ONION: Physics-Informed Deep Learning Model for Line Integral Diagnostics Across Fusion Devices

This paper introduces a Physics-Informed model architecture that can be adapted to various backbone networks. The model incorporates physical information as additional input and is constrained by a Physics-Informed loss function. Experimental results demonstrate that the additional input of physical...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-11
Main Authors: Wang, Cong, Yang, Weizhe, Wang, Haiping, Yang, Renjie, Li, Jing, Wang, Zhijun, Yu, Xinyao, Yixiong Wei, Huang, Xianli, Liu, Zhaoyang, Zou, Changqing, Zhao, Zhifeng
Format: Article
Language:English
Subjects:
Algorithms
Datasets
Diagnostic systems
Error reduction
Onions
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper introduces a Physics-Informed model architecture that can be adapted to various backbone networks. The model incorporates physical information as additional input and is constrained by a Physics-Informed loss function. Experimental results demonstrate that the additional input of physical information substantially improve the model's ability with a increase in performance observed. Besides, the adoption of the Softplus activation function in the final two fully connected layers significantly enhances model performance. The incorporation of a Physics-Informed loss function has been shown to correct the model's predictions, bringing the back-projections closer to the actual inputs and reducing the errors associated with inversion algorithms. In this work, we have developed a Phantom Data Model to generate customized line integral diagnostic datasets and have also collected SXR diagnostic datasets from EAST and HL-2A. The code, models, and some datasets are publicly available at https://github.com/calledice/onion.
ISSN:2331-8422