Abstract
One of the main decision points for selecting a 3DP technology for production applications is the cost
per produced part. In order to enable this choice-point it is required to provide a relatively accurate
estimation of the cost per part. We have developed a way to calculate the cost automatically,
transparently to the user and more accurately than most of the currently available solutions for the
different 3DP technologies, by using a trained machine learning model in the nesting algorithm
executed in the Pre-print SW application. Then, the proposed method is intended to be combined with
any other packing algorithm which may have any optimization target. The packing algorithm generates
job nesting configurations and our proposed method analyzes if the solution found meets the cost
requirement previously defined by the user. If the solution meets the cost requirement it is accepted. In
any other case the solution is rejected, and the packing algorithm is re-executed to find a different
solution.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.
Recommended Citation
INC, HP, "PACKING ALGORITHM WHICH MINIMIZES 3D BUILD COST BASED ON PRE-TRAINED MACHINE LEARNING MODEL", Technical Disclosure Commons, (February 23, 2021)
https://www.tdcommons.org/dpubs_series/4098