Corrosion Detection Research Articles

Deep Learning-Based Decision Support System for Automatic Detection and Grading of Surface Corrosion on Galvanized Steel Sheets

Corrosion in the sheets produced leads to significant material losses, including the loss of resources, capital, labor, energy and knowledge. Corrosion control is significant for sheets produced and sent to customers in iron and steel factories. Surface corrosion testing of produced sheets and the accurate detection of corrosion levels are of great importance. The corrosion detection process for sheets in steel factories is performed visually with the naked eye. This is a subjective and time-consuming method. Identifying corrosion damage by visual detection and accurately determining the type and extent of corrosion requires expertise. Wrong decisions at this stage lead to losses during the production phase. Therefore, there is a need for systems that can automate this process and make it human-independent. In this study, a decision support system was designed to automatically detect the level of corrosion in galvanized sheets using convolutional neural networks. The average accuracy of the system is 97.5%, the average precision is 0.98, the average recall is 1 and the average F1 score is 0.99. The results we obtained indicate that a successful system has been developed for the detection and determination of corrosion levels. The high performance of the convolutional neural network models used for corrosion detection supports the practical applicability of the developed system. This system will increase the reliability and efficiency of industrial processes by enabling the accurate and automatic classification of corrosion. This system, which meets a significant need in this area for industrial organizations, reduces production costs and also makes the corrosion detection process more consistent and faster.

Quantitative Advantages of Corrosion Sensing Using Fluorescence, Microscopy, and Single-Molecule Detection.

The corrosion of metals and alloys is a fundamental issue in modern society. Understanding the mechanisms that cause and prevent corrosion is integral to saving millions of dollars each year and to ensure the safe use of infrastructure subject to the hazardous degrading effects of corrosion. Despite this, corrosion detection techniques have lacked precise, quantitative information, with industries taking a top-down, macroscale approach to analyzing corrosion with tests that span months to years and yield qualitative information. Fluorescence, a well-established optical method, can fill the niche of early-stage, quantitative corrosion detection and can be employed for both bulk and localized testing over time. The latter, fluorescence microscopy, can be pushed to greater levels of detail with single-molecule microscopy, achieving nanometer spatial and subsecond temporal resolutions of corrosion that allow for the extraction of dynamic information and kinetics. This review will present how fluorescence microscopy can provide researchers with a molecular view into the chemical mechanisms of corrosion at interfaces and allow for faster, quantitative studies of how to detect and prevent corrosion.

Internal inspection method for crack defects in ferromagnetic pipelines under remanent magnetization

Magnetic flux leakage (MFL) testing is effective in detecting corrosion in ferromagnetic pipelines. However, the MFL generated at the crack is highly weak and is easily drowned in the strong background magnetic field and difficult to detect. Therefore, this paper creatively proposes a remanent magnetic flux leakage (RMFL) detection method. This method utilizes the hysteresis state of the pipeline after MFL detection and identifies crack defects by collecting the remanent magnetic flux density near the inner wall surface of the pipeline. The remanent magnetic field distribution near the pipeline surface is examined at different crack sizes, magnetization speeds, and lift-off values via theoretical analysis, finite element simulation, and experimental verification. In addition, experiments have demonstrated that in terms of crack detection capability, RMFL is superior to MFL. Therefore, adding a RMFL measurement module to the conventional MFL detector has important practical value. It can realize the targeted collaborative application of these two technologies, namely the synchronous detection of corrosion and crack defects, which greatly improves the detection coverage and detection efficiency.

Detection of corrosion effects on prestressed concrete bridge deck slabs from the champlain bridge through non‐destructive testing techniques

AbstractAs aging infrastructures raise public concerns, evaluating their performance is crucial for maintaining structural integrity, especially for corroding prestressed concrete members. These structures may experience substantial tendon cross‐sectional area loss before any visible deterioration becomes detectable. While various non‐destructive techniques (NDT) have proven effective in labs, correlating corrosion‐induced damage in field members remains a challenge. Establishing these correlations is key for understanding the overall performance of aging structural concrete elements and ensuring their continued safe operation through non‐invasive means. This paper investigates various NDTs on a concrete bridge deck, aiming to correlate results. Visual inspection, Schmidt rebound hammer, Ultrasonic Pulse Velocity (UPV), corrosion detection techniques, Ground Penetrating Radar (GPR), Ultrasonic Pulse Echo (UPE), and Impact Echo (IE) methods are evaluated for detecting concrete deck damage. Results show the methods' capabilities in detecting defects to a certain extent, highlighting their potential in assessing aging concrete infrastructures.

