Towards understanding and prediction of atmospheric corrosion of an Fe/Cu corrosion sensor via machine learning

Zibo Pei, Dawei Zhang*, Yuanjie Zhi, Tao Yang, Lulu Jin, Dongmei Fu, Xuequn Cheng, Herman A. Terryn, Johannes M.C. Mol, Xiaogang Li

*Corresponding author for this work

    Research output: Contribution to journalArticleScientificpeer-review

    17 Citations (Scopus)
    13 Downloads (Pure)

    Abstract

    The atmospheric corrosion of carbon steel was monitored by a Fe/Cu type galvanic corrosion sensor for 34 days. Using a random forest (RF)-based machine learning approach, the impacts of relative humidity, temperature and rainfall were identified to be higher than those of airborne particles, sulfur dioxide, nitrogen dioxide, carbon monoxide and ozone on the initial atmospheric corrosion. The RF model demonstrated higher accuracy than artificial neural network (ANN) and support vector regression (SVR) models in predicting instantaneous atmospheric corrosion. The model accuracy can be further improved after taking into consideration of the significant effect of rust formation on the sensor.

    Original languageEnglish
    Article number108697
    Number of pages9
    JournalCorrosion Science
    Volume170
    DOIs
    Publication statusPublished - 2020

    Keywords

    • Atmospheric corrosion
    • Corrosion monitoring
    • Corrosion prediction
    • Machine learning

    Fingerprint

    Dive into the research topics of 'Towards understanding and prediction of atmospheric corrosion of an Fe/Cu corrosion sensor via machine learning'. Together they form a unique fingerprint.

    Cite this