Evaluation of wear resistance and surface properties of additively manufactured restorative dental materials.

OBJECTIVES: To evaluate the wear resistance of three additively manufactured dental crown materials (NextDent C&B MFH, Saremco print CROWNTEC and Bego VarseoSmile Crown) under two environmental conditions (dry and artificial saliva), two loads (49 N and 70 N) and two surface treatments (polished and glazed). METHODS: A total of 120 specimens were divided into 24 groups and tested for wear under two loads (49 N and 70 N), surface treatment (polished or glazed), and environment (dry or submerged in artificial saliva). All samples underwent reciprocating wear testing at 1 Hz using a wear simulator, replicating 48 months of In Vivo conditions with a stainless-steel ball as the antagonist. The coefficient of friction (CoF), surface roughness, volumetric and vertical wear loss were measured and statistically analysed. Confocal microscopy assessed the surface properties of crown materials and the antagonists. RESULTS: The NextDent material demonstrated the most homogenous wear, with relatively low vertical and volumetric loss across all groups (p < 0.004). NextDent and Bego materials performed similarly in artificial saliva regardless of the load type (p > 1.000). The CoF remained below 0.3 for all groups. All groups exhibited significant increases in surface roughness after testing, however, this did not correlate with an increase in the CoF. Confocal analysis revealed material deformities due to load and notable scratch marks on the stainless-steel antagonists. CONCLUSION: It was found that all investigated addtively manufactured materials can be suggested for provisional use. Both vertical loss and volumetric loss results should be included for material evaluation. CoF and surface roughness should be implemented into wear evaluation. CLINICAL SIGNIFICANCE: This study highlights the practical value of additively manufactured dental crown materials, particularly for provisional restorations. However, their extended use requires careful consideration of individual patient needs, emphasising the need for judicious clinical application evaluation.

Effect of Zonal Laser Texturing on Friction Reduction of Steel Elements in Lubricated Reciprocating Motion.

During co-action between contact elements in reciprocating motion, different working conditions exist in outer and inner zones of stationary elements. Because the tribological effects of surface texturing depend on the operating conditions, various dimple patterns were created in the middle part of the steel disc and near the reversal points. The behaviors of variable dimple patterns were compared with those of uniform texturing and untexturing. It was found that the dimple patterns in the middle disc zone depended on the resistance to motion. The best tribological behavior was obtained for a pit area ratio of 13% and diameter of 0.4 mm in the inner zone, and pit area ratio of 3% and diameter of 0.2 mm in the outer zones. Low resistance to motion and the smallest friction variation of all tested sliding pairs were achieved. For the same pit area ratio of 13% in a disc of 0.4 mm, the dimple diameter behaved better than in the 0.2 mm diameter disc. The greatest decrease in the coefficient of friction of 85% compared to untextured sliding pair was achieved for uniform laser texturing with a pit area ratio of 13% and dimple diameter of 0.4 mm, when the normal load was 40 N and frequency of displacement was 20 Hz.

Method for Determining the Coefficient of Friction Variation Pattern as a Function of Density at Low Temperatures Using the Example of Dry Ice-Steel Contact.

The developments in manufacturing technologies are expected to reduce energy input without compromising product quality. Regarding the material densification process, numerical simulation methods are applied to achieve this goal. In this case, relevant material models are built using functions that describe the variation in mechanical parameters of the material in question due to its deformation. The literature review conducted for this research has revealed a shortage of experimental research methods allowing a determination of the coefficient of friction at low temperatures, approximately 200 K. This article proposes a method for determining the friction coefficient of dry ice sliding against steel. The experimental results were analysed to obtain several functions describing the variation in the coefficient of friction. These functions were then compared using goodness-of-fit indexes. Finally, two functions with similar goodness-of-fit values were chosen. The findings of this research project will complement the already available information and may be used in various research and implementation projects related to the development or improvement of currently used crystallised carbon dioxide conversion processes.

Tribological properties of MAO ceramic coatings with annulus array texture on disposable surgical gloves.

