Quantitative Characterization of the Spatial Distribution of Corrosion Pits Based on Nearest Neighbor Analysis

Abass, Adeyinka; Wada, Kentaro; Matsunaga, Hisao; Remes, Heikki; Vuorio, Tiina

doi:10.5006/3551

Cited by 6 publications

(1 citation statement)

References 29 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For localized corrosion such as pitting and crevice corrosion, precise understand of the conditions at every point on a metal surface is unlikely, and statistic techniques thereby become necessary for the quantitative characterization of the corrosion processes. Therefore, many studies are devoted to the study of statistical features of corrosion pits including spatial statistics [21]. However, the microstructures and corrosion processes are usually exhibiting scale-dependent features [22,23] and the high-resolution images with small field-of-view used in the traditional analysis can only provide limited information for typical corrosion pits.…”

Section: Introductionmentioning

confidence: 99%

Multiscale Statistical Analysis of Massive Corrosion Pits Based on Image Recognition of High Resolution and Large Field-of-View Images

Wang

Tian

2020

Materials

View full text Add to dashboard Cite

In the present study, a new multiscale method is proposed for the statistical analysis of spatial distribution of massive corrosion pits, based on the image recognition of high resolution and large field-of-view (montage) optical images. Pitting corrosion for high strength pipeline steel exposed to sodium chloride solution was observed using an optical microscope. Montage images of the corrosion pits were obtained, with a single image containing a large number of corrosion pits. The diameters and locations of all the pits were determined simultaneously using an image recognition algorithm, followed by statistical analysis of the two-dimensional spatial point pattern. The multiscale spatial distributions of pits were analyzed by dividing the montage image into a number of different windows. The results indicate the clear dependence of distribution features on the spatial scales. The proposed method can provide a better understanding of the pit growth from the perspective of multiscale spatial evolution.

show abstract

Section: Introductionmentioning

confidence: 99%

Multiscale Statistical Analysis of Massive Corrosion Pits Based on Image Recognition of High Resolution and Large Field-of-View Images

Wang

Tian

2020

Materials

View full text Add to dashboard Cite

show abstract

Gravimetric inhibition efficiency prediction model of AA7075-T7351 alloy using Treculia africana extract in 1.0 M HCl through input feature optimization

Udensi,

Ejelonu

2024

Surf. Sci. Tech.

View full text Add to dashboard Cite

The applications of four machine learning (ML) algorithms, namely: Support Vector Regressor (SVR), Extreme Gradient Boosting (XGBoost), Least absolute shrinkage and selection operator (Lasso), and Ridge, in predicting the corrosion inhibition efficiency (IE) of Treculia africana (TA) leaves extract on AA7075-T7351 alloy, in corrosive 1.0 M HCl environment, with a small (42) sample space, have been studied. Time and resource constraints in traditional corrosion study methods have been avoided through feature engineering to expedite prediction process. The dominant features, which affected the IE, were done through feature importance and selection processes using pair plot matrix of features and Kendall correlation etc., to remove redundant features. The results in the form of data visualization, feature importance, and the performance of each algorithm on the test set were explicitly depicted. The evaluation metrics, including coefficients of determination (R2) and root mean square error (RMSE), validated the efficacy of the models in predicting the IE of TA on AA7075-T7351 in 1.0 M HCl environments. Ridge model demonstrated superior accuracy, with R2 score of 0.972, particularly in handling the highly correlated dataset used in this study. SVR followed closely in performance (0.969). XGBoost proved reliable at R2 score of 0.953. Lasso with R2 of 0.952 was the least of the four models, due to its random feature selection method. The RMSE scores corroborated the prediction accuracies with values; 4.145, 4.408, 5.138 and 5.462 respectively. This study revealed the viability of using the four machine learning algorithms in potential generalization ability of IE prediction accuracy, while offering an efficient and accurate alternative to traditional methods. Graphical Abstract

show abstract

Bibliography

2024

Corrosion and Corrosion Protection of Wind Power Structures in Marine Environments

View full text Add to dashboard Cite

Quantitative Characterization of the Spatial Distribution of Corrosion Pits Based on Nearest Neighbor Analysis

Cited by 6 publications

References 29 publications

Multiscale Statistical Analysis of Massive Corrosion Pits Based on Image Recognition of High Resolution and Large Field-of-View Images

Multiscale Statistical Analysis of Massive Corrosion Pits Based on Image Recognition of High Resolution and Large Field-of-View Images

Gravimetric inhibition efficiency prediction model of AA7075-T7351 alloy using Treculia africana extract in 1.0 M HCl through input feature optimization

Bibliography

Contact Info

Product

Resources

About