Vortrag (20 Min., 5 Min. Diskussion, 5 Min. Raumwechsel)
Functional laser surface texturing arose in recent years to a very powerful tool for tailoring the surface properties of parts and components. Consequently, self-cleaning surfaces with an improved wettability, efficient engine components with optimized tribological properties as well as functional implants with increased biocompatibility are today achievable. However, with the increasing capabilities in functional laser surface texturing, the prediction of surface properties become more and more important in order to reduce the development time of those functionalities. Therefore, advanced approaches for the prediction of the properties of laser-processed surfaces – the so called predictive modelling – are required.
This work will introduce the concept of predictive modelling with respect to functional laser surface texturing by means of selected laser-based manufacturing techniques such as Direct Laser Interference Patterning and Direct Laser Writing. We will focus on fundamental concepts for the prediction of surface properties such as surface roughness, wettability as well as pattern homogeneity employing machine learning approaches and statistical methods. The modelling takes into consideration the used laser parameters and the analysis of topographical and other process-relevant information in order to predict the resulting surface properties. For this purpose, two different algorithms, namely Artificial Neural Network and Random Forest, were trained with experimental data for stainless steel and titanium surfaces. Statistical results indicate that both models can predict the desired surface functionality and topography with high accuracy, despite the use of a small dataset for the learning process. This gives the opportunity to easily apply the described approaches to new materials. The approaches can be used to further optimize the laser process regarding the process efficiency, overall throughput and other process outcomes. This allows estimating the functional performance of a surface before the laser texturing process is initiated.