Phase composition and mechanical properties of Ti1-x-yAlxNbyN coatings as a function of the process bias and the chemical composition: A machine learning assisted approach
Year: 2026
Type: article
Abstract: Understanding the relationship between chemical composition, process parameters, and their impact on titanium-based physical vapor deposition (PVD) coatings – such as titanium nitride (TiN), titanium niobium nitride (TiNbN), and titanium aluminum nitride (TiAlN) – remains a key challenge in advancing arc PVD coating technologies for industrial applications. Building on the promising performance of Ti 1-x-y Al x Nb y N reported in previous studies, this study aimed to evaluate the impact of process bias on Ti 1-x-y Al x Nb y N coatings with varying chemical configurations. Five arc target configurations were tested at three different bias levels using an industrial-scale arc PVD-process, following a multifactorial experimental design. Deposition rate, scratch resistance, and hardness were measured using standardized testing protocols. The coatings' microstructure was analyzed using scanning electron microscopy (SEM) and X-ray diffraction (XRD). Additionally, a machine learning model was developed to assess the influence of chemical composition and process bias on the resulting coating properties. The experimental findings demonstrated that process bias significantly influences the microstructure and mechanical properties of Ti 1-x-y Al x Nb y N coatings. The machine learning models exhibited strong reproducibility in predicting mechanical surface characteristics.
Source: Vacuum
Language: English
Subfield: Mechanics of Materials
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,860
OpenAlex ID: W7160852145