The high-power impulse magnetron sputtering (HiPIMS) technique is widely used owing to the high degree of ionization and the ability to synthesize high-quality coatings with a dense structure and smooth morphology. However, limited efforts have been made in the deposition of MAX phase coatings through HiPIMS compared with direct current magnetron sputtering (DCMS), and tailoring of the coatings’ properties by process parameters such as pulse width and frequency is lacking. In this study, the Cr₂AlC MAX phase coatings are deposited through HiPIMS on network structured TiBw/Ti6Al4V composite. A comparative study was made to investigate the effect of average power by varying frequency (1.2–1.6 kHz) and pulse width (20–60 μs) on the deposition rate, microstructure, crystal orientation, and current waveforms of Cr₂AlC MAX phase coatings. X-ray diffraction (XRD), scanning electron microscopy (SEM), and atomic force microscopy (AFM) were used to characterize the deposited coatings. The influence of pulse width was more profound than the frequency in increasing the average power of HiPIMS. The XRD results showed that ex situ annealing converted amorphous Cr-Al-C coatings into polycrystalline Cr₂AlC MAX phase. It was noticed that the deposition rate, gas temperature, and roughness of Cr₂AlC coatings depend on the average power, and the deposition rate increased from 16.5 to 56.3 nm/min. Moreover, the Cr₂AlC MAX phase coatings produced by HiPIMS exhibits the improved hardness and modulus of 19.7 GPa and 286 GPa, with excellent fracture toughness and wear resistance because of dense and column-free morphology as the main characteristic.

This research presents a comprehensive analysis of deep neural network models (DNNs) for the precise prediction of Vickers hardness (HV) in nitrided and carburized M50NiL steel samples, with hardness values spanning from 400 to 1000 HV. By conducting rigorous experimentation and obtaining corresponding nanoindentation data, we evaluated the performance of four distinct neural network architectures: Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory network (LSTM), and Transformer. Our findings reveal that MLP and LSTM models excel in predictive accuracy and efficiency, with MLP showing exceptional iteration efficiency and predictive precision. The study validates models for broad application in various steel types and confirms nanoindentation as an effective direct measure for HV hardness in thin films and gradient-variable regions. This work contributes a validated and versatile approach to the hardness assessment of thin-film materials and those with intricate microstructures, enhancing material characterization and potential application in advanced material engineering.