Advancing LightGBM with data augmentation for predicting the residual strength of corroded pipelines

Machine learning methods have been widely applied in predicting the residual strength of corroded pipelines due to their powerful predictive capabilities. However, the effective application of these techniques is constrained by the limited availability of high-quality data, as traditional pipeline b...

Full description

Saved in:

Bibliographic Details
Published in:	Npj Materials degradation Vol. 9; no. 1; pp. 128 - 12
Main Authors:	Wang, Qiankun, Lu, Hongfang, Li, Fan, Cheng, Y. Frank
Format:	Journal Article
Language:	English
Published:	London Nature Publishing Group UK 22.10.2025 Nature Publishing Group Nature Portfolio
Subjects:	639/166 639/166/4073 639/166/988 639/4077 Accuracy Burst tests Chemistry and Materials Science Corrosion Corrosion and Coatings Data augmentation Datasets Electrochemistry Finite element analysis Generative adversarial networks Machine learning Materials Science Pipelines Real time Residual strength Structural Materials Tensile strength Tribology Wall thickness Yield stress
ISSN:	2397-2106, 2397-2106
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!