Multiphysics-Informed Neural Network (MPINN) for Accurate Multidimensional Predictions of Mechatronic Systems

Abstract

Mechatronic systems are often characterized by complex multiphysics phenomena that are difficult to model using traditional analytical or computational methods. Deep neural networks (DNNs) have shown great potential in predicting the behavior of these systems, but their accuracy and robustness are heavily dependent on the availability of large amounts of data. In this proposal, we introduce a novel architecture for a multiphysics-informed neural network (MPINN) that can accurately and efficiently predict the multidimensional responses of mechatronic systems, even with limited data.

Document Details

Document Type
DoD Grant Award
Publication Date
Feb 16, 2024
Source ID
FA23862314094

Entities

People

  • Ki Yong Oh

Organizations

  • Air Force Office of Scientific Research
  • United States Air Force

Tags

Fields of Study

  • Physics

Readers

  • Computational Fluid Dynamics (CFD)
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks