Machine learning modeling of time-dependent corrosion rates of carbon steel in presence of corrosion inhibitors

Using machine learning algorithms to predict failure on the PCB surface under corrosive conditions

“…Hyperparameters are important individual parameters for each algorithm to improve the model's performance, such as its complexity or its learning rate, and are commonly chosen based on some insights and trials for the training datasets [68]. This study has considered two main hyperparameters of each algorithm that are understood to have the most considerable influence on the algorithms' performance [69]. In contrast, for other hyperparameters, the default value is given by scikit-learn ML library of Python version 3 [70].…”

“…Kernel, gamma (γ), and regularization (C) are among the most important hyperparameters which directly affect the performance of SVM [75]. Radial basis function (RBF) kernel is the most preferred function to make proper separation when there is no prior knowledge of data [69]. C is greater than zero and tells the SVM optimization how much you want to avoid misclassification [75], where a smaller value of C allows the optimizer to ignore points close to the boundary and increases the margin.…”

Corrosion prediction of iron-based metals by the prophet model

“…Recently, machine learning (ML) as a powerful forecasting tool has been expanded to solve several corrosion-related problems [1][2][3]. Mohammadreza Aghaaminiha et al predicted the corrosion rate of carbon steel by using four machine learning (ML) models [1].…”

Data-driven pitting evolution prediction for corrosion-resistant alloys by time-series analysis

“…This has helped to predict the corrosion rate of low alloy steel and carbon steel, analyze the important factors that affect the corrosion rate, and forecast the local corrosion behavior of Co-based alloys under different compositions, preparation processes, temperatures, static corrosion environments, and corrosion times [22][23][24][25][26] provides a data-oriented overview of the rapidly growing research field covering ML applied to predicting electrochemical corrosion, which highlights assessing the predictive power of different approaches and elaborate on the current status of regression modeling for various corrosion topics 27 . Sharma et al have employed Random Forest method to model measurements of corrosion rates of carbon steel as a function of time when corrosion inhibitors are added in different dosage and doseschedules 28 . However, traditional statistical analysis methods, such as support vector machine, random forest and gradient boosting regression default to the assumption of independent and identical distribution among the data samples.…”