Project no.: S-MIP-25-96
The project focuses on the advanced design and optimisation of laser-textured surfaces to improve the performance of materials under challenging conditions. By combining advanced experimental techniques, state-of-the-art computer modelling and AI-driven optimisation, this multidisciplinary effort aims to substantially change the application of laser surface texturing (LST) in various industries. The project aims to investigate in detail how different laser-generated nano-textures from simple 2D models to complex 3D and bio-inspired models affect the tribological properties of key materials such as aluminium and titanium alloys. Using state-of-the-art equipment such as nano-laser systems, atomic force microscopy, surface profilometry and tribometers, the project will analyse in detail changes in surface morphology, chemical composition, hardness, friction and wear resistance. At the same time, the project uses artificial intelligence and machine learning techniques to model the complex relationships between laser parameters and the resulting surface properties. By training advanced supervised learning models, including Random Forests, Gradient Boosting and Deep Neural Networks, the extensive experimental data will be used to develop a robust artificial intelligence system that can predict optimal laser parameters tailored to specific materials and industrial needs. The final objective is to integrate these AI models directly into industrial manufacturing workflows, enabling automated design and real-time optimization of laser-textured surfaces. This integration promises to significantly reduce production costs, enhance manufacturing precision, and boost the durability and sustainability of engineered components. Overall, this pioneering project aims to push the boundaries of laser surface engineering by combining nano-scale experiments with smart computing tools and setting new standards for material design in harsh environments.
Project funding:
Research Council of Lithuania, Projects carried out by researchers’ teams
Project results:
The proposed project will generate several key scientific outcomes, including a novel methodology for AI-assisted laser surface texturing (LST) of metals optimized for performance in harsh tribological environments, and a validated machine learning model for predicting optimal laser parameters based on material properties and desired performance criteria. A conceptual model integrating AI/ML systems into industrial LST workflows will also be developed, enabling adaptive, efficient, and sustainable manufacturing practices. Additionally, the project will produce comprehensive experimental datasets on the tribological performance of laser-textured aluminium and titanium alloy surfaces under various loading and environmental conditions. These outcomes will be complemented by a synthesis and interpretation of how 2D, 3D, and bio-inspired surface textures influence wear, friction, and energy efficiency across different applications. The success of the outcomes will be measured by quantifiable improvements in material performance (e.g., over 20% increase in wear resistance), enhanced process efficiency (e.g., over 30% reduction in optimization time using ML tools), sustainability metrics (e.g., reduced energy consumption and material waste), and the reproducibility and accessibility of results, including open datasets and models for further scientific use.
Period of project implementation: 2025-12-01 - 2028-11-30
Project coordinator: Kaunas University of Technology
