“…The ANN predictions for the wear coefficient are shown in Figure 5 by the solid lines together with the estimates (dashed lines) extracted from the regression model (15). Figure 4.Comparison of measured data 28 and ANN-predicted trends for the wear mass loss versus the sliding distance for the two values of the applied load L = 20 N (a) and L = 40 N (b) for different values of the percentage concentration of reinforcement.Figure 5.Predictions of the linear regression model (dashed lines), the ANN model (solid lines), and the SWR-based approximations (dot symbols) for the wear coefficient as a function of the sliding distance for the two values of the applied load L = 20 N (a) and L = 40 N (b) for different values of the mass percentage of zirconia reinforcement.…”
Section: Validation Of the Ann Modeling Approachmentioning
confidence: 97%
“…Figure 6 shows our predictions for the true wear coefficient (evaluated at s = 600 m) as a function of the zirconia mass percentage obtained from the experimental data. 28 It is interesting to observe that the wear coefficient decreases with increasing contact load. This fact implies that the Archard–Kragelsky model, which assumes the power-law dependence of the wear rate w· on the contact pressure p seems to be more appropriate than Archard's equation (1).…”
Section: Validation Of the Ann Modeling Approachmentioning
confidence: 98%
“…In their 24 pin-on-disk tests, Arif et al 28 considered aluminum hybrid composites reinforced with micro-SiC (5 wt%) and nano-zirconia (0, 3, 6, and 9 wt%) under two levels of applied load L (20 and 40 N) and for three values of sliding distance s (300, 600, and 900 m). Using the ANN modeling and linear regression method, the following relation for the wear mass loss m (mg) was established 28 m ¼ À3:50417 þ 0:047z% þ 0:010s þ 0:058L À 0:00043sz% ð15Þ Here, z% is the zirconia mass percentage (wt%).…”
Section: Wear Of Zirconia Reinforced Ai-sic Hybrid Compositesmentioning
confidence: 99%
“…Comparison of measured data 28 and ANN-predicted trends for the wear mass loss versus the sliding distance for the two values of the applied load L = 20 N (a) and L = 40 N (b) for different values of the percentage concentration of reinforcement.…”
Section: Validation Of the Ann Modeling Approachmentioning
A widely used type of artificial neural networks, called multilayer perceptron, is applied for data-driven modeling of the wear coefficient in sliding wear under constant testing conditions. The integral and differential forms of wear equation are utilized for designing an artificial neural network-based model for the wear rate. The developed artificial neural network modeling framework can be utilized in studies of wearing-in period and the so-called true wear coefficient. Examples of the use of the developed approach are given based on the experimental data published recently.
“…The ANN predictions for the wear coefficient are shown in Figure 5 by the solid lines together with the estimates (dashed lines) extracted from the regression model (15). Figure 4.Comparison of measured data 28 and ANN-predicted trends for the wear mass loss versus the sliding distance for the two values of the applied load L = 20 N (a) and L = 40 N (b) for different values of the percentage concentration of reinforcement.Figure 5.Predictions of the linear regression model (dashed lines), the ANN model (solid lines), and the SWR-based approximations (dot symbols) for the wear coefficient as a function of the sliding distance for the two values of the applied load L = 20 N (a) and L = 40 N (b) for different values of the mass percentage of zirconia reinforcement.…”
Section: Validation Of the Ann Modeling Approachmentioning
confidence: 97%
“…Figure 6 shows our predictions for the true wear coefficient (evaluated at s = 600 m) as a function of the zirconia mass percentage obtained from the experimental data. 28 It is interesting to observe that the wear coefficient decreases with increasing contact load. This fact implies that the Archard–Kragelsky model, which assumes the power-law dependence of the wear rate w· on the contact pressure p seems to be more appropriate than Archard's equation (1).…”
Section: Validation Of the Ann Modeling Approachmentioning
confidence: 98%
“…In their 24 pin-on-disk tests, Arif et al 28 considered aluminum hybrid composites reinforced with micro-SiC (5 wt%) and nano-zirconia (0, 3, 6, and 9 wt%) under two levels of applied load L (20 and 40 N) and for three values of sliding distance s (300, 600, and 900 m). Using the ANN modeling and linear regression method, the following relation for the wear mass loss m (mg) was established 28 m ¼ À3:50417 þ 0:047z% þ 0:010s þ 0:058L À 0:00043sz% ð15Þ Here, z% is the zirconia mass percentage (wt%).…”
Section: Wear Of Zirconia Reinforced Ai-sic Hybrid Compositesmentioning
confidence: 99%
“…Comparison of measured data 28 and ANN-predicted trends for the wear mass loss versus the sliding distance for the two values of the applied load L = 20 N (a) and L = 40 N (b) for different values of the percentage concentration of reinforcement.…”
Section: Validation Of the Ann Modeling Approachmentioning
A widely used type of artificial neural networks, called multilayer perceptron, is applied for data-driven modeling of the wear coefficient in sliding wear under constant testing conditions. The integral and differential forms of wear equation are utilized for designing an artificial neural network-based model for the wear rate. The developed artificial neural network modeling framework can be utilized in studies of wearing-in period and the so-called true wear coefficient. Examples of the use of the developed approach are given based on the experimental data published recently.
“…From the research studies [ 12 ], it is witnessed that the magnetic field incorporation with conventional EDM technique significantly improves the thermoelectric properties, enhancing its machining capability. In addition, various researchers have experimented with EDM to improve for its low MRR, and enhance the surface properties of workpiece by mixing various types of powders in dielectric fluid (known as powder mixed EDM), which has proved to be a major breakthrough [ 13 , 14 , 15 ]. Likewise, an increased MRR and micro-hardness of machined surface along with reduced roughness has been witnessed in powder mixed hybrid EDM by researchers [ 16 ].…”
In the present work, a hybrid magnetic field assisted powder mixed electrical discharge machining had been carried out on the Aluminum-Silicon Carbide (Al-SiC) metal matrix composite. The aim of the study was to obtain higher surface finish, and enhanced material removal rate. The dielectric mediums employed were plain EDM oil, SiCp mixed and graphite powder mixed EDM oil for flushing through the tube electrode. The magnetic field intensity, discharge current, T-on/off duration and type of dielectric were the control variables used for present investigation. From the results, it was observed that the machining variables for instance, discharge current, T-on/off duration and type of dielectric conditions remarkably affected the material removal rate, micro-hardness and surface roughness of the machined composite material. The MRR augmented considerably with an increase in the magnetic field intensity along with peak current. Subsequently, the composite with lesser vol.% of SiC particulates witnessed sharp rise in MRR in maximum magnetic field environment (0.66T). In addition, quality of the machined surface improved significantly in graphite powder mixed dielectric flushing condition with intermediate external magnetic field environment. Besides, an enhancement of micro-hardness was quantified as compared to base material due to the transfer of the material (SiCp) during powder mixed ED machining.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
