Fulltext search in archive

This paper details a systematic machine learning workflow designed for the prediction of surface roughness in grinding operations using key machining parameters. Those parameters are: Depth of Cut, Feed Rate, Work Speed, and Wheel Speed. The model was trained and validated on a data set which comprised experimental measurements of those parameters and their corresponding values of surface roughness. Three machine learning models, Random Forest, Gradient Boosting, and LightGBM, were developed and tested based on accuracy of prediction of the surface roughness. The validation of all three models was performed using performance metrics like Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R²). Among the models, LightGBM exhibited the highest value of performance with the lowest error ob-served MSE 0.0047, MAE 0.064, and RMSE 0.09 respectively while an R-squared value closest to zero. (-0.02). The moderate performance was shown by the Random Forest which presented an MSE of 0.0063, MAE of 0.085, and RMSE of 0.10 while the Gradient Boosting recorded the highest error rates which may indicate that it is the least effective model. It's an effective application of machine learning in predicting surface roughness and gives an insight into machining process optimization through predictive modelling.

Austenitic steels are among the most widely used materials in industries such as automotive, food, energy, chemical, etc. They are mainly used due to properties such as corrosion resistance, good strength, hardness, or weldability. Microstructural analysis was performed on a light microscope Neo-phot 32. AISI 304 austenitic steel has a microstructure formed by a large number of polyhedral austenite grains of different sizes. The steel microstructure, mechanical and fatigue properties, and areas of the plastic zone after the bending impact test were investigated. The surface hardness of samples was measured on a Zwick Roell ZHVμ microhardness measuring device using the Vickers method. After the bending impact test, fractures were formed with a significant deformation with a typical dimple morphology. The fatigue test, performed on a Zwick Roell resonant pulsator, monitored the plastic deformation causing changes in mechanical properties. Finally, fractographic evaluations of the fracture surfaces were performed on a Tescan Vega LMUII. scanning electron microscope.

This article is dedicated to exploring the potential enhancement of mechanical properties, such as hardness and tensile strength, in selected Al-Si alloys (AlSi7Mg0.3, AlSi7Cu4, and Al-Si10.5Cu1.2Mn0.8Ni1.2). High-melting-point elements, such as chromium and molybdenum, are rarely utilized as additives in Al-Si alloys. However, the article demonstrates the feasibility of improving the mechanical properties of these alloys through the addition of high-melting-point elements. High-melting-point metals, often referred to as refractory metals, typically have melting points above 2000 degrees Celsius. Common refractory metals include tungsten, molybdenum, tantalum, niobium, rhenium, and others. These metals exhibit excellent mechanical properties at elevated temperatures and often possess high density and good corrosion resistance. All casts were made using by gravity casting with different heat treatment conditions at 740 °C. The microstructures, hardness, microhard-ness and tensile strenght of the samples were analyzed. Hardness measurements were conducted using two types of hardness testers according to ČSN EN ISO 6506-1 for the Brinell hardness test method and ČSN EN ISO 6507-1 for the Vickers hardness test method. A static tensile test was performed on a universal testing machine, Inspekt 100, in accordance with the standard ČSN EN ISO 6892-1. The measured data demonstrated that high-melting-point metals affect each alloy differently. In some alloys, mechanical properties improved after heat treatment, while in others, a significant deterioration was observed, particularly in tensile strength.

The aim of this work is to verify the reliability of optical inspection of tires during their transport on a roller conveyor, with an emphasis on the accuracy of 3D scanning in real and simulated operating conditions. A measuring box was designed and constructed to eliminate environmental interference, and measurements were subsequently compared with different degrees of site coverage. Testing was carried out using a 3D sensor O3D302 operating on the Time-of-Flight principle, and spatial data in the form of point clouds were obtained and compared with the reference dimensions of the Nokian WR D4 tire. The effects of solar IR radiation, rain, surface moisture, and natural lighting conditions were analyzed, which caused different levels of deformation, noise, and measurement deviations. The results show that significant errors occur without coverage, while the measuring box significantly reduces these deviations and increases the stability of point data. Complete coverage from above and below proved to be the most effective solution, but the wet tire surface remains a significant source of interference. The work further proposes structural modifications to the box and recommends the application of a matte surface and the expansion of tests to include the effects of vibrations and real conveyor operation. The result is a technical evaluation of the measurements and recommendations for improving optical tire detection in the industrial process.

This paper examines the detection of internal defects in composite specimens composed of Onyx, a material featuring a nylon matrix reinforced with chopped carbon fibers. Artificial defects, in the form of flat-bottom holes of various geometries, were intentionally introduced during the additive manufac-turing process. The primary objective is to determine the depth detection capabilities of ultrasound by varying the excitation frequency and determining whether these defects remain identifiable at different subsurface levels. Ultrasonic lock-in thermography is utilized to excite specimens. As the frequency is modified, the depth of wave propagation also changes, a phenomenon well established in homogene-ous materials. However, the heterogeneous nature of Onyx introduces complexities into wave propa-gation. The recorded thermographic data are processed in MATLAB to calculate contrast ratio values, enabling a quantitative comparison of defect detectability for different defect geometries.

The paper deals with the influence of various quenching media based on polymer aqueous solutions on the quenching process of carbon steel C45, connecting theoretical knowledge about heat transfer, surface phenomena and phase transformations with experimental verification. Surface phenomena at the interface of the hardened sample and the quenching medium were monitored using a high-speed camera. Cooling curves of the samples were obtained using the method according to ISO 9950 (Determination of cooling characteristics – Nickel-alloy probe test method). The paper contains practical recommendations for optimizing industrial hardening processes, especially when choosing polymer hardening baths as an alternative to water hardening baths and confirms their ability to ensure a more controlled cooling process, reduce the risk of cracks and deformations, and achieve higher hardness of hardened parts.

By achieving the accuracy and roughness requirements imposed on the connecting surfaces of machine components –the topography created during machining – it is guaranteed to meet the operational requirements. We cannot ignore the fact that if connected milled plane surfaces move in different directions relative to each other during operation, there may be different contact conditions caused by the unevenness of the topography. The direction-dependent roughness irregularities and functional characteristics of the topography are not sufficiently explored, thus in this work we examine the roughness and its deviations by assuming displacements in different directions compared to the feed motion during operation. The inhomogeneity of the topography is analyzed with a symmetrical milling setup on a face-milled surface, with profiles measured in plane sections parallel to and in 8 other different directions from the feed. The degree and distribution of deviations of the recorded roughness profiles, the selected amplitude and functional roughness values are examined at several points of the measurement planes.

The use of supercritical water in energy applications is motivated by the aim of increasing the thermal efficiency of power systems. However, structural materials exposed to this environment may undergo corrosive degradation. The objective of this study was to conduct experiments on samples exposed to simulated operational conditions in supercritical water, steam, and air. The material surfaces were sub-sequently analyzed using optical microscopy and scanning electron microscopy coupled with energy-dispersive spectroscopy (SEM/EDS). Particular attention was given to the formation of oxide layers on the nickel-based alloy Inconel 718 produced by additive manufacturing by PBF-SLM technology. The corrosion behavior was evaluated by monitoring mass gains. The results were compared with materials manufactured using conventional techniques.

Corrosive damages can lead to accidents on pipelines in various industries. Therefore, the main objective of the work is to study the peculiarities of the development of internal corrosion at the corners of turns in steel pipes. The paper discusses the development of corrosion. It substantiates the primary importance of the development of corrosion on curved sections of steel pipes. It has been established that, in curvilinear areas, the rate of corrosion development depends on the rate of fluid flow, on the number of ions, and also on the effect of centrifugal force. The authors studied the average rate of corrosion development at the turns of hydraulic structures. Thus, the results obtained showed that the location of steel pipes of hydraulic structures affect the rate of corrosion development from inside the pipes.

A single-stage evaporator with natural circulation was used to densify the plasticizing bath through continuous evaporation and to prepare a solution used in the production of viscose fiber. During the process, sodium calcium sulfate salts were formed, leading to fouling of the heat transfer surfaces in the heat exchangers. This fouling created a layer of deposits that gradually reduced the efficiency of the evaporation process in the evaporator. It was determined that a processing medium with a volumetric flow rate of 6 m³·h⁻¹ required a heat exchanger power of 1448 kW. A fouling layer with a thickness of 0.1 mm reduced the heat exchanger's performance by approximately 40%. When the fouling layer increased to 0.5 mm, the heat exchanger power decreased by nearly 74%, down to 889 kW. The purpose of this paper was to analyze the process parameters of the densification technology in order to identify potential optimisations that could increase equipment availability and reliability. Alternatively, the study aimed to provide recommendations for design modifications to the existing technology.

This article deals with the influence of plasma nitriding and sensitization on the microstructure and microhardness of AISI 304 austenitic steel. The microstructure of AISI 304 austenitic steel in all states was observed on a Neophot 32 optical microscope. The initial structure consisted of polyhedral austenite grains of different sizes. The microstructure contained a large number of non-metallic MnS-based inclu-sions. After plasma nitriding, a continuous nitriding layer was formed under the steel surface, while the grain shape was preserved. After the processes of sensitization and plasma nitriding followed by sensiti-zation, carbides were excluded along the austenitic grain boundaries were excluded. The nitriding layer began to deteriorate due to temperature and length of sensitization. Vickers microhardness measure-ment on a Zwick/Roell ZHμ machine proved that the nitriding layer is reaching the high hardnesses compared to the core of samples. After sensitization, the nitrided samples achieved only slightly in-creased microhardness compared to the core. Finally, EDX analysis of the nitriding layer was performed on the SEM and compared with the layer that was affected by the sensitization process.

In the present work, the microstructure, crystal orientation, mechanical properties and strengthening mechanisms for different regions of WE71 cylindrical parts have been investigated. The results showed that from inner wall to outer wall, second phases density, DRX fraction decreased but average grain size increased, which is well agree with the strain state and metal flow during back extrusion. For compression area, α//ED texture type can be found in region a, but α directions deflects from ED to TD at a certain angle for region b and c. For shear area, α directions deflects from ED to TD about 10°~45°. For stable forming area, the texture is close toα//ND. After peak ageing, a large number of nanometer scaled β' phases were formed and uniformly distributed in the Mg matrix, while zigzag GP zone and RE-hexagons precipitates can also be found in the peak-aged alloy. Tensile properties for region c in compression area are the lowest: UTS, YS and EL are 322 MPa, 215 MPa and 2.5%, respectively. Furthermore, for the stable forming area, the UTS, YS and EL of 283 MPa, 187 MPa and 19% in the region f are the highest, but the strength of region g is the lowest, which is related to the grain size and volume fraction of second phases on flow lines. The strengthening contributes from fine-grain strengthening, texture strengthening and Orowan strengthening.

With the progress of science and technology and the continuous development of robot technology, the performance and intelligence of robots are also constantly improving. It has been widely used in many fields such as life service, military, industrial production and so on. Among them, autonomous mobile is an important embodiment of intelligence. Therefore, it is necessary to solve the problem of robot real-time positioning and map building (SLAM). SLAM is the abbreviation of Simultaneous localization and mapping, which means "synchronous localization and mapping". It is mainly used to solve the problem of localization and mapping when robots move in unknown environments. This paper designs and implements a positioning and navigation system for mobile robots based on lidar in the environment of robot operating system (ROS). The system is based on the gamping algorithm of particle filter, so that robots can perform self-positioning and map building in strange environments. By studying the Rao-Blackwelized particle filter algorithm and enlarging the bandwidth of Kalman filter to increase its estimation accuracy, the filter was optimized. In the process of robot implementation of map construction and autonomous obstacle avoidance, the robot can conduct self-positioning and map building in unfamiliar environments by using the algorithm provided by the open source Gampping function package in the robot operating system (ROS).The navigation function package allows the robot to navigate independently and avoid obstacles with known maps of the environment. Finally, the simulation tool gazebo of the robot operating system (ROS) is used to build the simulation environment required for the experiment and simulate the real environment of the robot. Finally, the robot is equipped with lidar sensors to carry out experimental simulation, so that it can achieve the functions of self-positioning, map building, self-navigation and obstacle avoidance.

