Predictive Iterative Learning Control with Data-Driven Model for Optimal Laser Power in Selective Laser Sintering

Nettekoven, A.
Fish, S.
Topcu, U.
Beaman, J.
Journal Title
Journal ISSN
Volume Title
University of Texas at Austin

Building high quality parts is still a key challenge for Selective Laser Sintering machines today due to a lack of sufficient process control. In order to improve process control, we propose a Predictive Iterative Learning Control (PILC) controller that minimizes the deviation of the postsintering temperature profile of a newly scanned part from a desired temperature. The controller does this by finding an optimal laser power profile and applying it to the plant in a feedforward manner. The PILC controller leverages machine learning models that accurately capture the process’ temperature dynamics based on in-situ measurement data while still guaranteeing low computational cost. We demonstrate the controller’s performance in regards to the control objective with heat transfer simulations by comparing the PILC-controlled laser power profiles to constant laser power profiles.