Quality Estimation during CFRTP Press Molding by Machine Learning of Condition Monitoring

Abstract

During the two years of this research, PIs developed and demonstrated the innovative technologies in digital manufacturing. More precisely it is possible to measure the dynamically varying the material flow during the press molding by evaluating the apparent viscosity under in-line measurements. They also demonstrated that machine learning can be used to monitor process control state from the estimated viscosity, which was one of the main purposes of this research. The other accomplishment of this research includes the visualization of fiber orientation analysis using a new X-ray phase imaging to predict mechanical properties. Unfortunately, extension to 3D fiber orientation analysis of rib shape could not be achieved. Nevertheless, the results obtained in this project are highly contribute to the process control for composite materials related in digital twin, digital manufacturing, and additive manufacturing.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 11, 2023
Accession Number
AD1209929

Entities

People

  • Yasushi Miyano

Organizations

  • Kanazawa Institute of Technology

Tags

Communities of Interest

  • Autonomy
  • Sensors

DTIC Thesaurus Topics

  • Air Force Research Laboratories
  • Carbon Fiber Reinforced Polymer
  • Carbon Fibers
  • Composite Materials
  • Data Sets
  • Detectors
  • Fiber Reinforced Polymers
  • Laminates
  • Machine Learning
  • Materials
  • Materials Laboratories
  • Materials Science
  • Measurement
  • Mechanical Properties
  • Neural Networks
  • Polymer Matrix Composites
  • Reinforced Plastics
  • Resins
  • Thermoplastic Resins
  • X-Ray Computed Tomography

Readers

  • Computer Science/Computer Engineering/Data Science/Digital Signal Processing.
  • Distributed Systems and Data Platform Development
  • Reinforced Composite Materials

Technology Areas

  • AI & ML