Current Volume 9
Machine Learning for Predicting Corrosion Rate and Inhibitor Efficiency of an Optimized Ternary Inhibitor Blend on Variable Temperatures
Abstract
Using weight-loss research, statistical exploration, and predictive modeling to examine how carbon steel corrodes in acidic conditions; and assesses the effectiveness of organic corrosion inhibitors. The experimental controlled settings were; different exposure durations (25-125 h), and temperatures (40-80 °C), while inhibitor doses ranging from 0 to 250 ppm. Further optimization was carried out for the best inhibitor blend; utilizing a design of experiments (DoE) method including Bitter Leaf Extract, Plantain Peel Extract, and Snail Water. The corrosion rate for the unconstrained (blank) samples exhibits near-exponential behavior and rises strongly with temperature, according to the results. Thermal instability is indicated by the inhibitor's excellent efficacy at moderate temperatures and sharp drop at 70 °C. Time-dependent deterioration of the inhibitor's protective coating is highlighted by the fact that, at constant temperature, corrosion rate rises with exposure time while inhibitor efficiency progressively declines. Higher concentrations continuously enhanced protection in both datasets, with the maximum efficiency occurring at 200-250 ppm. The DoE-based blend optimization indicated substantial interactions among inhibitor components, with Bitter Leaf contributing most to corrosion reduction, while excess Plantain Peel promoted corrosion. Snail water had little direct impact, but when mixed with other extracts, it improved performance in a synergistic way. It predicts corrosion rate from experimental factors by Ridge, Random Forest, Polynomial Regression, Linear Regression, and MLP Neural Network were used. The highest accuracy was attained by Random Forest and Polynomial Regression (R2=0.90-0.97). It was a model-driven and experimental insight for the best inhibitor dosage, exposure limits, and blend formulation. It supports for data-driven corrosion control in industrial systems that operate in settings that are both temporal and thermal variable.
Keywords
Corrosion, Inhibitors, Modeling, Optimization, Regression
Citations
IRE Journals:
Okubo, Keneotubo Ekromokumoh , Dio, Eres, Suoware, Pereowei Bernard "Machine Learning for Predicting Corrosion Rate and Inhibitor Efficiency of an Optimized Ternary Inhibitor Blend on Variable Temperatures" Iconic Research And Engineering Journals Volume 9 Issue 11 2026 Page 4929-4937 https://doi.org/10.64388/IREV9I11-1718510
IEEE:
Okubo, Keneotubo Ekromokumoh , Dio, Eres, Suoware, Pereowei Bernard
"Machine Learning for Predicting Corrosion Rate and Inhibitor Efficiency of an Optimized Ternary Inhibitor Blend on Variable Temperatures" Iconic Research And Engineering Journals, 9(11) https://doi.org/10.64388/IREV9I11-1718510
About IRE Journals
IRE Journals is an open access online journals established with an aim to publish high quality of research work in various diciplines. We have more than 6 years in publications. Over 2500+ papers already published.
Important Links
For Authors
Volume 8:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 7:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 6:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 5:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 4:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 3:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12