Development of Smart Surface Texturing Techniques Using Ai-Driven Laser Machining for Enhanced Tribological Performance

Abstract

An approach to increase the tribological performance of engineering materials via the development of smart surface texturing techniques using artificial intelligence (AI)-driven laser machining is presented in this study. However, existing surface texturing approaches largely rely on trial-and-error methods and lack adaptive optimization and predictive design capabilities. This study integrates AI-based texture design with precision laser surface texturing (LST) to develop optimized surface patterns on AISI 316 L stainless steel and Ti 6Al 4V alloy substrates. This deep learning model was used to train the generation of ten unique texture geometries, each of which was subsequently fabricated using a nanosecond pulsed fiber laser system. Tribological testing using a ballon-disk tribometer under dry sliding conditions revealed significant improvements, including up to 35% reduction in the coefficient of friction and up to 48% reduction in wear volume compared to untextured surfaces. Data analysis confirmed that key texture parameters, such as dimple spacing, cut depth, and aspect ratio, were major factors that improved the surface performance. The results also demonstrated improvements in post-test surface roughness and lower contact temperature (better wear resistance and thermal management). Overall, the integration of AI in laser texturing is a scalable, adaptive, and highly effective advanced surface engineering technique with a strong impact on aerospace, biomedical, and automotive applications.