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 Concept Videos

Predicting Molecular Geometry02:27

Predicting Molecular Geometry

35.7K
VSEPR Theory for Determination of Electron Pair Geometries
35.7K

You might also read

Related Articles

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

Sort by
Same author

A Modeling Framework for the Thermoforming of Carbon Fiber Reinforced Thermoplastic Composites.

Polymers·2024
Same author

Face shield design against blast-induced head injuries.

International journal for numerical methods in biomedical engineering·2017
See all related articles

Related Experiment Video

Updated: Sep 3, 2025

Knowledge Based Cloud FE Simulation of Sheet Metal Forming Processes
11:05

Knowledge Based Cloud FE Simulation of Sheet Metal Forming Processes

Published on: December 13, 2016

12.3K

Prediction and Optimization of Process Parameters for Composite Thermoforming Using a Machine Learning Approach.

Long Bin Tan1, Nguyen Dang Phuc Nhat1

  • 1Institute of High Performance Computing (IHPC), A*STAR, 1 Fusionopolis Way, #16-16, Connexis North Tower, Singapore 138632, Singapore.

Polymers
|July 27, 2022
PubMed
Summary

Artificial neural networks (ANN) offer a novel approach to optimize thermoforming of fiber-reinforced composites. This machine learning method predicts and refines process parameters, reducing defects and improving product quality in composite manufacturing.

Keywords:
artificial neural networkcarbon fibermachine learningoptimizationthermoformingthermoplasticswoven composites

More Related Videos

Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

1.2K
A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars
05:32

A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars

Published on: August 4, 2018

12.7K

Related Experiment Videos

Last Updated: Sep 3, 2025

Knowledge Based Cloud FE Simulation of Sheet Metal Forming Processes
11:05

Knowledge Based Cloud FE Simulation of Sheet Metal Forming Processes

Published on: December 13, 2016

12.3K
Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

1.2K
A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars
05:32

A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars

Published on: August 4, 2018

12.7K

Area of Science:

  • Materials Science
  • Manufacturing Engineering
  • Artificial Intelligence

Background:

  • Thermoforming of fiber-reinforced composites traditionally requires extensive physical trials or simulations to optimize process parameters, leading to high costs and time investment.
  • Defects like wrinkles, matrix-smear, and ply-splitting can occur if thermoforming processes are not meticulously optimized.
  • Existing machine learning applications have not yet addressed the specific challenges of woven composite thermoforming.

Purpose of the Study:

  • To introduce and evaluate the application of artificial neural networks (ANN) for analyzing and optimizing the thermoforming process of woven composites.
  • To develop an ANN model capable of predicting process parameters from visual data of thermoformed laminates.
  • To utilize ANN for optimizing process parameters to minimize defects and enhance the quality of the final formed composite part.

Main Methods:

  • Two distinct applications of artificial neural networks (ANN) were developed and tested.
  • The first ANN application focused on analyzing full-field contour results from simulations to predict process parameters linked to product quality.
  • The second ANN application aimed to optimize process parameters by minimizing slip-path length and maximizing desired shear angle regions.

Main Results:

  • The developed ANN demonstrated a reasonable ability to predict certain input parameters by analyzing images of the thermoformed laminate.
  • The ANN effectively optimized process parameters, leading to improved product quality by addressing objectives such as minimizing slip-path length.
  • ANN predictions showed encouraging agreement with experimental data, validating the proposed machine learning approach.

Conclusions:

  • Artificial neural networks present a promising, data-driven approach for optimizing composite thermoforming processes.
  • The proposed image analysis method using ANN is novel for composite manufacturing and can potentially integrate with machine vision for real-time quality control.
  • This research highlights the potential of machine learning to significantly reduce costs and improve efficiency in composite manufacturing.