Introduction: In recent research, the expansion in the use of Mg alloys for biomedical applications has been approached by modifying their surfaces in conjunction with micro-arc oxidation (MAO) techniques which enhance their abrasion and corrosion resistance. Methods: In this study, combining laser texturing and MAO techniques to produce the dense ceramic coatings with microstructures. On the surface of the AZ31 Mg alloy, a micro-raised annulus array texture has been designed in order to increase the surface friction under liquid lubrication and to improve the operator's grip when holding the tool. For this work, the micro-morphology of the coatings was characterised, and the friction properties of the commonly used scalpel shank material 316 L, the untextured surface and the textured surface were comparatively analysed against disposable surgical gloves. Results and discussion: The results show that the Laser-MAO ceramic coating grows homogenous, the porosity decreases from 14.3% to 7.8%, and the morphology after friction indicates that the coating has good wear resistance. More specifically, the average coefficient of friction (COF) of the three types of gloves coated with Laser-MAO ceramic was higher than that of the 316 L and MAO ceramic coatings under the action of the annulus-integrated texture under the lubrication conditions of physiological saline and defatted sheep blood, which achieved the goal of increasing friction for the purpose of helping to prevent the problem of tool slippage from the hand.

Study on the evaluation method of cigarette astringency in the simulated oral environment.

Cigarettes with pronounced astringency can diminish consumers' enjoyment. However, due to the complex composition of cigarettes, quantifying astringency intensity accurately has been challenging. To address this, research was conducted to develop a method for assessing astringency intensity in a simulated oral environment. The astringency intensity of four cigarette brands was determined using the standard sensory evaluation method. The mainstream smoke absorbing solution (MS) was prepared by simulating the cigarette smoking process, and its physicochemical properties (such as total phenol content and pH levels) were analyzed. The lubrication properties of the five solutions were tested using the MFT-5000 wear tester, and factors influencing cigarette astringency were examined. The findings showed that total phenol content and pH of MS were positively and negatively correlated with astringency intensity, respectively. Particularly, the lubrication properties of MS were significantly correlated with astringency intensity, and the correlation coefficient was affected by load and speed during testing. The study concluded that coefficient of friction was a more reliable measure for assessing the extent of astringency in cigarettes than the total phenol content and pH of MS, offering new insights into astringency evaluation and development of high-grade cigarettes.

Exploring prosthetic screw rupture in titanium and zirconia superstructures under various conditions.

The fastening mechanics of prosthetic screws under various conditions is crucial to the maintenance of dental implants. This study comprehensively explores the prosthetic screw rupture in titanium (Ti) and zirconia (ZrO2) superstructures under wet and dry conditions. Superstructures were fabricated using digital technology and subjected to tightening torque trials. Experimental results suggested that the implications of the conventionally recommended torque of 15 N•cm differ significantly between dry and wet environments. Both Ti and ZrO2 exhibited preloads of >30 N•cm under dry conditions; however, differences emerged under wet conditions. In addition, screw rupture posed a prominent clinical challenge -particularly during long-term cyclic loading. Notably, the ZrO2 superstructures exhibited a greater resistance to breaking torque than that of Ti. This study underscores the importance of reevaluating torque recommendations with consideration to the distinct characteristics of Ti and ZrO2 in diverse environments.

The Influence of Q & T Heat Treatment on the Change of Tribological Properties of Powder Tool Steels ASP2017, ASP2055 and Their Comparison with Steel X153CrMoV12.

