Note: This video may require joining the NVIDIA Developer Program or login
GTC Silicon Valley-2019 ID:S9640:Industrial automation based on auto ML and GANs to address predictive maintenance
Konstantin Kiselev(Conundrum),Vladislav Mironov(Conundrum)
The session is focused on applying deep learning to predictive maintenance for paper manufacturing. Although addressing this problem with machine learning methods requires considerable training data that's usually not available in the paper industry, we'll introduce an approach that combines GANs and reinforcement learning. We'll describe how that makes it possible to create a digital twin of equipment based on data from sensors, which works like a virtual environment for synthetic data generation.