Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Nov 7, 2025

Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

1.4K

Feature Engineering for Surrogate Models of Consolidation Degree in Additive Manufacturing.

Mriganka Roy1, Olga Wodo2

  • 1Mechanical and Aerospace Engineering Department, University at Buffalo, Buffalo, NY 14260, USA.

Materials (Basel, Switzerland)
|April 30, 2021
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Taxonomy of amorphous ternary phase diagrams: the importance of interaction parameters.

Physical chemistry chemical physics : PCCP·2025
Same author

Metric Learning for High-Throughput Combinatorial Data Sets.

ACS combinatorial science·2019
See all related articles

This study develops accurate surrogate models (SM) for fused filament fabrication, predicting part consolidation. These models significantly reduce computational cost while maintaining high accuracy for additive manufacturing processes.

Area of Science:

  • Materials Science
  • Mechanical Engineering
  • Computational Modeling

Background:

  • Surrogate models (SM) offer cost-effective predictions for complex simulations.
  • Additive manufacturing (AM) surrogate model development faces challenges due to high-dimensional inputs and expensive data generation.
  • Predicting consolidation degree in fused filament fabrication (FFF) is crucial for part quality.

Purpose of the Study:

  • To engineer effective features for a surrogate model to predict consolidation degree in FFF.
  • To leverage physics-informed features capturing thermal, geometric, and depositional characteristics.
  • To achieve high prediction accuracy at a reduced computational cost.

Main Methods:

  • Feature engineering informed by the physics of thermal processes and polymer healing theory.
Keywords:
additive manufacturingdata-driven approachfused filament fabrication

More Related Videos

Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads
07:58

Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads

Published on: July 25, 2025

368
Additive Manufacturing of Functionally Graded Ceramic Materials by Stereolithography
06:53

Additive Manufacturing of Functionally Graded Ceramic Materials by Stereolithography

Published on: January 25, 2019

14.7K

Related Experiment Videos

Last Updated: Nov 7, 2025

Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

1.4K
Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads
07:58

Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads

Published on: July 25, 2025

368
Additive Manufacturing of Functionally Graded Ceramic Materials by Stereolithography
06:53

Additive Manufacturing of Functionally Graded Ceramic Materials by Stereolithography

Published on: January 25, 2019

14.7K
  • Training a surrogate model using medium-sized data generated from a coupled physics-based thermal model.
  • Validation of prediction accuracy and computational efficiency against the numerical model.

    • Main Results:

    • Engineered features successfully captured key process characteristics.
    • The surrogate model achieved over 90% accuracy in predicting consolidation degree.
    • Prediction speed was four orders of magnitude faster than the original numerical model.

    Conclusions:

    • Physics-informed feature engineering is effective for surrogate modeling in AM.
    • The developed surrogate model provides a computationally efficient and accurate method for predicting FFF consolidation.
    • This approach can significantly accelerate the design and optimization of AM processes.