Interpretable physical-informed machine learning for dynamic characteristics prediction of air spring with limited measurement information
ISA Transactions · 2026-08 · 175 · 28-41
DOI: 10.1016/j.isatra.2026.05.010 ↗Kurz gefasst
Fachartikel in der Zeitschrift ISA Transactions, 2026-08. Verfasst von Wu Qin und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China. Electronic address: qw@ecjtu.edu.cn. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Ministry of Science and Technology of the People's Republic of China, Natural Science Foundation of Jiangxi Province.
Abstract (Originalsprache)
Pipe-type air spring with auxiliary airbag (ASAA) are important vibration isolation component due to its tunable volume and adjustable dynamic characteristics. However, its dynamic modeling is challenging because airbag expansion work, rubber bladder viscoelasticity, and turbulence-dominated throttle dynamics are strongly coupled under large-amplitude excitations. Traditional data-driven models often require large datasets and lack interpretability. To address this issue, this study proposes an interpretable physics-informed machine learning (PIML) framework for ASAA dynamic prediction. A reduced-order physical model is first developed to provide baseline predictions of stiffness and lag angle, and the discrepancies between physical predictions and experimental measurements are then used to construct residual datasets. An interpretable Kolmogorov-Arnold Network (KAN) is employed to learn these residuals through adaptive B-spline activation functions and derive explicit symbolic correction terms. Experimental validation shows that the proposed hybrid model improves prediction accuracy while retaining physical interpretability, outperforming pure data-driven, advanced physics-data and physical models.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China. Electronic address: qw@ecjtu.edu.cn.
- School of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China. Electronic address: 2023038080200027@ecjtu.edu.cn.
- State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangdong University of Technology, Guangzhou 510006, China; Reutlingen University, Alteburgstraße 150, Reutlingen 72762, Germany. Ele…
- School of Mechanical Engineering, South China University of Technology, China. Electronic address: 202111080705@mail.scut.edu.cn.
- School of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China. Electronic address: 2971@ecjtu.edu.cn.
- State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangdong University of Technology, Guangzhou 510006, China. Electronic address: mezychen@gdut.edu.cn.
Förderung
- National Natural Science Foundation of China
- Ministry of Science and Technology of the People's Republic of China
- Natural Science Foundation of Jiangxi Province
- China Postdoctoral Science Foundation
- Basic and Applied Basic Research Foundation of Guangdong Province
Zitieren
APA
Qin, W., Liao, X., Qi, J., He, Y., Liu, F., & Chen, Z. (2026). Interpretable physical-informed machine learning for dynamic characteristics prediction of air spring with limited measurement information. ISA Transactions, 175, 28-41. https://doi.org/10.1016/j.isatra.2026.05.010
Vancouver
Qin W, Liao X, Qi J, He Y, Liu F, Chen Z. Interpretable physical-informed machine learning for dynamic characteristics prediction of air spring with limited measurement information. ISA Transactions. 2026;175:28-41. doi:10.1016/j.isatra.2026.05.010
BibTeX
@article{Qin2026,
author = {Qin, Wu and Liao, Xundong and Qi, Junyu and He, Yi and Liu, Feifei and Chen, Zhuyun},
title = {Interpretable physical-informed machine learning for dynamic characteristics prediction of air spring with limited measurement information},
journal = {ISA Transactions},
year = {2026},
volume = {175},
pages = {28--41},
doi = {10.1016/j.isatra.2026.05.010}
}
EUVIMED