Porosity poses a challenge to the mechanical properties of cold sprayed coatings, especially when it is open or surface-connected, limiting the coatings’ capabilities to act as a barrier. The porosity formation is dependent on the feedstock powder characteristics and the cold spray process parameters. We present a machine learning-based approach to predict porosity based on the above-mentioned factors. Nine different machine learning models based on linear regression (LR), decision trees, random forests, gradient boosting, support vector machine (SVM), and neural networks were explored. Considering the excellent properties of high entropy alloys, Cantor alloy was taken as the consumable. Our dataset, derived from the literature and experiments, identified SVM with a linear kernel and LR as the top-performing models based on the Pearson correlation coefficient (PCC) and root mean square error, where the PCC values exceeded 0.8. The SHapley Additive exPlanations method helped in identifying that the type of gas and powder are the top two factors in pore formation.

A layer of composite material has been developed on the surface of microalloyed steel by embedding hard SiC particles into the matrix. Reinforcement of particles in a fused matrix was performed by Tungsten Inert Gas arcing on a flux coating containing SiC particles applied on the substrate. The modified surface has been characterized by using optical microscopy, field emission scanning electron microscopy, energy dispersive spectroscopy, and X-ray diffraction analysis to confirm the formation of the composite layer. The modified surface was further examined by Vickers' microhardness testing, which confirms a noteworthy improvement in hardness of about 2.9 times when compared to that of the base metal.

In this study, laser-assisted cold spray (LACS) of titanium alloy Ti6Al4V onto Ti6Al4V substrates has been investigated in two phases: (i) single-track deposits on substrates preheated to 400 °C, 600 °C, and 800 °C, respectively, and (ii) single-layer (multi-track) deposits on substrates preheated to 600 °C with three different track spacings (1 mm, 2 mm, and 3 mm). Cross-sectional microstructures of the single-track deposits showed intimate contact at the interfaces, especially extensive interfacial mixing for specimens with substrate preheating at 600 °C and 800 °C. Cross-sectional area porosity content in single layer LACS coatings was found to be around 0.4%, which is significantly lower than the standard or conventional cold spray (CS) process having ~2.3% porosity. The microstructure reveals that the LACS process has improved the adhesion and cohesion of the deposits, in addition to the other advantages of the CS process. The average microhardness values of LACS deposits were found to be in the range of 388–403 HV (the highest hardness with the lowest track spacing), which is approximately 6–10% lower than that of the CS deposits without laser substrate preheating. Tensile residual stresses were found in all three LACS coatings, which was due to elevated process gas temperature along with high heat input during laser preheating of the substrate. It was observed that the higher the track spacing, the higher the stress magnitude, i.e., 31 MPa, 135 MPa, and 191 MPa in the longitudinal direction when deposited with 1 mm, 2 mm, and 3 mm track spacings, respectively. Heat treatments induced varied microstructures in LACS coatings, encompassing fully equiaxed or lamellar α-phase within the β-phase, or a bimodal microstructure, with characteristics linked to track spacing variations. Key contributions of this study include enhanced coating-substrate adhesion through extensive interfacial mixing, a substantial reduction in cross-sectional area porosity compared to CS, insights into the effects of residual stresses, and, ultimately, advancing the comprehension of LACS and its potential advantages over conventional CS process.