Publications

Huang, Andy H.; Trask, Nathaniel A.; Gao, Xujiao G.; Reza, Shahed R.; Patel, Ravi G.; Brissette, Christopher B.; Hu, Xiaozhe H.

Abstract not provided.

Huang, Andy H.; Gao, Xujiao G.; Reza, Shahed R.; Trask, Nathaniel A.; Wilcox, Ian Z.; Diaz, Candace; Patel, Ravi G.

Abstract not provided.

Huang, Andy H.; Trask, Nathaniel A.; Gao, Xujiao G.; Reza, Shahed R.; Wilcox, Ian Z.; Diaz, Candace

Abstract not provided.

Zinser, Brian; Blake, Samuel B.; Pfeiffer, Robert A.; Huang, Andy H.; Himbele, John J.; Freno, Brian A.; Dang, Vinh Q.; Kotulski, J.D.; Rajamanickam, Sivasankaran R.; Johnson, William Arthur.; Campione, Salvatore; Langston, William L.

Abstract not provided.

CEUR Workshop Proceedings

Huang, Andy H.; Trask, Nathaniel A.; Brissette, Christopher; Hu, Xiaozhe

The data-driven discrete exterior calculus (DDEC) structure provides a novel machine learning architecture for discovering structure-preserving models which govern data, allowing for example machine learning of reduced order models for complex continuum scale physical systems. In this work, we present a Greedy Fiedler Spectral (GFS) partitioning method to obtain a chain complex structure to support DDEC models, incorporating synthetic data obtained from high-fidelity solutions to partial differential equations. We provide justification for the effectiveness of the resulting chain complex and demonstrate its DDEC model trained for Darcy flow on a heterogeneous domain.

International Conference on Simulation of Semiconductor Processes and Devices, SISPAD

Gao, Xujiao G.; Huang, Andy H.; Trask, Nathaniel A.; Reza, Shahed R.

We present a Physics-Informed Graph Neural Network (pigNN) methodology for rapid and automated compact model development. It brings together the inherent strengths of data-driven machine learning, high-fidelity physics in TCAD simulations, and knowledge contained in existing compact models. In this work, we focus on developing a neural network (NN) based compact model for a non-ideal PN diode that represents one nonlinear edge in a pigNN graph. This model accurately captures the smooth transition between the exponential and quasi-linear response regions. By learning voltage dependent non-ideality factor using NN and employing an inverse response function in the NN loss function, the model also accurately captures the voltage dependent recombination effect. This NN compact model serves as basis model for a PN diode that can be a single device or represent an isolated diode in a complex device determined by topological data analysis (TDA) methods. The pigNN methodology is also applicable to derive reduced order models in other engineering areas.

Gao, Xujiao G.; Huang, Andy H.; Trask, Nathaniel A.; Reza, Shahed R.

Abstract not provided.

Zinser, Brian; Blake, Samuel A.; Pfeiffer, Robert A.; Huang, Andy H.; Himbele, John J.; Freno, Brian A.; Dang, Vinh Q.; Kotulski, J.D.; Rajamanickam, Sivasankaran R.; Johnson, William Arthur.; Campione, Salvatore; Langston, William L.

Abstract not provided.

Trask, Nathaniel A.; Huang, Andy H.

Abstract not provided.

Huang, Andy H.; Gao, Xujiao G.; Pawlowski, Roger P.; Gates, Jason M.; Musson, Lawrence M.; Hennigan, Gary L.; Negoita, Mihai N.

Abstract not provided.

Huang, Andy H.; Gao, Xujiao G.; Pawlowski, Roger P.; Gates, Jason M.; Musson, Lawrence M.; Hennigan, Gary L.; Negoita, Mihai N.

Abstract not provided.

Huang, Andy H.; Gao, Xujiao G.; Pawlowski, Roger P.; Gates, Jason M.; Musson, Lawrence M.; Hennigan, Gary L.; Negoita, Mihai N.

Abstract not provided.

Gao, Xujiao G.; Huang, Andy H.; Peterson, Kara J.; Hennigan, Gary L.; Musson, Lawrence M.; Bochev, Pavel B.

Abstract not provided.