Data-driven Framework for Optimization of Manufacturing Processes under Uncertainty  
Author T.Q.D. Pham


Co-Author(s) V.S. Bui; X.V. Tran


Abstract Additive manufacturing is a unique capability for building complex three-dimensional objects, which is used in many industrial sectors thanks to its sustainability, flexibility, and efficiency. However, typical parameter optimization and uncertainty quantification of the metallic additive manufacturing process usually requires significant experimental and computational costs for performing high-quality experiments with different process settings. This work aims to develop an efficient data-driven framework optimization of advanced additive manufacturing processes. The proposed framework would allow efficiently tuning the process parameters to obtain the desired quality of fabricated products with a controllable and acceptable variability. In general, these findings provide valuable insights for the process parameter optimization of the metallic additive manufacturing process under uncertainty to improve the quality of the final printed parts efficiently.


Keywords Additive manufacturing, Deep Learning, Surrogate model, Probabilistic approach, Robust optimization
    Article #:  DSBFI23-67
Proceedings of 2nd ISSAT International Conference on Data Science in Business, Finance and Industry
January 8-10, 2023 - Da Nang, Vietnam