The conventional solid-state friction welding process involves imparting a movement to one of them, bringing them closer together so that there is friction from the clamping force. By overcoming the frictional resistance on the surface of the workpieces, work converted into heat is generated. The obtained heat heats the elements to a temperature close to the melting point but not exceeding it. After stopping the movement in relation to each other, the process of pressing the elements with the force P with a greater force causes plasticization of the material and the formation of a flash. In low pressure friction welding, most of the heat required for the joining process comes from the induction coil. This means that two key process parameters such as friction time and contact force are significantly reduce. This affects the course of the process and the end result of the process of joining materials. The shape and size of the flash as well as the size of the heat-affected zone in the weld will change. Among the many advantages of this method of joining metals, one should mention the possibility of welding smaller parts, thin-walled, with complicated geometry, which the friction butt welding process would not be able to cope with. Additionally, there is a possibility of heat treatment. In order to verify the feasibility of the friction welding process with low pressure in industrial conditions, a number of tests presented in this study were carried out, together with the analysis of the results. A number of proposals for the optimization of low-force friction welding with the use of artificial intelligence have also been developed has also been developed. A simpler but less effective solution is application of neural networks. It is possible due to multiple digital recording and process automation parameters with digital recording and process automation This solution approach is not as productive as the proposed hybrid algorithm combining neural networks, fuzzy logic and genetic algorithmsThe hybrid method enables you to take advantages of all three algorithms in the position optimization.

The basic process of acquiring new knowledge is trial/experiment. We can define an experiment as a certain process that we prepare, organize and plan in order to know the object under investigation. Each experiment requires a multifaceted activity associated with professional knowledge, preparation of material security, espe-cially security with measuring devices and measurement methods for determining the correct (objective) measured values. Planning experiments and analyzing the obtained results are important stages in revealing the nature and course of the technological process. With the planned experiment, we try to create such con-ditions that the range of experiments is as small as possible, but the volume and form of information are of the highest quality. The article presents the method of the planned experiment and its use in industrial prac-tice. The mentioned methodology of the planned experiment is applied to the calculation of the mean arith-metic value of the surface roughness Ra depending on the cutting parameters. The advantage of this method is that it increases the accuracy of the obtained results, but mainly reduces the number of performed at-tempts.

The growing use of composite materials in various industries implies the necessity of conducting research on both their manufacture and subsequent machining. One of the main problems in composite machining is the selection of a suitable cutting tool. This study investigates the effect of the geometry and material of a milling cutter on the quality of a milled composite part. A carbon fiber-reinforced epoxy resin matrix composite was tested. Two cutting tools were used: an end mill with PCD inserts with a diameter of 12 mm and the number of teeth of 3 as well as a PCD-coated carbide end mill with a diameter of 12 mm and the number of teeth of 4. Variable technological parameters were used. The quality of the machined surfaces was assessed based on burr height and selected profile roughness parameters. Results showed that for the milling process conducted with the same technological parameters, the surface quality obtained with the 4-tooth PCD-coated carbide tool was higher than that obtained with the 3-tooth tool with PCD inserts.

Selective Laser Sintering (SLS) or sintering of polymer powders is one of the most well-known additive technologies for printing 3D components. The properties of individual polymer powder materials have a significant impact on the quality of the manufactured part. Potential deformation and shrinkage can occur during printing if a significant number of parts are piled on top of one another or are oriented incorrectly, accumulating thermal energy in certain areas. The aforementioned research focuses on an experimental study to investigate the impact of the distribution and orientation of printing samples in the build chamber on the accuracy of dimensions and the surface roughness of PA12 prints. The aim of the study was to examine the impact of model settings during production as well as the effect of individual factors on the properties of manufactured parts, with a focus on ensuring that heat rises evenly from each print without accumulating.

