Developing Real-time Corrosion Monitoring: A Cutting-Edge Fusion of Electrochemical Noise Data and Machine Learning Techniques
No Thumbnail Available
Date
2024-12-20
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Curtin University
Abstract
The study addresses effectively monitoring and controlling the corrosion process using electrochemical noise analysis in different scenarios. It explores the challenges in feature extraction and analytical methods. It also proposes novel systematic approaches to overcome these challenges using deep learning models such as stochastic neighbour embedding (t-SNE) and principal component analysis (PCA). This work provides a potential quantification analysis method for online corrosion monitoring and control, widely considered the industry standard.
Description
The research thesis is now available on Curtin University's institutional repository, espace, under embargo until 18/06/2027.
You can access the thesis at https://hdl.handle.net/20.500.11937/98063.
Keywords
Carbon steels, deep learning approach, Discrete Wavelet Transform, Electrochemical noise, Localized corrosion, online corrosion monitoring, wavelet scalograms, wavelet transform analysis, Process monitoring
Citation
A. Abdulmutaali, Developing Real-time Corrosion Monitoring: A Cutting-Edge Fusion of Electrochemical Noise Data and Machine Learning Techniques. Curtin University, 2024.