In connection with the growing importance of the efficiency and reliability of tools in industrial sectors, our research represents a key step in the effort to optimize production processes and increase their service life in real conditions. The study deals with the comparison of the tribological properties of three tool steels, two of which were produced by the powder metallurgy method-ASP2017 and ASP2055-and the last tool steel underwent the conventional production method-X153CrMoV12. The samples were mechanically machined with the finishing technology of turning and, finally, heat treated (Q + T). The study focused on the evaluation of hardness, resulting microstructure, wear resistance, and coefficient of friction (COF). The ball-on-disc method was chosen as part of the COF and wear resistance test. The tribological test took place at room temperature with dry friction to accelerate surface wear. The pressing material was a hardened steel ball G40 (DIN 100Cr6). Measurements were performed at loads of 10 N, 6 N, and 2 N and turning radii of 13 mm, 18 mm, and 23 mm, which represents a peripheral speed of 0.34, 0.47, and 0.60 m/s. The duration of the measurement for each sample was 20 min. The results showed that the COF of powder steels showed almost the same values, while a significant difference occurred with the increase of the radius rotation in the case of conventional steel. The results within the friction mechanism showed two types of wear, namely, adhesive and abrasive wear, depending on the Q + T process. From a tribological point of view in terms of wear, it was possible to state that the material ASP2055 after Q + T showed the lowest rate of wear of all the tested steels.

Machine learning prediction of footwear slip resistance on glycerol-contaminated surfaces: A pilot study.

Slippery surfaces due to oil spills pose a significant risk in various environments, including industrial workplaces, kitchens, garages, and outdoor areas. These situations can lead to accidents and falls, resulting in injuries that range from minor bruises to severe fractures or head trauma. To mitigate such risks, the use of slip resistant footwear plays a crucial role. In this study, we aimed to develop an Artificial Intelligence model capable of classifying footwear as having either high or low slip resistance based on the geometric characteristics and material parameters of their outsoles. Our model was trained on a unique dataset comprising images of 37 indoor work footwear outsoles made of rubber. To evaluate the slip resistant property of the footwear, all samples were tested using a cart-type friction measurement device, and the static and dynamic Coefficient of Frictions (COFs) of each outsole was determined on a glycerol-contaminated surface. Machine learning techniques were implemented, and a classification model was developed to determine high and low slip resistant footwear. Among the various models evaluated, the Support Vector Classifier (SVC) obtained the best results. This model achieved an accuracy of 0.68 ± 0.15 and an F1-score of 0.68 ± 0.20. Our results indicate that the proposed model effectively yet modestly identified outsoles with high and low slip resistance. This model is the first step in developing a model that footwear manufacturers can utilize to enhance product quality and reduce slip and fall incidents.

Sandwich hydrogel to realize cartilage-mimetic structures and performances from polyvinyl alcohol, chitosan and sodium hyaluronate.

Developing artificial substitutes that mimic the structures and performances of natural cartilage is of great importance. However, it is challenging to integrate the high strength, excellent biocompatibility, low coefficient of friction, long-term wear resistance, outstanding swelling resistance, and osseointegration potential into one material. Herein, a sandwich hydrogel with cartilage-mimetic structures and performances was prepared to achieve this goal. The precursor hydrogel was obtained by freezing-thawing the mixture of poly vinyl alcohol, chitosan and deionized water three cycles, accompanied by soaking in sodium hyaluronate solution. The top of the precursor hydrogel was hydrophobically modified with lauroyl chloride and then loaded with lecithin, while the bottom was mineralized with hydroxyapatite. Due to the multiple linkages (crystalline domains, hydrogen bonds, and ionic interactions), the compressive stress was 71 MPa. Owing to the synergy of the hydrophobic modification and lecithin, the coefficient of friction was 0.01. Additionally, no wear trace was observed after 50,000 wear cycles. Remarkably, hydroxyapatite enabled the hydrogel osseointegration potential. The swelling ratio of the hydrogel was 0.06 g/g after soaking in simulated synovial fluid for 7 days. Since raw materials were non-toxic, the cell viability was 100 %. All of the above merits make it an ideal material for cartilage replacement.

Fabrication of a novel aesthetic orthodontic bracket and evaluation of friction properties between PEEK and stainless steel wires.

