Joint Inversion of Stress and Plastic Strain in X80 Pipeline Steel from Magnetic Measurements Using an MLP–GPR Model

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.

Authors

Institutions

Publication Details

Journal
Applied Sciences
Published
2026-11-19
DOI
https://doi.org/10.3390/app162211483
Primary Topic
Non-Destructive Testing Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Joint Inversion of Stress and Plastic Strain in X80 Pipeline Steel from Magnetic Measurements Using an MLP–GPR Model

Yi Li, Chuntian Zhao
Applied Sciences
Non-Destructive Testing Techniques
article

Joint Inversion of Stress and Plastic Strain in X80 Pipeline Steel from Magnetic Measurements Using an MLP–GPR Model

Yi Li, Chuntian Zhao
article en

Abstract

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.

Applied SciencesVol. 16(22)
Sichuan University (CN)
Non-Destructive Testing Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon