Detection and Classification of Corrosion-related Damage Using Solitary Waves

Jalali, Hoda; Misra, Ritesh; Dickerson, Samuel J.; Rizzo, Piervincenzo

doi:10.1080/09349847.2022.2088913

Cited by 4 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the severity of corrosion progresses with time, more data are required for a regression model to estimate the corrosive state of a structure. Therefore, instead of estimating the quantitative dimension of corrosion, it is also common to classify the severity of corrosion into several categories, such as poor and fair [21][22][23]. Hence this paper aims to detect corrosion using eddy current testing and classify the corrosive state into a less corroded state (state-1) and a highly corroded state (state-2), using a generative model and a discriminative model.…”

Section: Introductionmentioning

confidence: 99%

Classification of Corrosion Severity in SPCC Steels Using Eddy Current Testing and Supervised Machine Learning Models

Xie,

Baskaran,

Ribeiro

et al. 2024

Sensors

View full text Add to dashboard Cite

Steel Plate Cold-Rolled Commercial (SPCC) steel is known to have long-term durability. However, it still undergoes corrosion when exposed to corrosive environments. This paper proposes an evaluation method for assessing the corrosion level of SPCC steel samples using eddy current testing (ECT), along with two different machine learning approaches. The objective is to classify the corrosion of the samples into two states: a less corroded state (state-1) and a highly corroded state (state-2). Generative and discriminative models were implemented for classification. The generative classifier was based on the Gaussian mixture model (GMM), while the discriminative model was based on the logistic regression model. The features used in the classification models are the peaks of the perturbated magnetic fields at two different frequencies. The performance of the classifiers was evaluated using metrics such as absolute error, accuracy, precision, recall, and F1 score. The results indicate that the GMM model is more conducive to categorizing states with higher levels of corrosion, while the logistic regression model is helpful in estimating states with lower levels of corrosion. Meanwhile, high classification accuracy can be achieved based on both methods using eddy current testing.

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of Corrosion Severity in SPCC Steels Using Eddy Current Testing and Supervised Machine Learning Models

Xie,

Baskaran,

Ribeiro

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…They allow identifying cracks, lapping, delamination, no-welding, porosity, leaks and other irregularities inside the tested elements (D. Woźniak and al) [7].In addition, ultrasonic waves are strongly reflected at boundaries where material properties change, and thus are often used for thickness measurements and crack detection [8].It is also use for the detection and classification of corrosion (H. Jalali and al 2022) [9]. Ultrasonic technique was used to determine thickness of the external piping of the secondary circuit of the heat exchanger to complete the indirect visual inspection.…”

Section: Introductionmentioning

confidence: 99%

Non-Destructive Testings of the Lifting Hook and Heat Exchanger Circuits of the Research Reactor TRICO II by Liquid Penetrant and Ultrasonics Testing

KAJA

KADIMA

MUJINGA

et al. 2023

Arab Journal of Nuclear Sciences and Applications

View full text Add to dashboard Cite

For its restart, components of research reactor TRICO II are subject of Non-Destructive Testings (NDT). Its STAHL hoist lifting hook 5000kg was inspected by colored liquid penetrant method for the research of surfaces defects, through white light in 750 lux. Result obtained indicates that it is not degraded. Indirect visual inspection by the multifunction video endoscope KC 350 was used to control internal wall of heat exchanger secondary circuit piping, some photos of internal wall were captured. The ultrasonic method consisted in measuring thickness of internal and external part of piping of the heat exchanger secondary circuit using thickness gauge ATG II with builtin 4.00mm calibration block. Results obtained by visual inspection showed the presence of rust and corrosion. The ultrasonic method showed thickness variation on controlled surface due to deposit rust (high value of thickness) and corrosion (low value of thickness). This work is carried out as part of maintenance, periodic testing and inspection for proper management of the TRICO II reactor.

show abstract