Researchers reduce graphene-enhanced composite development time using neural networks

Researchers reduce graphene-enhanced composite development time using neural networks

Nano Graphene Inc. dba GrapheneCA (“GrapheneCA”) has cut the time and cost of developing graphene-enhanced advanced composites by using neural networks to extrapolate material data from a single sample.

Optimizing graphene-enhanced composites for specific uses – such as the leading edge for an aircraft tail plane – traditionally involves testing many material samples in order to reach the best formulation. GrapheneCA’s new process, developed with investigators from the NYU Tandon School of Engineering, formulates and analyzes theoretical graphene-enhanced composites, dramatically reducing preproduction assessment. In one round of tensile testing and dynamic mechanical analysis, an artificial neural network predicted the viscoelastic properties the material with an average error of 0.7%, compared to a series of conventional testing.

“Working with the researchers at NYU Tandon’s department of mechanical and aerospace engineering, we have developed a new method for predicting the behavior of thermosetting nanocomposites over a wide range of temperature and strain rates,” says Dr. Voskresensky, head of research and development at GrapheneCA’s New York-based production facility. “Furthermore, the same approach potentially can be applied to predict a behavior of thermoplastic materials. This is a critical step towards advanced 3D composite production.”

The development of graphene dates back to 2004, when two University of Manchester scientists realized they had isolated a single layer of carbon atoms on a piece of scotch tape used to clean a graphite crystal. Since then, graphene has captured the imagination of researchers due to its fascinating properties. It is 200 times stronger than steel, very flexible, transparent, and is an excellent conductor of electricity.



By incorporating atomically-thin graphene into existing materials used to build aircraft, the safety and performance properties of aircraft could be significantly improved. This in turn, could lead to reduced material weight and positive impact on the fuel efficiency of the aircraft and, as result, the environment.


Read more about graphene


Grapheneca is dedicated to tackling the challenge of integrating graphene into real-world applications through the use of its proprietary scalable and environmentally friendly production process. The company currently produces high quality graphene on a large scale in the form of pristine stacked graphite flakes with less than 0.03% oxygen contamination.

Nikhil Gupta, professor of mechanical and aerospace at NYU Tandon, led the research with Ph.D. student Xianbo Xu, developing data that could help manufacturers optimize the characteristics of composites for specific uses without having to perform countless costly, time-intensive testing with numerous samples. The work is detailed in “Artificial Neural Network Approach to Predict the Elastic Modulus from Dynamic Mechanical Analysis Results.”

“Applying an artificial neural network approach to predict the properties of nanocomposites can help in developing an approach where modeling can guide the material and application development and reduce the cost over time,” says Dr. Gupta.

“This is an invitation for manufacturers to work with us to make new graphene composites,” concludes Dr. Voskresensky, “But it is but one example of what we envision doing in cooperation with NYU Tandon.”


Learn more


William Kucinski is content editor at SAE International, Aerospace Products Group in Warrendale, Pa. Previously, he worked as a writer at the NASA Safety Center in Cleveland, Ohio and was responsible for writing the agency’s System Failure Case Studies. His interests include literally anything that has to do with space, past and present military aircraft, and propulsion technology.

Contact him regarding any article or collaboration ideas by e-mail at william.kucinski@sae.org.
  Continue reading »
X