BACKGROUND: Polyetheretherketone (PEEK) is a polyaromatic semi-crystalline thermoplastic polymer with mechanical and lubrication properties favorable for biomedical applications. Despite of its aesthetic appearance, ceramic brackets are unsatisfactory in brittleness and thickness, while PEEK is a potential material for aesthetic orthodontic brackets. OBJECTIVE: To fabricate a novel aesthetic orthodontic bracket and evaluate friction properties of PEEK and stainless steel wires. METHODS: All polyether ether ketone (PEEK) and ceramic samples disks were made into disks (diameter, 5 mm; thickness, 2 mm). The tested surfaces of PEEK were ground with #600, #800 and #1200 SiC papers, followed by polishing with Sof-Lex kit (3M ESPE, USA). The surface roughness was tested using a laser profilometer device (VK-X200, Keyence, Japan). The COFs of the specimens and stainless steel (SS) archwires were tested using a Universal Micro-Tribotester (UMT-3, Bruker, USA). The wear scratches on the materials' surfaces were examined by using a scanning electron microscope (SEM) (Hitachi SU8010). The elastic modulus and hardness of samples were examined with a nano-indenter (XP, Keysight Technologies, USA). RESULTS: The mean surface roughness of PEEK and Ceramic are 0.320 ± 0.028 µm and 0.343 ± 0.044 µm, respectively. PEEK has a lower Friction coefficient than Ceramic and the difference between the two groups was statistically significant (P< 0.05). The abrasive wear of Ceramic was the main wear style and was characterized by the observation of chipping fractures, while PEEK surface looked smooth without obvious scale-like desquamations and granular debris, indicating adhesive wear. CONCLUSION: Within the limitations of the present study, PEEK shows lower coefficient of friction than ceramic. PEEK has excellent properties such as low friction coefficient, smooth surface and good mechanical properties, and thus meets the requirements for orthodontic brackets. It is considered as a potential bracket material with both low friction and aesthetic performance.

The Effect of Sliding Speed on the Tribological Properties of Ceramic Materials.

Ceramics are considered to be candidate materials for galvanising pot bearing materials due to their excellent corrosion resistance in many molten metals. Galvanising pot roll bearings must have excellent wear resistance, and, therefore, it is important to understand the wear behaviour of prospective bearing materials. This study investigates the friction- and wear-resistant properties of select ceramics, namely, pure hBN, BN M26, AlN-BN, Macor, 3YSZ, Al2O3 and Si3N4. The ceramics were tested at different sliding speeds using a pin-on-disc device equipped with SiC pins. The lowest coefficient of friction (COF) achieved was below 0.1, and it was measured for pure hBN at a 3.14 m/min sliding speed. However, a wear scar analysis showed that the BN grades suffered from severe wear. The highest wear rate was obtained for BN M26 at a 9.42 m/min sliding speed and was equal to 17.1 × 10-6 mm3 N-1 m-1. It was shown that the wear coefficient of the tested ceramics varied exponentially with hardness. The lowest wear was observed on the 3YSZ, Al2O3 and Si3N4 ceramics, which showed no volume loss, and, for this reason, they can be potentially used as bearing materials in continuous galvanising lines.

Potential and Design Parameters of Polyvinylidene Fluoride in Gear Applications.

(1) Background: With the ever-increasing number of polymer materials and limited data on polymer gear calculations, designers are often required to perform extensive experimental testing in order to establish reliable operational data for specific gear applications. This research investigates the potential of a Polyvinyldene fluoride (PVDF) polymer material in gear applications, considering various loading conditions and different types of gear transmission configurations, including both self-mated mesh and steel/PVDF mesh. (2) Methods: PVDF gear samples were tested on a specially designed test rig that enables active torque control and temperature monitoring in order to obtain the necessary design parameters and failure modes. Each test for certain load conditions was repeated five times, and to fully investigate the potential of PVDF gear samples, comparative testing was performed for Polyoxymethylene (POM) gear. (3) Results: Tribological compatibility, tooth load capacity, and lifespan assessment, along with the types of failure, which, for some configurations, include several types of failures, such as wear and melting, were determined. Temperature monitoring data were used to estimate the coefficient of friction at the tooth contact of analyzed gear pairs, while optical methods were used to determine a wear coefficient. (4) Conclusions: The tribological compatibility of polymer gear pairs needs to be established in order to design a gear pair for a specific application. PVDF gear samples mated with steel gear showed similar lifespan properties compared to POM samples. Temperature monitoring and optical methods serve as a basis for the determination of the design parameters. PVDF is an appropriate material to use in gear applications, considering its comparable properties with POM. The particular significance of this research is reflected in the establishment of the design parameters of PVDF gear, as well as in the analysis of the potential of the PVDF material in gear applications, which gives exceptional significance to the current knowledge on polymer gears, considering that the PVDF material has not previously been analyzed in gear applications.

Tribological Performance of Anti-Wear Coatings on Tools for Forming Aluminium Alloy Sheets Used for Producing Pull-Off Caps.

Ensuring adequate reliability of the production process of packaging closures has made it necessary to study the effect of annealing and varnishing variants on the strength and structural properties of the stock material. As a test material, EN AW-5052-H28 aluminium alloy sheets with a thickness of 0.21 mm were used. The surface treatment of the test material involved varnishing the sheet metal surface using various varnishes and soaking the sheet metal. The coefficient of friction and the abrasion resistance of the coatings were determined using the T-21 ball-and-disc tribotester. The tested sheets were subjected to tribological analysis by the T-05 roller-block tribotester using countersamples made of Caldie and Sverker 21 tool steels. The results of the tests showed differences in mechanical and structural properties depending on the method of sample preparation. Based on the test results, significant differences in the adhesion of anti-wear coatings were found. The results revealed that the most favourable friction conditions are provided by the CrN coating. The (AlTi)N interlayer in the (AlTi)N/(AlCr)N coating adheres to the substrate over the entire tested area and no detachment from its surface was observed, which proves good bonding at the substrate/coating interface. The tested AlTiN/TiAlSiXN coating is characterised by a more homogeneous, compact microstructure compared to the (AlTi)N/(AlCr)N coating.

Tribological Characterisation and Modelling for the Fused Deposition Modelling of Polymeric Structures under Lubrication Conditions.

In recent years, additive manufacturing technology, particularly in plastic component fabrication, has gained prominence. However, fundamental modelling of the influence of materials like ABS, PC, and PLA on tribological properties in fused deposition modeling (FDM) remains scarce, particularly in non-lubricated, oil-lubricated, and grease-lubricated modes. This experimental study systematically investigates the effects of material type, lubrication method, layer thickness, and infill density on FDM component tribology. A tribology analysis is conducted using a TRB3 tribometer. The results indicate a coefficient of friction (CoF) range between 0.04 and 0.2, generally increasing and decreasing with layer thickness and filler density. The lubrication impact hinges on the material surface texture. The study models the intricate relationships between these variables via full-factor analysis, showing a strong alignment between the modelled and measured friction coefficients (an average error of 3.83%). Validation tests on different materials affirm the model's reliability and applicability.

Design and manufacture of one-size-fits-all healthcare face shields for the NHS during the COVID-19 pandemic.

During the COVID-19 pandemic, there was a shortage of personal protective equipment, PPE, which resulted in non-certified PPE being used by healthcare staffs. These would not provide the appropriate protection against the SARS-CoV-2 virus. Together with the local NHS Trust (University Hospitals of Derby and Burton (UHDB) NHS Foundation Trust) and a local small and medium enterprise (SME), Riverside Medical Packaging Ltd, the University of Derby (UoD) developed test protocols for PPE with a one-size-fits-all concept. Building on best practice in reviewing the literature and current design requirements, key design parameters were identified such as a minimum strap width and comfort level for healthcare related Face Shield. Two strap headbands made from fabric and elastomer with linear stiffness of 44.1 ± 0.3 N/m and 149.1 ± 3.1 N/m respectively were tested with respect to fit and comfort on small and large arc-shaped models. There was an exponential change in pressure from the side to the middle of the strap headbands. The high stiffness of the elastomer in a radial set-up influenced the pressure exerted on a wearer's head when the elastomer strap was used. Meanwhile the coefficient of friction between the fabric strap and arc-shaped model influenced the pressure exerted when a fabric strap was used. The ergonomics of the designed Face Shields supported the one-size-fits-all concept, whereby various gender and head circumferences were considered. The findings in this paper will promote new standards in the design of PPE with a one-size-fits-all target.

