Hakimian, Soroosh, Bouzid, Abdel-Hakim et Hof, Lucas A..
2025.
« Corrosion type identification in flanged joints using recurrent neural networks on electrochemical noise measurements ».
npj Materials Degradation, vol. 9, nº 1.
Prévisualisation |
PDF
Bouzid-H-2025-31208.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY. Télécharger (4MB) | Prévisualisation |
Résumé
Bolted flanged joints are essential for connecting piping and process equipment but are vulnerable to localized corrosion that leads to sudden, unpredictable leaks. Electrochemical noise (EN) measurements can detect such corrosion, yet processing EN data is time-consuming and requires expertise. This study applies recurrent neural networks (RNNs) to automate corrosion type identification on flange surfaces using raw EN signals from spontaneous electrochemical reactions. In this work, supervised, hybrid, and unsupervised ML approaches are evaluated using experimentally obtained EN data. Among supervised models, the long short-term memory (LSTM) model achieves 93.62% accuracy. A hybrid method combining LSTM autoencoder features with a random forest classifier improves accuracy to 97.85%. An unsupervised method using LSTM autoencoder, principal component analysis, and k-means clustering also shows strong potential for real-time corrosion monitoring. Automated identification of corrosion types on flanged joints supports more effective material protection strategies, reducing the risk of failure in critical infrastructure.
| Type de document: | Article publié dans une revue, révisé par les pairs |
|---|---|
| Professeur: | Professeur Bouzid, Hakim Hof, Lucas |
| Affiliation: | Génie mécanique, Génie mécanique |
| Date de dépôt: | 30 juill. 2025 13:26 |
| Dernière modification: | 22 sept. 2025 12:47 |
| URI: | https://espace2.etsmtl.ca/id/eprint/31208 |
Actions (Authentification requise)
 |
Dernière vérification avant le dépôt |