Magnesium alloys are popular in the aerospace and automotive industries due to their light weights and high specific strengths. The major disadvantages of magnesium alloys are their weak wear and corrosion resistances. Surface coating is one of the most efficient methods of making material surfaces resistant to wear. Experimental determination of wear loss is expensive and time-consuming. These disadvantages can be eliminated by using machine learning algorithms to predict wear loss. This study used experimentally obtained wear loss data for AZ91D magnesium alloy samples coated via two different spray coating methods (plasma and high velocity oxy-fuel spraying) using various parameters. Support vector regression (SVR) and extreme learning machine (ELM) methods were used to predict wear loss quantities. In models tested using 10-k cross-validation, R² was calculated as 0.9601 and 0.9901 when the SVR and ELM methods were applied, respectively. The ELM method was more successful than SVR. Thus, the ELM method has excellent potential to support the production of wear-resistant parts for various applications via spray coating.

In this study, it was aimed to improve the dielectric properties of ZnO nanoparticles with the addition of hBN, which was not previously available in the literature, and thus to expand their usage areas. Sol–gel synthesis method was used in this study to create pure and hexagonal boron nitride (hBN) doped zinc oxide (ZnO) nanoparticles. Zinc acetate dihydrate Zn(CH₃COO)₂2H₂O), sodium hydroxide NaOH, and hexagonal boron nitride (hBN), all from Sigma Aldrich, were used as starting reagents. The reagents were dissolved during the sol–gel synthesis by being heated to 90 °C for 4 h in a magnetic stirrer. FT-IR, XRD, FE-SEM, EDX characterization techniques, and impedance analyzer were used to find functional groups, structural, morphological, and chemical composition, and dielectric properties of the nanoparticles, respectively. The produced un-doped and hBN-doped ZnO particles consist of nano-sized structures. Changes occurred in the intensities and locations of the XRD diffraction peaks and FT-IR peaks with the addition of hBN. Characteristic peaks of both ZnO and hBN were observed in the diffraction peaks of the doped nanoparticles. All nanoparticles were of high purity and were successfully produced by the sol–gel method. It was shown that as the hBN doping level increased, there were more hBN nanoplates in the ZnO matrix, and the EDX results also showed an increase in hBN addition. The frequency stability of the dielectric properties improved after hBN doping. While the dielectric constant at 1 kHz frequency at room temperature is 12.07 in pure ZnO nanoparticles, the increase up to 55.21 is observed in 10% hBN doped nanocomposites. This situation is considered as a great potential for technological applications of this novel nanocomposite material.

Cutting fluids are difficult and expensive to recycle. These drawbacks mentioned can be reduced or eliminated by performing the cutting operations with minimum quantity lubrication or without using any cutting fluid. In this study, the effects of different cutting parameters on performance characteristics are studied empirically during the drilling of Al7075. The work piece surface roughness and the temperature changes due to the incurred heat at the cutting process are taken as performance outputs. In the experiments, HSS tools with a diameter of 8 mm and an angle of 118o were used. Minimum quantity lubrication (MQL), compressed air and dry processing (without the usage of any cooling liquid) techniques are used as the applied cooling technique. In the processing technique with MQL, the cooling liquid is sent pulverized on the interface between the work piece and the tool. Boron oil-water emulsion is used as the cutting liquid. As a result of the experiments, it is determined that better results are achieved with the MQL technique than with other cooling techniques. The best surface roughness is achieved at 20 m/min cutting speed and 0.1 mm/rev feed rate

In this study, AISI 1020 steel surface was coated in different heat inputs with (wt.-%) 50FeCrC-20FeW-30FeB powder mixture by using plasma transferred arc (PTA) welding method. The microstructure of the coated samples were investigated by using optical microscope (OM), scanning electron microscope (SEM), X-ray diffraction (XRD) and energy dispersive X-ray (EDS). The hardness was measured with micro hardness test device. The dry sliding wear and friction coefficient properties were determined using a block-on-disk type wear test device. Wear tests were performed at 19.62 N, 39.24 N, 58.86 N load and the sliding distance of 900 m. The results were shown that different microstructures formed due to the heat input change. The highest average micro hardness value was measured at 1217 HV on sample coated with low heat input. It was determined that the wear resistance decreased with increasing heat input.