Work

Physics Informed Neural Networks for Electrical Impedance Tomography

Year: 2025

Type: article

Abstract: Electrical Impedance Tomography (EIT) is an imaging modality used to reconstruct the internal conductivity distribution of a domain via boundary voltage measurements. In this paper, we present a novel EIT approach for integrated sensing of composite structures utilizing Physics Informed Neural Networks (PINNs). Unlike traditional data-driven only models, PINNs incorporate underlying physical principles governing EIT directly into the learning process, enabling precise and rapid reconstructions. We demonstrate the effectiveness of PINNs with a variety of physical constraints for integrated sensing. The proposed approach has potential to enhance material characterization and condition monitoring, offering a robust alternative to classical EIT approaches.

Source: Neural Networks

DOI: 10.1016/j.neunet.2025.107410

Authors: Danny Smyl, Tyler N. Tallman, Laura Homa, Chenoa Flournoy, Sarah J. Hamilton, John Wertz

Institutions: Georgia Institute of Technology, Purdue University West Lafayette, United States Air Force Research Laboratory, Wright-Patterson Air Force Base, University of Dayton Research Institute, Marquette University

Language: English

Topic: Electrical and Bioimpedance Tomography

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

Funder: Air Force Research Laboratory

OpenAlex ID: W4408761525

FWCI: 4.89

Cites: 18

Cited by: 22

Related to: 10