Practical Application of ML in Detecting Bond Graph Domain

DOI

10.2991/978-94-6463-805-9_20How to use a DOI?

Keywords

bond graphs; multi-domain systems; deep learning; multidisciplinary systems

Abstract

Bond graph modeling provides a unified and structured approach for analyzing complex multi-domain systems. These systems often involve interactions between multiple physical domains such as mechanical, electrical, hydraulic, thermal, and chemical. The challenge lies in correctly identifying the domain of a bond graph, especially in complex systems. To address this issue, we propose a supervised learning approach using a pre-trained MobileNetV2 for automated bond graph domain classification. Through experiments on synthesized bond graph models in different domains (Electrical, Mechanical, Electromechanical), our deep learning model achieved highly accurate predictions, with an overall accuracy of approximately 97%.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ikram Ralem
AU  - Hafid Haffaf
PY  - 2025
DA  - 2025/08/05
TI  - Practical Application of ML in Detecting Bond Graph Domain
BT  - Proceedings of the First International Conference on Artificial Intelligence, Smart Technologies and Communications (AISTC 2025)
PB  - Atlantis Press
SP  - 177
EP  - 184
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-805-9_20
DO  - 10.2991/978-94-6463-805-9_20
ID  - Ralem2025
ER  -