Joint Inversion of Stress and Plastic Strain in X80 Pipeline Steel from Magnetic Measurements Using an MLP–GPR Model
Applied Sciences · 19.11.2026 · 16 (22) · 11483
DOI: 10.3390/app162211483 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 19.11.2026. Verfasst von Yijie Li und 1 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Plastic deformation alters the magnetic response of pipeline steel, complicating stress estimation from magnetic measurements. We propose a two-stage multilayer perceptron–Gaussian process regression (MLP–GPR) framework that incorporates predicted plastic state information into stress regression from magnetic hysteresis features. The framework was evaluated by repeated stratified five-fold cross-validation using magnetic measurements from a single X80 tensile specimen under controlled uniaxial loading. The model achieved a mean absolute error of 6.297 MPa for stress prediction, outperforming the comparison models under the same evaluation protocol. The results indicate that, under the present experimental conditions, the proposed method enables plastic state identification and stress inversion from magnetic hysteresis features and provides a feasible approach to the quantitative nondestructive assessment of pipeline mechanical condition.
Zitieren
APA
Li, Y., & Zhao, C. (2026). Joint Inversion of Stress and Plastic Strain in X80 Pipeline Steel from Magnetic Measurements Using an MLP–GPR Model. Applied Sciences, 16(22), 11483. https://doi.org/10.3390/app162211483
Vancouver
Li Y, Zhao C. Joint Inversion of Stress and Plastic Strain in X80 Pipeline Steel from Magnetic Measurements Using an MLP–GPR Model. Applied Sciences. 2026;16(22):11483. doi:10.3390/app162211483
BibTeX
@article{Li2026,
author = {Li, Yijie and Zhao, Chuntian},
title = {Joint Inversion of Stress and Plastic Strain in X80 Pipeline Steel from Magnetic Measurements Using an MLP–GPR Model},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {22},
pages = {11483},
doi = {10.3390/app162211483}
}
EUVIMED