Abstract
Modification and reconfiguration of the surface topography by the laser polishing (LP) process is a new innovative, non-material additive nor removal technology enabling new and/or enhancing existing value-adding surface functionalities, such as improving surface quality, visual appearance, wettability, friction, and others. However, the resultant surface is dependent upon many process parameters which makes selecting optimal process parameters to achieve desired surface topography complicated and unrepeatable. This study proposes and demonstrates that feed-forward neural network (FFNN) can reliably model the LP of H13 tool steel and predict the laser polished surface topography parameters such as areal waviness and roughness with a probability of 70%. © 2021 Her Majesty the Queen in Right of Canada, as represented by the National Research Council of Canada; equal contribution of co-authors
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
