Data-driven pitting evolution prediction for corrosion-resistant alloys by time-series analysis

Corrosion initiation and propagation are a time-series problem, evolving continuously with corrosion time, and future pitting behavior depends closely on the past. Predicting localized corrosion for corrosion-resistant alloys remains a great challenge, as macroscopic experiments and microscopic theo...

Full description

Saved in:
Bibliographic Details
Published inNpj Materials degradation Vol. 6; no. 1; pp. 1 - 8
Main Authors Jiang, Xue, Yan, Yu, Su, Yanjing
Format Journal Article
LanguageEnglish
Published London Nature Publishing Group UK 11.11.2022
Nature Publishing Group
Nature Portfolio
Subjects
639/301/1023
639/301/1023/1026
Algorithms
Alloys
Artificial intelligence
Carbon steel
Chemistry and Materials Science
Cobalt base alloys
Corrosion and Coatings
Corrosion potential
Corrosion resistance
Corrosion resistant alloys
Data analysis
Datasets
Duplex stainless steels
Electrochemistry
Evolution
Genomes
Immersion tests (corrosion)
Localized corrosion
Machine learning
Materials Science
Neural networks
Pitting (corrosion)
Propagation
Saline solutions
Stainless steel
Structural Materials
Time dependence
Time series
Tribology
Online AccessGet full text

Cover

More Information
Summary:Corrosion initiation and propagation are a time-series problem, evolving continuously with corrosion time, and future pitting behavior depends closely on the past. Predicting localized corrosion for corrosion-resistant alloys remains a great challenge, as macroscopic experiments and microscopic theoretical simulations cannot couple internal and external factors to describe the pitting evolution from a time dimension. In this work, a data-driven method based on time-series analysis was explored. Taking cobalt-based alloys and duplex stainless steels as the case scenario, a corrosion propagation model was built to predict the free corrosion potential (E corr ) using a long short-term memory neural network (LSTM) based on 150 days of immersion testing in saline solution. Compared to traditional machine learning methods, the time-series analysis method was more consistent with the evolution of ground truth in the E corr prediction of the subsequent 70 days’ immersion, illustrating that time-series dependency of pitting propagation could be captured and utilized.
ISSN:2397-2106
2397-2106
DOI:10.1038/s41529-022-00307-4