Mechanical, tribological, and surface morphological studies on the effects of hybrid ilmenite and silicon dioxide fillers on glass fibre reinforced epoxy composites.

Recently, researchers have been attempting to enhance the mechanical and tribological characteristics of thermosetting epoxy composites by incorporating inorganic nanoparticles and ensuring their uniform distribution throughout the matrix. This study characterises ball-milled ilmenite (FeTiO3-size of 63 nm) and silicon dioxide (SiO2-size of 67.5 nm) fillers added to epoxy in proportions of 0:0, 2.5:2.5, 5:5, and 7.5:7.5% by weight. A liquid ultrasonic technique is used to blend the fillers with the epoxy, and compression moulding is used to fabricate the composite. Mechanical tests were performed based on ASTM standards. Tensile strength, tensile modulus, flexural strength, flexural modulus and elongations at break(tensile and flexural test) of 5:5 wt % are 30.54%, 12.2%, 32.22%, 28.98%,23.78% and 23.53% higher than neat sample respectively. Shore "D" hardness and Izod's impact strength are 4.65% and 98.93% higher at 5:5 wt % than neat sample respectively. Specific wear rate decreased from 2.6 × 10-11 m3/Nm (neat GFRP: 0 wt % glass fibre reinforced polymer composite) to 0.7 × 10-11 m3/Nm at 5:5 wt % filler. Nanoparticles lowered the coefficient of friction by around 16.66%, 60.42%, and 33.33% at sliding distances of 100 m for 2.5:2.5, 5:5, and 7.5:7.5 wt % respectively with the neat sample. A 5:5 wt percent resulted in 76.68% less wear volume loss than pure GFRP. Field emission scanning electron microscopy (FESEM) analysis revealed element distributions, particle size, pullout of fibers, damaged interfaces, filler dispersion, voids, wear debris, interfacial debonding, and cavities. Thus, this approach enhances GFRP composite's mechanical, tribological, and structural properties.

Open-Cell AlSn6Cu-SiC Composites: Fabrication, Dry-Sliding Wear Behavior, and Machine Learning Methods for Wear Prediction.

Open-cell AMMCs are high-strength and lightweight materials with applications in different types of industries. However, one of the main goals in using these materials is to enhance their tribological behavior, which improves their durability and performance under frictional conditions. This study presents an approach for fabricating and predicting the wear behavior of open-cell AlSn6Cu-SiC composites, which are a type of porous AMMCs with improved tribological properties. The composites were fabricated using liquid-state processing, and their tribological properties are investigated by the pin-on-disk method under different loads (50 N and 100 N) and with dry-sliding friction. The microstructure and phase composition of the composites were investigated by scanning electron microscopy, energy-dispersive X-ray spectroscopy, and X-ray diffraction. The mass wear and coefficient of friction (COF) of the materials were measured as quantitative indicators of their tribological behavior. The results showed that the open-cell AlSn6Cu-SiC composite had an enhanced tribological behavior compared to the open-cell AlSn6Cu material in terms of mass wear (38% decrease at 50 N and 31% decrease at 100 N) while maintaining the COF at the same level. The COF of the composites was predicted by six different machine learning methods based on the experimental data. The performance of these models was evaluated by various metrics (R2, MSE, RMSE, and MAE) on the validation and test sets. Based on the results, the open-cell AlSn6Cu-SiC composite outperformed the open-cell AlSn6Cu material in terms of mass loss under different loads with similar COF values. The ML models that were used can predict the COF accurately and reliably based on features, but they are affected by data quality and quantity, overfitting or underfitting, and load change.

Skin Friction: Mechanical and Tribological Characterization of Different Papers Used in Everyday Life.

