This diagram illustrates the way the new system combines detailed data that is expensive to generate with synthesized data that can be generated cheaply, as shown at left, to arrive at reliable predictions of multiple material properties, at right. Image courtesy of the researchers.
This diagram illustrates the way the new system combines detailed data that is expensive to generate with synthesized data that can be generated cheaply, as shown at left, to arrive at reliable predictions of multiple material properties, at right. Image courtesy of the researchers.

A standard method for testing some of the mechanical properties of materials is to poke them with a sharp point. This ‘indentation technique’ can provide detailed measurements of how the material responds to the point’s force, as a function of its penetration depth.

With advances in nanotechnology over the past two decades, the indentation force can now be measured to a resolution on the order of one-billionth of a Newton (a measure of the force approximately equivalent to the force you feel when you hold a medium-sized apple in your hand). In addition, the sharp tip’s penetration depth can be captured to a resolution as small as 1nm. Such instrumented nanoindentation tools have provided new opportunities for probing physical properties in a wide variety of materials, including metals and alloys, plastics, ceramics and semiconductors.

But while indentation techniques, including nanoindentation, work well for measuring some properties, they exhibit large errors when probing the plastic properties of materials. This is the kind of permanent deformation that happens, for example, if you press your thumb into a piece of silly putty and leave a dent, or when you permanently bend a paper clip using your fingers.

Such tests can be important in a wide variety of industrial applications, including conventional and digital manufacturing (3D printing) of metallic structures, material quality assurance of engineering parts, and optimization of performance and cost. However, conventional indentation tests and existing methods to extract critical properties can be highly inaccurate.

Now, an international research team comprising researchers from Massachusetts Institute of Technology (MIT), Brown University and Nanyang Technological University (NTU) in Singapore has developed a new analytical technique that can improve the estimation of mechanical properties of metallic materials from instrumented indention, with as much as 20 times greater accuracy than existing methods. Their findings are reported in a paper in the Proceedings of the National Academy of Sciences that combines indentation experiments with computational modeling of materials using the latest machine-learning tools.

The team includes co-lead and senior author Ming Dao, a principal research scientist at MIT, and senior author Subra Suresh, professor emeritus at MIT and president and distinguished university professor at NTU Singapore. Their co-authors are Lu Lu and George Em Karniadakis from Brown University, and Punit Kumar and Upadrasta Ramamurty from NTU Singapore.

“Indentation is a very good method for testing mechanical properties,” Dao says, especially in cases where only small samples are available for testing. “When you try to develop new materials, you often have only a small quantity, and you can use indentation or nanoindentation to test really small quantities of materials.”

Such testing can be quite accurate for elastic properties – that is, situations where the material bounces back to its original shape after having been poked. But when the applied force goes beyond the material’s ‘yield strength’ – the point at which the poking leaves a lasting mark on the surface – this is called plastic deformation, and traditional indentation testing becomes much less accurate. “In fact, there's no widely available method that's being used” that can produce reliable information in such cases, Dao says.

Indentation can be used to determine hardness, but Dao explains that “hardness is only a combination of a material’s elastic and plastic properties. It's not a ‘clean’ parameter that can be used directly for design purposes. … But properties at or beyond yield strength, the strength denoting the point at which the material begins to deform irreversibly, are important to access the material’s suitability for engineering applications.”

The new method does not require any changes to experimental equipment or operation, but rather provides a way to work with the data to improve the accuracy of its predictions. By using an advanced neural network machine-learning system, the team found that a carefully planned integration of both real experimental data and computer-generated ‘synthetic’ data of different levels of accuracy (a so-called multifidelity approach to deep learning) can produce the kind of quick and simple, yet highly accurate, data that industrial applications require for testing materials.

Traditional machine learning approaches require large amounts of high-quality data. However, detailed experiments on actual material samples are time-consuming and expensive to conduct. But the team found that doing the neural network training with lots of low-cost synthetic data and then incorporating a relatively small number of real experimental data points – somewhere between three and 20, as compared with 1000 or more accurate but high-cost datasets – can substantially improve the accuracy of the outcome. In addition, they utilize established scaling laws to further reduce the number of training datasets needed to cover the parameter space for all engineering metals and alloys.

What’s more, the authors found that the majority of the time-consuming training process can be done ahead of time. This means that for evaluating the actual tests, a small number of real experimental results can be added for ‘calibration’ training just when they’re needed, and give highly accurate results.

These multifidelity deep-learning approaches have been validated using conventionally manufactured aluminum alloys as well as 3D-printed titanium alloys.

“The new approach takes advantage of novel machine learning strategies to improve the accuracy of the predictions and has a large potential for fast screening of the mechanical properties of components manufactured by 3D printing,” said Javier Llorca, scientific director of IMDEA Materials Institute in Madrid, Spain, who was not connected with this research. “It will allow one to discriminate the differences in the mechanical properties in different regions of the 3D-printed components, leading to more accurate designs.”

Ares Rosakis at Caltech, who also was not connected with this work, says this approach “results in remarkable computational efficiency and in unprecedented predictive accuracy of the mechanical properties. ... Most importantly, it provides a previously unavailable, fresh pair of eyes for ensuring mechanical property uniformity as well as manufacturing reproducibility of 3D-printed components of complex geometry for which classical testing is impossible.”

In principle, the basic approach could be extended and applied to many other kinds of problems involving machine-learning, Dao says. “This idea, I think, can be generalized to solve other challenging engineering problems.” The use of the real experimental data helps to compensate for the idealized conditions assumed in the synthetic data, where the shape of the indenter tip is perfectly sharp, the motion of the indenter is perfectly smooth, and so on. By using ‘hybrid’ data that includes both the idealized and the real-world situations, “the end result is a drastically reduced error,” he says.

This story is adapted from material from MIT, with editorial changes made by Materials Today. The views expressed in this article do not necessarily represent those of Elsevier. Link to original source.