21062/mft.2025.059
The Mg-Y-Zn alloy system is well known for its outstanding combination of high strength and ductility, even at relatively low concentrations of alloying elements. This exceptional performance is primarily at-tributed to its characteristic microstructure, which features Long-Period Stacking Ordered (LPSO) phas-es and the distinctive Mille-Feuille Structure (MFS). Kink-induced strengthening, developed during thermomechanical processing, has emerged as a promising strategy to simultaneously enhance strength and ductility. In this study, the beneficial effect of pre-deformation aimed at introducing additional kinks into the microstructure prior to extrusion...
Novel Multi Levels Tool Based on Rotating Ballizing Technique to Manufacturing the Externally Toothed Components an Experimental Study
Eman S. M. Abd-Elhalim, Emad A. Fahmy, Mohamed N. El-Sheikh, Ahmed M.I. Abu-Oqail, Hammad T. Elmetwally, Ayman Ali Abd-Eltwab
Manufacturing Technology 2025, 25(4):460-468 | DOI: 10.21062/mft.2025.049
Externally toothed components have a very crucial and essential role in all areas of production and manufacturing because they function as away of transmitting motion, energy, and power in all indus-trial applications, such asmodes of transportation, aviation, aerospace, equipment, and operating machines like lathes and milling. All machines have a gear box. Therefore, it is receiving increasing attention. This research presents a new multi-stage rotary ballizing technology for producing toothed parts in one stroke. This process has been investigated experimentally. The parameters that were ex-amined experimentally was at the optimal conditions for...
Experimental Evaluation of Vibration Responses to Progressive Gear Damage in Planetary Gear
Tomáš Gajdošík, Matúš Vereš, Igor Gajdáč, Ronald Bašťovanský
Manufacturing Technology 2025, 25(4):469-481 | DOI: 10.21062/mft.2025.056
This study presents a systematic experimental analysis of vibration responses in a planetary gearbox (type A2000) under both undamaged and artificially induced fault conditions. The primary aim was to identify specific frequency-domain signatures of various types and severities of gear defects—such as pitting on the flanks of gear teeth, missing teeth, unbalance of the carrier, and damage to the ring gear—through spectral analysis of vibration signals. Measurements were conducted in both loaded and unloaded states using non-contact torque sensors and a multi-channel diagnostic system (SKF IMx-S) with tri-axial accelerometers. The results...
Influence of Selected Heat Treatment on Alloy Properties of Ti–6Al–4V Alloy
Roman Horký, Sylvia Kuśmierczak, Tomáš Vlach
Manufacturing Technology 2025, 25(4):482-488 | DOI: 10.21062/mft.2025.054
Titanium is the polymorphic metal whose recrystallization temperature significantly affects its final properties. The area between 850 °C and 995 °C is a very important area from the point of view of heat treatment of titanium alloys. It is a transition area just below the β transition limit. This article deals with the analysis of the influence of thermal loading on the change in tensile strength and fracture behavior of titanium alloys in comparison with thermally unloaded samples. Monitoring of fracture surfaces and description of the internal structure of the material.
Geometric Accuracy of Elements Made Using the FFF Method from Selected Polymers with Different Internal Structure Densities
Małgorzata Gontarz-Kulisiewicz, Jacek Bernaczek, Mariusz Dębski
Manufacturing Technology 2025, 25(4):489-499 | DOI: 10.21062/mft.2025.058
Due to their availability and ease of use, additive techniques are experiencing dynamic development. This applies to both the industrial sector and individual recipients. The authors of numerous publications address in their research the subject of the influence of selected printing process parameters on the strength of models, usually made using selected MEX (Material Extrusion) methods. Among the MEX methods, the most frequently chosen are the FFF (Fused Filament Fabrication) and FDM (Fused Deposition Modeling) methods. This is due to the high availability and low cost of devices using the methods mentioned above and the high availability of polymer...
Overcoming Rotary Mechanism Limitations in CNC Machines: A 3-PRS Approach
Rudolf Madaj, Matúš Vereš, Róbert Kohár, Peter Weis, Filip Šulek
Manufacturing Technology 2025, 25(4):500-510 | DOI: 10.21062/mft.2025.050
This paper presents the design and analysis of a 3-PRS mechanism for positioning cutting heads in CNC machines, addressing limitations of traditional rotary mechanisms such as hose twisting, wear, and limited modularity. Kinematic and dynamic analyses guided actuator selection and confirmed bearing durability. The mechanism achieves a favourable load-to-weight ratio and integrated Z-axis movement, making it suitable for simpler gantry CNC machines. Though programming is complex due to multiaxis synchronization, the modular design supports easy adaptation to different tools. Future research will focus on reducing the eccentric torch offset and refining...
Strain Field Determination for Additively Manufactured Thermoplastics Using Computer Vision
Jaroslav Majko, Ondrej Piroh, Ján Minárik, Milan Vaško, Marián Handrik, Milan Sága, Zbigniew Saternus
Manufacturing Technology 2025, 25(4):511-520 | DOI: 10.21062/mft.2025.060
The effective application of additively manufactured materials requires accurate identification of their mechanical properties as well as damage mechanisms. Computer vision offers a novel approach for non-contact measurements, enabling the identification of selected mechanical properties. This paper presents a new method based on image analysis and the detection of circular markers for non-contact displacement measurements. The core principle involves detecting the centers of gravity of the circular markers formed on the sample under investigation. The centers of gravity are evaluated on each image created during the tensile test, representing nodal...
