Aerospace Testing InternationalAerospace Testing International
  • News
    • A-E
      • Acoustic & Vibration
      • Avionics
      • Data Acquisition
      • Defense
      • Drones & Air Taxis
      • Electric & Hybrid
      • EMC
      • Engine Testing
      • Environmental Testing
    • F-L
      • Fatigue Testing
      • Flight Testing
      • Helicopters & Rotorcraft
      • High Speed Imaging
      • Industry News
    • M-S
      • Materials Testing
      • NDT
      • Simulation & Training
      • Software
      • Space
      • Structural Testing
      • Supplier News
    • T-Z
      • Technology
      • Telemetry & Communications
      • Weapons Testing
      • Wind Tunnels
  • Features
  • Magazines
    • March 2025
    • Dec 2024/Jan 2025
    • Showcase 2025
    • September 2024
    • June 2024
    • Archive Issues
    • Subscribe Free!
  • Opinion
  • Webinars
  • Events
    • All Events
    • Aerospace Test & Development Show
  • Podcasts
  • Videos
  • Suppliers
    • Supplier Spotlights
    • Press Releases
    • Technical Papers
  • Jobs
    • Browse Jobs
    • Post a Job – It’s FREE!
    • Manage Jobs (Employers)
LinkedIn YouTube X (Twitter)
LinkedIn YouTube X (Twitter)
Subscribe to magazine Subscribe to email newsletter Media Pack
Aerospace Testing InternationalAerospace Testing International
  • News
      • Acoustic & Vibration
      • Avionics
      • Data Acquisition
      • Defense
      • Drones & Air Taxis
      • Electric & Hybrid
      • EMC
      • Engine Testing
      • Environmental Testing
      • Fatigue Testing
      • Flight Testing
      • Helicopters & Rotorcraft
      • High Speed Imaging
      • Industry News
      • Materials Testing
      • NDT
      • Simulation & Training
      • Software
      • Space
      • Structural Testing
      • Supplier News
      • Technology
      • Telemetry & Communications
      • Weapons Testing
      • Wind Tunnels
  • Features
  • Magazines
    1. March 2025
    2. Dec 2024/Jan 2025
    3. Showcase 2025
    4. September 2024
    5. June 2024
    6. March 2024
    7. Archive Issues
    8. Subscribe Free!
    Featured
    19th March 2025

    In this issue: March 2025

    Online Magazines By Ben Sampson
    Recent

    In this issue: March 2025

    19th March 2025
    contents and front cover of magazine

    In this issue: December / January 2025

    19th December 2024
    Showcase 2025

    In this issue – Showcase 2025

    6th November 2024
  • Opinion
  • Webinars
  • Events
    • All Events
    • Aerospace Test & Development Show
  • Podcasts
  • Videos
  • Suppliers
    • Supplier Spotlights
    • Press Releases
    • Technical Papers
  • Jobs
    • Browse Jobs
    • Post a Job – It’s FREE!
    • Manage Jobs (Employers)
LinkedIn YouTube X (Twitter)
Aerospace Testing InternationalAerospace Testing International
Materials Testing Technology

Machine learning improves NDT accuracy

Ben SampsonBy Ben Sampson15th April 20203 Mins Read
Share LinkedIn Twitter Facebook Email
3D printing
(Image: Ines Álvarez Fdez/Unsplash)

Researchers in the USA and China have developed an artificial intelligence algorithm that improves the accuracy of plastic deformation measurements.

The algorithm, which was developed at Brown, Massachusetts Institute of Technology and Nanyang Technical University (NTU) in Singapore, vastly reduces the error rates involved in testing the mechanical properties of materials using instrumented indentation techniques. The process could also be particularly useful on evaluating modern 3D printed materials.

Instrumented indentation is a way of testing the mechanical properties of materials in a non-destructive way and involves measuring the forces required to make tiny dents in a material and then using those measurements to calculate material properties.

The technique works well for measuring elastic deformation, but not for plastic deformation, the forces that cause irreversible changes to a material. “The error rates using this technique for plastic properties had been on the order of 140%,” said George Karniadakis, a professor of applied mathematics at Brown. “But using this machine learning technique, we can bring that down to 4 or 5%.”

Multifidelity

The researchers used a set of neural network machine learning algorithms that are able to learn from data of varying quality. The “multifidelity” approach can combine lower-fidelity data from computer simulations of plastic deformation with data from direct experiments.

The experimental data is much higher in quality but is often scarce for a given material. By combining experimental data with simulation, the multifidelity algorithm needs only a handful of experiments to return reliable results.

The researchers also showed that a neural network that had been trained on one material could be easily adapted to a different material with minimal additional training.

“Normally it would take 10,000 iterations to train a network on a new material,” said Lu Lu, a postdoctoral researcher at Brown and the study’s lead author. “But we can use information from one material and transfer it to the new material with just a few experimental data points.”

Karniadakis says the new algorithms can be easily incorporated into existing instrumented indentation hardware. The researchers have patented the algorithms and plan to make them available commercially.

The new system could be particularly useful for evaluating materials made via 3D printing and other additive manufacturing methods, where experimental data on their properties is particularly scarce.

“Materials have to be carefully tested before they’re used, particularly in areas like the aerospace industry and other critical applications,” Karniadakis said. “As we move more toward 3D printing and other additive manufacturing, there’s a need to evaluate these novel materials, and this will help to do that.”

The research has been published in Proceedings of the National Academy of Sciences. Co-authors on the paper were Subra Suresh, a former Brown professor and National Science Foundation director who is now president of NTU, Ming Dao, Punit Kumar and Upadrasta Ramamurty.

Share. Twitter LinkedIn Facebook Email
Previous ArticleF-15QA fighter jet makes maiden test flight
Next Article CH-53K Stallion passes air-to-air refueling test
Ben Sampson

Ben has worked as a journalist and editor, covering technology, engineering and industry for the last 20 years. Initially writing about subjects from nuclear submarines to autonomous cars to future design and manufacturing technologies, he was editor of a leading UK-based engineering magazine before becoming editor of Aerospace Testing in 2017.

Related Posts

Materials Testing

Glasgow NextSpace facility to test 3D printed space materials

14th May 20253 Mins Read
News

Commercial aircraft could deploy aerosols to cool planet

9th May 20253 Mins Read
Materials Testing

Self-healing polymer developed for spacecraft protection

6th May 20254 Mins Read
Latest Posts

Industry Adoption of 3D Optical Surface Gauges

21st May 2025

NDT: Robotics and software spur innovation

21st May 2025

Wisk and NASA to partner on US autonomous flight operations and standards

20th May 2025
Supplier Spotlights
Our Social Channels
  • Twitter
  • YouTube
  • LinkedIn
Getting in Touch
  • Subscribe To Magazine
  • Contact Us
  • Meet the Team
  • Media Pack
Related Topics
  • Aircraft Interiors
  • Business Jet Interiors
FREE WEEKLY NEWS EMAIL!

Get the 'best of the week' from this website direct to your inbox every Wednesday

© 2023 Mark Allen Group Ltd | All Rights Reserved
  • Cookie Policy
  • Privacy Policy
  • Terms & Conditions

Type above and press Enter to search. Press Esc to cancel.