Today's milling cutting tools are produced in various types and shapes for a wide variety of machining processes. Development continues and offers new technological solutions. The design of replaceable milling heads offers a significant cost reduction, as only the worn-out part is replaced instead of the en-tire tool. The tough connection between the tool and the shank achieves stable performance in roughing and finishing milling. Because of the possibility of using different milling inserts, the number of neces-sary tools will also be reduced and the flexibility of using milling tools will increase. The article exam-ines the cutting forces when machining a milling head produced by additive technology and made of Onyx material, which is reinforced with carbon fibre.

The article presents the possibilities of using wavelet transform and fast Fourier analysis (FFT) to evaluate the signal collected during roughness measurement. During the tests, high-density polyeth-ylene was turned using variable cutting parameters. During cutting, the tool feed was changed to ob-tain roughness structures of different types and with varying degrees of anisotropy. The measured roughness profiles were filtered with Daubechies 6 (db6), Morlet and "Mexican Hat" wavelets and examined using Fourier analysis. The research carried out shows how the machining conditions affect the surface condition and the stability of the cutting process under variable machining conditions for high molecular weight polymers. The effectiveness of the continuous wavelet transform (CWT), sup-plemented with data obtained from Fourier analysis, in identifying places and detecting the nature of disturbances in the generated roughness signal is also shown.

Benzoylation treatment represents a promising strategy to enhance adhesion between plant fibres and polymer matrices. This study aims to improve the properties of epoxy composites using benzoylated fibres of Demostachya bipinnata (Darbha). The analysis focuses on the impact of chemical treatment on the physicochemical and mechanical characteristics of the fibres and resulting composites. After retting and alkaline pre-treatment of the fibres, benzoylation using 10 wt% concentrated benzyl chloride is applied to introduce benzene groups, thereby enhancing the density and chemical stability of the fibres. Results highlight increased density (1869 kg.m-3) and enriched crystalline cellulose composition in benzoylated fibres (BDE) compared to untreated fibres (UDE). FTIR analysis confirms significant structural modifications with the introduction of additional carbonyl and carboxyl groups, reinforcing essential interfacial bonds. Mechanical tests reveal 30% higher tensile and flexural strength for epoxy/BDE composites compared to epoxy/UDE composites, demonstrating the effec-tiveness of benzoylation in improving mechanical properties. Thermal analysis also shows improved thermal stability of BDE fibres, crucial for demanding industrial applications. In summary, this study demonstrates significant enhancement in performance of benzoylated Darbha fibres as composite reinforcements, opening new avenues for their use in sectors such as automotive and construction, where high mechanical strength is crucial.

The cutting performance of abrasive water jet (AWJ) machining is commonly evaluated using cutting depth, cutting efficiency, and specific cutting energy. To systematically investigate the influence of process parameters on AWJ cutting performance, a five-axis CNC cutting platform was developed, allowing precise control of operating conditions. Single-factor experiments were conducted to analyze the effects of pump pressure, traverse speed, cutting angle, abrasive mass flow rate, standoff distance, and nozzle diameter. Both qualitative analysis and quantitative evaluation were employed to identify parameter ranges that maximize cutting efficiency or minimize specific cutting energy. The results indicate that the minimum specific cutting energy is achieved when the pump pressure is approximately three times the threshold pressure, the traverse speed is 110 mm/min, the cutting angle is 90°, and the abrasive mass flow rate approaches its optimal value. The effects of standoff distance and nozzle diameter on specific energy depend on their combined influence on cutting depth and kerf width. In addition, repeated cutting passes were found to increase energy consumption, indicating that complete material penetration in a single pass is more energy-efficient. These findings provide practical guidance and theoretical support for achieving high-efficiency and energy-saving AWJ cutting processes.

