Getty Images
Machine learning

Machine Learning Technique Improves Material Testing in Manufacturing

March 20, 2020
A hybrid approach of machine learning and nano-identification yields benefits.

Harnessing the power of machine learning, scientists have developed a material testing technique that improves the accuracy of a previous technique used in manufacturing.

Nano-indentation is a process used for poking a sample of a material with a sharp needle-like tip to see how the material responds by deforming. The technique has had poor accuracy in obtaining certain key mechanical properties of a material, which has prevented it from being used widely in the manufacturing industry.

The new technique is a hybrid approach that combines machine learning with nano-indentation techniques. It involves using the standard nano-indentation process and feeding its experimentally measured data to a neural network machine learning system. The scientists then developed and “trained” the system to predict samples’ yield strength 20 times more accurately than existing methods.

According to the researchers—a team from Nanyang Technological University, Singapore (NTU Singapore), Massachusetts Institute of Technology (MIT) and Brown Universitythe new analytical technique is able to reduce the need for time-consuming and costly computer simulations in the manufacture of parts. The technique tests whether parts are safe to use in real-life conditions and can be employed in structural applications such as airplanes and automobiles, as well as those made from digital manufacturing techniques such as 3D printing.

“By incorporating the latest advances in machine learning with nano-indentation, we have shown that it is possible to improve the precision of the estimates of material properties by as much as 20 times,” reported NTU Distinguished University Professor Subra Suresh, the senior corresponding author of the paper.

In addition to improving the precision of the estimates of material properties by as much as 20 times, Suresh noted, the research also validates the system’s predictive capability and accuracy enhancement on conventionally manufactured aluminum alloys and 3D-printed titanium alloys. “This points to our method’s potential for digital manufacturing applications in Industry 4.0, especially in areas such as 3D printing,” he said.

The findings will be published in the Proceedings of the National Academy of Sciences.

A Hybrid Approach

The process starts with pressing a hard tip—typically made of a material-like diamond—into the sample material at a controlled rate with precisely calibrated force, while constantly measuring the penetration depth of the tip into the material being deformed.

To improve accuracy, the NTU, MIT and Brown team developed an advanced neural network—a computing system modelled loosely on the human brain—and “trained” it with a combination of real experimental data and computer-generated data. The researchers’ “multi-fidelity” approach incorporated real experimental data as well as physics-based and computationally simulated “synthetic” data (from both two-dimensional and three-dimensional computer simulations) with deep learning algorithms.

Previous attempts at using machine learning to analyze material properties mostly involved the use of synthetic data generated by the computer under unrealistically perfect conditions—for instance, where the shape of the indenter tip is perfectly sharp, and the motion of the indenter is perfectly smooth. The measurements predicted by machine learning were inaccurate as a result.

However, training the neural network initially with synthetic data, then incorporating a relatively small number of real experimental data points, was shown to improve the accuracy of the results.

The researchers also report that the training with synthetic data can be done ahead of time, with a small number of real experimental results to be added for calibration when it comes to evaluating the properties of actual materials.

“The use of real experimental data points helps to compensate for the ideal world that is assumed in the synthetic data,” said Suresh. “By using a good mix of data points from the idealized and real world, the end result is drastically reduced error.”

Sponsored Recommendations

How BASF turns data into savings

May 7, 2024
BASF continuously monitors the health of 63 substation assets — with Schneider’s Service Bureau and EcoStruxure™ Asset Advisor. ►Learn More: https://www.schn...

Agile design thinking: A key to operation-level digital transformation acceleration

May 7, 2024
Digital transformation, aided by agile design thinking, can reduce obstacles to change. Learn about 3 steps that can guide success.

Can new digital medium voltage circuit breakers help facilities reduce their carbon footprint?

May 7, 2024
Find out how facility managers can easily monitor energy usage to create a sustainable, decarbonized environment using digital MV circuit breakers.

The Digital Thread: End-to-End Data-Driven Manufacturing

May 1, 2024
Creating a Digital Thread by harnessing end-to-end manufacturing data is providing unprecedented opportunities to create efficiencies in the world of manufacturing.

Voice your opinion!

To join the conversation, and become an exclusive member of Machine Design, create an account today!