New machine-learning simulations reduce energy need for N95 mask fabrics

Producing a large number of N95 masks, that have protected the world during the COVID-19 pandemic, is a highly energy intensive process that also demands extreme attention to detail. Producing a high quality product (N95 mask) involves spinning tiny plastic fibers at high temperatures, which for an estimated 300,000 tons of annually melt-blown materials require roughly 245 gigawatt-hours per year of energy.

In conjunction with 3M, the Argonne National Laboratory (part of U.S. Department of Energy) seeks to reduce the energy consumption of this process by 20% by using simulations and machine learning on the Theta supercomputer at the Argonne Leadership Computing Facility (ALCF) with the computational fluid dynamics (CFD) software OpenFOAM and CONVERGE.

The melt blowing process uses a die to extrude plastic at high temperatures. Finding a way to create identical plastic components at lower temperatures and pressures motivated the machine-learning search. By using simulations and machine learning, Argonne researchers can run hundreds or even thousands of use cases, an exponential improvement on prior work.

The simulations provide key insights into the process, a method to assess a combination of parameters that are used to generate data for the machine-learning algorithm. The machine-learning model can then be leveraged to ultimately converge on a design that can deliver the required energy savings.