Research Projects

Difficult-to-cut materials such as Ti-6Al-4V alloys pose significant challenge due to their low thermal conductivity, high chemical reactivity at elevated temperatures, and rapid tool wear. Conventional hard coatings (e.g., TiN, TiAlN, AlCrN), though widely used, often underperform in extreme thermal and tribological environments. This lead to the develeopment of advanced thin-film coatings with superior wear resistance, thermal stability, and oxidation resistance in order to enhance tool life and productivity. This proposal aims to address this challenge by developing and evaluating a new class of multi-elemental nanolaminate coatings synthesized via reactive magnetron sputtering and High Power Impulse Magnetron Sputtering (HiPIMS), specifically designed for cutting tool inserts. The anisotropic layered structure and hybrid ceramic–metallic bonding in these coatings are expected to yield an optimal balance of hardness, toughness, heat dissipation, and oxidation resistance which are generally suitable for high-speed and dry machining applications. However, controlling stoichiometry, crystallographic orientation, and phase formation during sputtering, especially in multi-component systems with reactive gases, remains a significant challenge. The central hypothesis of the proposal would involve AI/ML modeling for fine tuning deposition parameters which might significantly enhance performance over commercial alternatives. It is further believed that ML algorithms can reliably predict phase stability and key performance metrics, thereby reducing trial-and-error and enabling scale-up. Experimental efforts will include combinatorial deposition using DC, RF, and HiPIMS from elemental targets. Resulting films will undergo high-resolution structural analysis to confirm phase formation and orientation. Tribo-mechanical tests will be conducted under realistic machining conditions to correlate coating hardness, toughness, and wear resistance. AI/ML algorithms (random forest, SVM, Gaussian processes) will be trained on these datasets to develop predictive models which can be generalizable across materials and machining conditions. This project builds upon prior work on WS₂-based nanocomposite coatings (TiN-WS₂, CrN-WS₂, ZrN-WS₂), which demonstrated the impact of nitrogen flow rate on coating performance. That study achieved hardness values of 22–36 GPa, friction coefficients as low as 0.08, and improved adhesion strength (up to 244 mN). These results underscored the critical role of process control in tailoring microstructure and performance. The current project transitions from empirical tuning to data-driven optimization, embedding prior learnings into a structured Process–Structure–Property–Performance (PSPP) framework. If successful, this research will advance both fundamental understanding and practical applications of advanced coatings. At the scientific level, it will demonstrate how AI/ML can accelerate coating development by mapping complex deposition–property relationships. At the applied level, the project will deliver prototype cutting tools with enhanced wear resistance, longer tool life, and reduced environmental impact via dry or near-dry machining. Moreover, the methodology and models developed in this work could provide useful guidance for intelligent coating design in different tribological systems, supporting future advancements in sustainable and high-performance manufacturing