The coefficient of friction for different contacting materials against skin is mainly influenced by the nature of the materials (synthetic and natural fabrics), mechanical contact parameters (interfacial pressure and sliding velocities), and physiological skin conditions (ambient humidity and skin moisture content). In the present research work, seven different types of papers used in everyday life were analyzed. The physical properties of these materials were determined through tensile tests and friction tests. By comparing mechanical properties with coefficient of friction, it was possible to conclude that the coefficient of friction is strongly correlated with the mechanical properties.

Data on the coefficient of friction and its prediction by a machine learning model as a function of time for open-cell AlSi10Mg-Al2O3 composites with different porosity tested by pin-on-disk method.

This data article presents the experimental data of the wear behavior of four types of open-cell AlSi10Mg materials and open-cell AlSi10Mg-Al2O3 composites with different pore sizes under dry sliding conditions tested by pin-on-disk method. The data include the coefficient of friction (COF) as a function of time for each material, as well as the predictions of COF using a machine learning model - Extreme Gradient Boosting. The data were generated to investigate the effect of pore size and reinforcement on the friction and wear properties of open-cell AlSi10Mg-Al2O3 composites, which are promising materials for lightweight and wear-resistant applications. The data can also be used to validate theoretical models or numerical simulations of wear mechanisms in porous materials, as well as to optimize the material design and processing parameters to enhance the wear resistance of open-cell AlSi10Mg materials. The data are available in DWF and XLSX format and can be opened by any text editor or spreadsheet software. The data article is related to an original research article entitled "Production and Tribological Characterization of Advanced Open-Cell AlSi10Mg-Al2O3 Composites", where the details of the experimental methods, the microstructural characterization, and the analysis of the wear mechanisms are provided [1].

Analysis of the Frictional Performance of AW-5251 Aluminium Alloy Sheets Using the Random Forest Machine Learning Algorithm and Multilayer Perceptron.

This paper is devoted to the determination of the coefficient of friction (COF) in the drawbead region in metal forming processes. As the test material, AW-5251 aluminium alloys sheets fabricated under various hardening conditions (AW-5251-O, AW-5251-H14, AW-5251-H16 and AW-5251H22) were used. The sheets were tested using a drawbead simulator with different countersample roughness and different orientations of the specimens in relation to the sheet rolling direction. A drawbead simulator was designed to model the friction conditions when the sheet metal passed through the drawbead in sheet metal forming. The experimental tests were carried out under conditions of dry friction and lubrication of the sheet metal surfaces with three lubricants: machine oil, hydraulic oil, and engine oil. Based on the results of the experimental tests, the value of the COF was determined. The Random Forest (RF) machine learning algorithm and artificial neural networks (ANNs) were used to identify the parameters affecting the COF. The R statistical package software version 4.1.0 was used for running the RF model and neural network. The relative importance of the inputs was analysed using 12 different activation functions in ANNs and nine different loss functions in the RF. Based on the experimental tests, it was concluded that the COF for samples cut along the sheet rolling direction was greater than for samples cut in the transverse direction. However, the COF's most relevant input was oil viscosity (0.59), followed by the average counter sample roughness Ra (0.30) and the yield stress Rp0.2 and strength coefficient K (0.05 and 0.06, respectively). The hard sigmoid activation function had the poorest R2 (0.25) and nRMSE (0.30). The ideal run was found after training and testing the RF model (R2 = 0.90 ± 0.028). Ra values greater than 1.1 and Rp0.2 values between 105 and 190 resulted in a decreased COF. The COF values dropped to 9-35 for viscosity and 105-190 for Rp0.2, with a gap between 110 and 130 when the oil viscosity was added. The COF was low when the oil viscosity was 9-35, and the Ra was 0.95-1.25. The interaction between K and the other inputs, which produces a relatively limited range of reduced COF values, was the least relevant. The COF was reduced by setting the Rp0.2 between 105 and 190, the Ra between 0.95 and 1.25, and the oil viscosity between 9 and 35.