Surface Morphology and Ablation Efficiency in DUV Ultrafast Laser Micromachining of Fused Silica
Jan Novotný, Libor Mrňa, Josef Sedlák, Štěpán Kolomý
Manufacturing Technology 2025, 25(4):521-530 | DOI: 10.21062/mft.2025.057
Fused silica is a key material for high-precision applications such as micro-optics and microfluidics. One route to improving direct laser writing (DLW) of fused silica is the use of shorter laser wavelengths, which enable tighter focusing and enhanced absorption. In this study, the influence of process parameters on surface quality and material removal during DLW using a deep ultraviolet (DUV) ultrafast laser (257 nm, 1 ps) was investigated. A full-factorial design of the experiment was used to identify conditions that optimise both surface quality and ablation efficiency. Surface roughness as low as Sa ≈ 200 nm and material removal...
Analytic Solution of the Motion Equations of the Rolling Stock Chassis Incorporating the Effect of Asymmetry and Kinematics Excitation
Blanka Skocilasova, Frantisek Klimenda, Jan Skocilas, Tereza Jarosova
Manufacturing Technology 2025, 25(4):531-539 | DOI: 10.21062/mft.2025.052
The article provides an analytical solution for the dynamics of a vehicle chassis designed for both road and rail operation, featuring either single or multiple primary linear suspensions using coil springs. It derives the equations of motion for a simplified two-axle chassis model that includes both a basic primary suspension and a simplified chassis suspension. The study focuses on the simplest calculation model to analyze suspension behavior, taking into account the asymmetry in spring stiffness and geometric positioning. There is an unequal distribution of weight across the vehicle body. An analysis is conducted on a comprehensive vehicle model...
Optimizing Process Parameters during the Creation of Powder Laser Weld Cladding Coatings from a Nickel Alloy
Martin Švec, Libor Dvořák
Manufacturing Technology 2025, 25(4):540-548 | DOI: 10.21062/mft.2025.047
Nowadays, increasing emphasis is placed on the production of parts using additive technologies, particularly for alloys that are difficult to process. In addition to standard additive technologies, such as Selective Laser Melting (SLM), other additive technologies are increasingly being used, including Directed Energy Deposition (DED). DED offers several advantages and is utilized both for producing entire components and for repairing damaged parts through weld cladding. In this study, the possibility of weld cladding of nickel-based hard alloys using DED was tested using a laser as the energy source to melt the additive material. The tests performed...
Study on Material Performance Calculation and Rolling Process Simulation of 35W210X Advanced High Strength Silicon Containing Steel
Tie Ye, Boran Chen, Zetian Li, Zhenyu Gao, Kuibo Liu, Zheng Ren
Manufacturing Technology 2025, 25(4):549-558 | DOI: 10.21062/mft.2025.055
This study used JMatPro software to comprehensively analyze the new low-iron-loss cold-rolled non-oriented high-grade electrical steel 35W210X, calculating phase composition, Gibbs free energy, stress-strain relationships, and yield strength changes. Results showed its ferritic structure and consistent calculated room-temperature yield strength with experiments. To study production cracks, JMatPro data was used in Deform-3D to simulate the five-pass reciprocating cold rolling on a Sendzimir 20-roll mill, successfully replicating the cracks. Aiming at the problems of frequent cracking and low yield rate (<50%), the study found the original single...
Fault Diagnosis of Electric Motor Rotor Systems Based on Feature Extraction and CNN-BiGRU-Attention
Mei Zhang, Zilong Sun, Wenchao Zheng
Manufacturing Technology 2025, 25(4):559-568 | DOI: 10.21062/mft.2025.048
To enhance the accuracy of fault diagnosis (FD) in motor rotor systems, this study introduces a novel method that leverages feature extraction (FE) combined with a CNN-BiGRU-Attention deep learning model. Initially, the time-domain features of the vibration signals are extracted using Variational Mode Decomposition (VMD), which also effectively denoises the data. Subsequently, the frequency-domain features of the vibration signals are extracted via Fast Fourier Transform (FFT). The aggregated features are then fed into the CNN-BiGRU-Attention model to perform fault classification. In this model, the Convolutional Neural Network (CNN) module extracts...
Crack Detection and Monitoring of their Growth in Critical Parts of Steam Pipeline by Electric Potential Drop Method
Petr Živný, Jindřich Jansa, Marek Měkuta, Pavla Lukášová
Manufacturing Technology 2025, 25(4):569-574 | DOI: 10.21062/mft.2025.046
An innovative way of using DCPD (Direct Current Potential Drop) method for off-line and online monitoring of critical parts of energy equipment in operation is presented. There are only a few NDT methods that allow detection and monitoring of defect growth in components at high temperatures and pressures. Monitoring of steam pipes and critical pipeline components in operation has been carried out for several years with different results. a relatively new way of using the DCPD method outside the laboratory is described. The carried-out tests were intended to resemble operational loads as much as possible. Therefore, the tests were performed at a temperature...