A novel assessment method for residual strength of CO2 pipelines with multiple defects based on RF-MLP

Yan Li, Zhanfeng Chen, Wen Wang, Ke Han, Yi Shuai and Ganxun Wang

Reliability Engineering and System Safety, 2025, vol. 261, issue C

Abstract: CO2 pipelines play a crucial role in Carbon Capture, Utilization, and Storage (CCUS), making the accurate prediction of the residual strength of pipelines with multiple corrosion defects essential for assessing reliability and remaining service life. This study proposes an RF-MLP method, where Random Forest (RF) is employed for feature analysis to identify the most influential factors affecting corrosion defects, and Multi-Layer Perceptron (MLP) is used for predicting the effective depth of corrosion defects. A finite element model was established to generate a dataset for training and validation. Through comparison with Support Vector Machine (SVM), MLP and Kriging model was ultimately selected as the optimal prediction model due to its superior performance. The RF-MLP approach was validated against experimental data, demonstrating high accuracy in predicting both the effective depth of defects and the residual strength of pipelines. This method provides an innovative and reliable approach to assessing the structural integrity of pipelines with corrosion defects in CCUS systems.

Keywords: CO2 pipelines; Multiple corrosion defects; RF-MLP; Residual strength (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0951832025002893
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:reensy:v:261:y:2025:i:c:s0951832025002893

DOI: 10.1016/j.ress.2025.111088

Access Statistics for this article

Reliability Engineering and System Safety is currently edited by Carlos Guedes Soares

More articles in Reliability Engineering and System Safety from Elsevier
Bibliographic data for series maintained by Catherine Liu ().