The optimization of process parameters plays a critical role in controlling temperature and velocity fields during centrifugal casting, which is essential for mitigating shrinkage porosity defects caused by uneven cooling in thick walled bearing alloy layers. In this study, two sequential numerical models were devel-oped using ProCAST software to simulate gravity filling and centrifugal solidification stages. The effects of key parameters, including inlet cross-sectional area and centrifugal rotational speed, on flow field characteristics were systematically analyzed. By using an orthogonal experimental design, we deter-mined the optimal parameters: a melt temperature of 440 °C for the Babbitt alloy, an initial temperature of 280 °C for the bearing blank, a filling inlet diameter of 16 mm, and a rotational speed of 340 r/min. Bearing alloy layers manufactured according to these optimized parameters exhibit no evident shrinkage or cracks on their surfaces. The high quality finished products meet the design requirements, thereby validating the accuracy of the numerical simulation.

This article presents the research findings on the flow behaviour of thermoplastic resin in foam core sandwich composites for aerospace applications during the vacuum assisted infusion process. After optimizing the process parameters, two sandwich panels were manufactured using glass fibre fabrics, a polymethacrylimide (PMI) foam core, and a liquid acrylic resin. To compare the sandwich and monolithic structure process behaviour, a monolithic composite panel was also manufactured. By combining experimental monitoring with Darcy's law, permeability differences between the structures were evaluated. The results indicate that PMI foam does not significantly affect the resin flow trend, and that Darcy´s law can be applied to both monolithic and sandwich structures when a thermoplastic liquid resin is used. These findings offer theoretical guidance for process parameter design and real-time in situ monitoring of the vacuum infusion process.

Investigation of cutting forces in metal cutting is of great importance for defining the effectiveness of the production as well as its impact on product quality. Several researchers studied the effect of cutting parameters on the cutting forces through statistical analysis; however, very few studies use the normalization of the data. Normalization reduces the skewness in the data and increases the accuracy of the results, which can be beneficial in modern industry where AI is being integrated with manufacturing. This research aimed to study the statistical analysis of cutting parameters and cutting forces using log-normalization and compare the accuracy of results with absolute data. The study uses a three-axis piezoelectric dynamometer to measure the cutting forces in the turning of X5CrNi18-10 steel. The results suggested that feed influences the cutting forces during machining. Coolant helps to reduce the cutting forces during the turning of hard steel. Log-normalization increases the accuracy of the results. These results can be used to predict cutting forces during the turning of chromium-nickel alloy steel.

In order to reveal the action mechanism of different brass solder compositions on the microstructure of weld joints in unleaded-tin-coated coppers brazing-stitch welding, the laser welding process of solar panel busbar was studied by using three different coated brass solders: Sn-37Bi-3Ag, Sn-42Bi-3Ag and Sn-47Bi-3Ag. Scanning electron microscope, energy spectrometer, X-ray diffractometer, tensile testing machine and Vickers microhardness tester were used to test and analyze the influence of Bi element content on the microstructure and mechanical properties of weld joints in solar panel busbar brazing-stitch welding. The results show that: (1) With the increase of Bi element content, the wettability of soldering ceam is gradually improved, and the weld joints eutectic mainly consists of SnAg phase, Ag3Sn phase, Cu6Sn5 phase, Cu3Sn phase, SnAgCu phase, β-Sn sosoloid and Bi with rhombic layered structure. (2) The fracture of weld joints occurred at the interconnection belt side, it presents brittle and ductile mixed fracture. With the decrease of Bi element content, the tensile strength of weld joints gradually increased, and the maximum tensile strength of weld joints was 212 MPa. (3) The of weld joints decreases gradually from the busbar side to the interconnection belt side, and the highest microhardness of weld joints appears at the interface layer, it can reach 330.1 HV. With the decrease of Bi element content, the microhardness of weld joints gradually increased. This paper provides a scientific basis for the optimal selection and use of busbars in solar panels high-quality laser welding.

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 normalizing annealing process inadequate. Thus, an optimized double annealing process was adopted, controlling cracks and raising the yield rate to over 85%. This research offers theoretical and technological support for rolling high-silicon electrical steels like 35W210X.

In response to the problems of insufficient strength and stiffness, as well as large weight in traditional car frames, this article takes titanium alloy frames as the research object. Based on the analysis of static and dynamic characteristics, a lightweight design is carried out to meet the design requirements. Firstly, static analysis was conducted on the frame structure under four different working conditions using the finite element analysis method to study its stress distribution and deformation under different loads and road conditions. Study the natural frequency and vibration mode of the frame through modal analysis, providing a basis for subsequent optimization design. Through harmonic response analysis, explore the changes in the amplitude and frequency of the frame during use. On this basis, topology optimization and lightweight design are carried out on the frame structure to reduce the weight of the frame and improve its strength and stiffness. Finally, validate and compare the optimized frame to explore the feasibility and superiority of the optimization plan. The research results show that the optimized frame weight has been reduced by 13.76%, the maximum stress has been reduced by 5.19%, and the maximum deformation has been reduced by 0.37%, effectively reducing the frame mass. This provides a way of thinking about the static and dynamic characteristics analysis and topology optimization design of automotive frames.

Today, machine learning regression methods are quietly but fundamentally transforming cost and time estimation in manufacturing: from early pricing to labor planning to operational order management. This survey offers a comprehensive map of approaches - from linear models, to tree ensembles (RF, GBM, XGBoost) and shallow neural networks, to multi-target and tensor regressions that can exploit data structure across BOM items and sequences of operations. With an emphasis on SME conditions, we show how to reconcile three often conflicting requirements of practice: accuracy, explainability, and integration into existing data flows (MES/ERP). The paper presents a comparative taxonomy of methods, recommended validation practices (MAE, RMSE, MAPE, R² including confidence intervals) and a pragmatic adoption trajectory: from regularized multiple regressions to tree models to multi-output formulations sharing re-presentations across operations. Consolidated findings show that modern learners consistently outperform traditional baselines when supported by careful flag engineering, drift management, and data standardization. As a major research-application contribution, we propose a unified multi-objective framework for simultaneous cost and time prediction that combines domain (queueing/simulation) features with data-driven regression to enable transparent decision making in pricing and capacity planning. The study thus creates a bridge between theory and manufacturing practice and invites the reader to systematically but achievably deploy ML in everyday decision making.

This study experimentally compares how three common machining routes, turning, milling and grinding, affect the surface texture and tribological response of three structural steels (C45, 42CrMo4, 30CrMoV9) under conditions where the profile roughness Ra is deliberately aligned across routes. Areal topography was measured by coherence correlation interferometry and evaluated according to ISO 25178 (height metrics Sa, Sq, Sp, Sv, Sz, St). The bearing area curve (Abbott–Firestone) was used to derive functional descriptors Rpk, Rk and Rvk. Scratch resistance was determined on a UMT‑3 tribometer (Rockwell 120°, P = 50 N) as HSp = 8·P / w² in accordance with ASTM G171. The results show that surfaces with comparable Ra can differ markedly in areal extremes and BAC‑derived parameters, which is reflected in scratch response. These findings support replacing sole Ra specification with areal and bearing‑curve descriptors when functional performance is critical (friction, sealing, wear).

At the present time, mechanical vibration is undesirable in many cases. Therefore it is necessary to minimize unwanted vibrations in any appropriate manner. This paper is focused on a study of factors influencing vibration damping properties that were investigated using multilayer composite structures. Frequency dependencies of the displacement transmissibility over a frequency range of 2?1500 Hz were determined by the method of forced oscillations. It was found in this study that the vibration damping properties of investigated multilayer structures are significantly influenced by number of material layers, excitation frequency of mechanical vibration, applied materials in multilayer structures, inertial mass, material thickness and density. It was also observed that a superior ability to damp mechanical vibration leads to a shift of the first resonance frequency peak position to lower excitation frequencies.