Advanced Machine Learning Techniques for Corrosion Rate Estimation and Prediction in Industrial Cooling Water Pipelines
Sensors · 31.05.2024 · 24 (11) · 3564
DOI: 10.3390/s24113564 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 31.05.2024. Verfasst von Desiree Ruiz und 4 weiteren Autor:innen. Beteiligte Einrichtung: Centro Tecnológico de Componentes-CTC, Scientific and Technological Park of Cantabria (PCTCAN), 39011 Santander, Spain. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Economy, Industry and Competitiveness, Spain, Ministry of Economy, Industry and Competitiveness and the State Research Agency.
Abstract (Originalsprache)
This paper presents the results of a study on data preprocessing and modeling for predicting corrosion in water pipelines of a steel industrial plant. The use case is a cooling circuit consisting of both direct and indirect cooling. In the direct cooling circuit, water comes into direct contact with the product, whereas in the indirect one, it does not. In this study, advanced machine learning techniques, such as extreme gradient boosting and deep neural networks, have been employed for two distinct applications. Firstly, a virtual sensor was created to estimate the corrosion rate based on influencing process variables, such as pH and temperature. Secondly, a predictive tool was designed to foresee the future evolution of the corrosion rate, considering past values of both influencing variables and the corrosion rate. The results show that the most suitable algorithm for the virtual sensor approach is the dense neural network, with MAPE values of (25 ± 4)% and (11 ± 4)% for the direct and indirect circuits, respectively. In contrast, different results are obtained for the two circuits when following the predictive tool approach. For the primary circuit, the convolutional neural network yields the best results, with MAPE = 4% on the testing set, whereas for the secondary circuit, the LSTM recurrent network shows the highest prediction accuracy, with MAPE = 9%. In general, models employing temporal windows have emerged as more suitable for corrosion prediction, with model performance significantly improving with a larger dataset.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Centro Tecnológico de Componentes-CTC, Scientific and Technological Park of Cantabria (PCTCAN), 39011 Santander, Spain.
ORCID-Profile: Desiree Ruiz, Abraham Casas, Cesar Adolfo Escobar
Förderung
- Ministry of Economy, Industry and Competitiveness, Spain
- Ministry of Economy, Industry and Competitiveness and the State Research Agency
Zitieren
APA
Ruiz, D., Casas, A., Escobar, C. A., Perez, A., & Gonzalez, V. (2024). Advanced Machine Learning Techniques for Corrosion Rate Estimation and Prediction in Industrial Cooling Water Pipelines. Sensors, 24(11), 3564. https://doi.org/10.3390/s24113564
Vancouver
Ruiz D, Casas A, Escobar CA, Perez A, Gonzalez V. Advanced Machine Learning Techniques for Corrosion Rate Estimation and Prediction in Industrial Cooling Water Pipelines. Sensors. 2024;24(11):3564. doi:10.3390/s24113564
BibTeX
@article{Ruiz2024,
author = {Ruiz, Desiree and Casas, Abraham and Escobar, Cesar Adolfo and Perez, Alejandro and Gonzalez, Veronica},
title = {Advanced Machine Learning Techniques for Corrosion Rate Estimation and Prediction in Industrial Cooling Water Pipelines},
journal = {Sensors},
year = {2024},
volume = {24},
number = {11},
pages = {3564},
doi = {10.3390/s24113564}
}
EUVIMED