Corrosion Assessment of Carbon Steel Using Texture and Color Features

Li, Jiacheng; Liu, Haoting; Wu, Weijie; Yang, Shaolong; Sheng, Liang

doi:10.1109/aemcse50948.2020.00079

Cited by 3 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, the image is transformed into a gray-level co-occurrence matrix. The statistical characteristics such as mean value, standard deviation, energy and entropy can be extracted to quantitatively characterize the severity or complexity of corrosion damage [20].…”

Section: Gray-level Co-occurrence Matrixmentioning

confidence: 99%

Intelligent Evaluation of Marine Corrosion of Q420 Steel Based on Image Recognition Method

Wang

Li²,

Jiang

et al. 2022

Coatings

View full text Add to dashboard Cite

Marine engineering materials are prone to serious corrosion damage, which affects the efficiency and reliability of marine equipment. The diversity of corrosion morphology makes it difficult to achieve the quantification and standardization of the microscopic local information on the corroded surface, which is of great significance to reveal the multi-scale corrosion mechanism. In this paper, an image intelligent recognition method for the corrosion damage of Q420 steel in seawater is established, which is based on the gray level co-occurrence matrix, binary image method and fractal model. Through the feature extraction of corrosion morphology, the quantitative analysis of corrosion morphology and the microscopic evaluation of corrosion characteristics are achieved. The image recognition data are consistent with the electrochemical result for most cases, which confirms the validity of this image intelligent recognition method. The average gray value and energy value of corrosion morphology reduces with the Cl− concentration, indicating that the corrosion damage aggravates gradually. The increasing standard deviation and entropy reflects that the randomness of the pit distribution increases. The pitting ratio increases from 20.19% to 51.64% as the Cl− concentration increases from 50% to 200% of the standard solution. However, there exists a discrepancy for high Cl− concentration because of the irregular corrosion morphology and various pit depth. The fractal dimension increases with the complexity of the corroded surface at low Cl− concentration, but the fractal dimension decreases at high Cl− concentration because the corrosion complexity is interfered by the interconnection of corrosion holes due to the accelerated pit evolution.

show abstract

Section: Gray-level Co-occurrence Matrixmentioning

confidence: 99%

Intelligent Evaluation of Marine Corrosion of Q420 Steel Based on Image Recognition Method

Wang

Li²,

Jiang

et al. 2022

Coatings

View full text Add to dashboard Cite

show abstract

“…Valeti and Pakzad proposed a combination of unsupervised and supervised classification methods to detect and segment the corroded regions in power transmission tower images using various color features of the image [13]. Li et al proposed a method using image processing techniques and a support vector machine for the corrosion evaluation of carbon steel and achieved an accuracy of 97.5% [14]. Qian et al proposed a method based on fractal theory and binary image processing techniques to extract the features and calculate the corresponding grade of corrosion damage of AerMet100 steel [15].…”

Section: Introductionmentioning

confidence: 99%

Corrosion grade recognition for weathering steel plate based on a convolutional neural network

Wang¹,

Shen²,

Wu³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

For the maintenance of weathering steel structure facilities, it is necessary to evaluate the corrosion grade of the rust layer on the surface regularly. At present, the corrosion grade classification of weathering steel is mainly based on the human-eye inspection. In this paper, a deep learning method using a convolutional neural network for evaluating the corrosion grade of weathering steel is proposed to save time and manpower. Firstly, the image dataset of the corrosion steel plate was established using salt spray tests. Then, a CNN architecture named VGG-Corrosion was designed to evaluate the corrosion grade of the corroded steel plate. The effect of the learning rate, transfer learning, and batch size was also investigated to clarify the best hyperparameter configurations to train a powerful corrosion grade classification model. Under the best combination of considered hyperparameters, the mean average accuracy for the corrosion grade evaluation of the test results is 90.96%. The testing results indicated that the CNN based corrosion grade recognition for weath-ering steel plate is prospective, which would be helpful for safety evaluation of steel structures.

show abstract

“…In general, the laser and its optic path include the laser, the beam expander and collimator, and the scanning mirrors. The cleaning effect perception sensor is always designed by an imaging sensor because of its capture ability for rich details [5]. Lastly, both the laser and the imaging sensor are installed in an electronic movement guideway.…”

Section: Introductionmentioning

confidence: 99%

“…The GLCM entropy, the GLCM contrast, the GLCM cluster prominence, and the GLCM homogeneity are all utilized. Equations ( 3), ( 4), (5), and (6) show their computational methods. The B The corrosion has happened, parts of the oxide layer have fallen off, and some small corrosion blocks can be observed.…”

mentioning

confidence: 99%

Investigation of Laser Power Output and Its Effect on Raman Spectrum for Marine Metal Corrosion Cleaning

Liu

Xue

et al. 2019

Energies

Self Cite

View full text Add to dashboard Cite

The relationship between the laser power output and its effect on Raman spectrum is investigated for a laser cleaning application of marine metal corrosion processing. First, an image feature based on a corrosion degree evaluation is implemented before cleaning. The image features include texture coarseness, texture entropy, texture intensity, texture contrast, the texture’s cluster degree, and texture homogeneity. To decrease the image feature dimension for a convenient application, the Analytic Hierarchy Process (AHP) method is used to estimate the weight of each feature. Then the linear weighted sum of image features can be computed to get only one evaluation result. Second, a series of laser power outputs are implemented for the cleaning application under a typical corrosion degree. Then the analysis results of Raman spectrum can be obtained. The analyzed spectrum results include the corrosion components and their contents. Lastly, the relationship between laser power output and Raman spectrum under a typical initial corrosion degree can be constructed. This research study can build the prediction result of the cleaning effect map for the workpiece and guide the secondary processing of metal surface cleaning.

show abstract

Corrosion Assessment of Carbon Steel Using Texture and Color Features

Cited by 3 publications

References 10 publications

Intelligent Evaluation of Marine Corrosion of Q420 Steel Based on Image Recognition Method

Intelligent Evaluation of Marine Corrosion of Q420 Steel Based on Image Recognition Method

Corrosion grade recognition for weathering steel plate based on a convolutional neural network

Investigation of Laser Power Output and Its Effect on Raman Spectrum for Marine Metal Corrosion Cleaning

Contact Info

Product

Resources

About