FURI | Fall 2020
A Novel Use of GAN’s to Efficiently Simulate Fracture in Polymer Composites
Can a neural network be used to speed up finite element analysis in certain material simulations? The researchers built a pipeline to generate thousands of finite element analysis maps and preprocess the data to be used by machine learning algorithms. Multiple architectures have been trained on the data and their effectiveness was measured. Preliminary data demonstrate that simple machine learning models can quickly and accurately estimate the output of finite element analysis in certain situations. These estimates can be refined with traditional analysis which results in a marked speedup. Future work involves expanding these models to handle more complex data.
Hometown: Walnut Creek, California, United States
Graduation date: Fall 2020