Corrosion prediction model for long-distance pipelines based on NLFE-NGO-ELM

Abstract To improve the accuracy of buried pipeline corrosion rate prediction, we developed a Northern Goshawk Optimization-based Extreme Learning Machine (NLFE-NGO-ELM) model enhanced by Non-linear Feature Expansion. Feature selection was used to expand the small dataset and reduce the dimensionality of factors affecting pipeline corrosion. The Northern Goshawk algorithm was used, and 106 sets of pipeline external corrosion detection data were simulated in MATLAB as a case study. The ELM optimizer was analyzed using Grey Wolf Optimization (GWO-ELM), Northern Goshawk Optimization (NGO-ELM), and BP optimization as comparison models. Using NLFE-NGO-ELM significantly improved the model's prediction accuracy and speed. The NGO-ELM model was applied to predict the corrosion rates of 21 pipelines, achieving an absolute error of only 2.40% and an R value of 0.97255, surpassing the predictive performance of NGO-BP and GWO-ELM models. These results indicate that the current model exhibits superior learning performance and stronger fitting capabilities.

An Experimental Assessment Using Acoustic Emission Sensors to Effectively Detect Surface Deterioration on Steel Plates

Acoustic emission (AE) testing is used for the continuous evaluation of structural integrity and the monitoring of damage evolution in structural components and materials. During operation, the environmental and loading conditions of metal structures can result in corrosion and surface wear damage. The early detection of surface degradation flaws is crucial, as they can serve as local stress concentration points, leading to crack initiation and failure. In this work, the effectiveness of AE in monitoring corrosion and surface wear flaw formation was experimentally evaluated. AE sensors were installed on steel test plates during the artificial induction of corrosion and surface wear in order to detect and record the generated AE signals. Corrosion-related AE signals typically exhibit low amplitude, count, and energy values. The direct detection of active corrosion can be challenging in noisy environments, but it can be carried out under certain conditions using dedicated AE sensor groups. Surface-wear-related AE signals exhibit high amplitude, energy, and count values, with long duration values that are associated with wear and grinding conditions. It was found that AE sensors can be utilised to detect corrosion and surface degradation events. The effectiveness of the AE method in detecting surface degradation in noisy environments can be improved by implementing a filtering methodology. This will limit the recording of noise-related signals that can mask out actual surface degradation AE events.

Comparative Analysis of Improved YOLO v5 Models for Corrosion Detection in Coastal Environments

Comparative Analysis of Improved YOLO v5 Models for Corrosion Detection in Coastal Environments

Methods for Corrosion Detection in Pipes Using Thermography: A Case Study on Synthetic Datasets

This study reviews advanced methods for corrosion detection and characterization in pipes using thermography, with a focus on addressing the limitations posed by small datasets. Thermography captures temperature distributions on the surface of pipes to identify subsurface defects. The challenges of sequential data processing, neural network performance, feature extraction, and dataset size are discussed, with proposed solutions such as advanced algorithms, feature selection techniques, and data augmentation. Given the significant gap in the current literature, there is a need for larger, more diverse datasets to train more robust and accurate machine learning models. A case study combining experimental data with Finite Element Method (FEM) simulations demonstrates that augmenting datasets with synthetic data significantly improves defect detection accuracy. These findings highlight the potential of integrating thermography with machine learning to enhance defect detection, providing insights for future research and practical applications.

Study on the initial corrosion characteristics of weathering steel bridges with corrugated steel webs

In this study, the characteristics and influencing factors of the early corrosion evolution process of the weathering steel (WS) bridge in northwest China were examined, revealing the seldom-studied corrosion evolution law of the corrugated web of weathering steel. The corrosion losses and average corrosion thickness of WS bridge components were measured and evaluated. The results revealed that compared with traditional flat steel webs, the corrosion of corrugated steel webs was enhanced in the vertical direction and at the wave peak, and resulted in a more complex corrosion pattern. The trend of the rust layer on the inner and outer surfaces of the box girder is related to the stage characteristics of the corrosion products. The appearance of microscopic characteristics of the rust layer is periodic, with the rust layer thickness, colour, and particle size varying with the bridge’s location. The development of the corrosion pit followed a lognormal distribution, and the corrosion rate was balanced in the radial and depth directions. These results can serve as a basis for designers or inspectors to design WS bridge structures, select correct corrosion allowances, and improve corrosion monitoring and detection techniques.

Ultrasonic imaging of concrete-embedded corroded steel liners using linear and nonlinear evaluation

ABSTRACT This study explores the efficacy of horizontally polarised shear (SH) waves in ultrasonic inspection of concrete-embedded steel liner plates, focusing on corrosion detection. SH-waves are found to significantly improve the localisation and potential dimensional assessment of embedded plate-like structures compared to compressional (P) waves, as evidenced by SH C-scans. Anomalies corresponding to severe corrosion are discernible in SH C-scans, whereas they are minimally visible in P-wave scans. Nonlinear evaluation explores harmonic-based imaging, including second harmonic generation (SHG) and third harmonic generation. Nonlinear SH-wave evaluation accurately locates the most severely corroded embedded plate, whereas comparative P-wave evaluations fail. However, potential FFT sidelobe contamination in the results warrants consideration. These results suggest a promising use for nonlinear waveform distortion in SH-wave-based corrosion detection though conclusive evidence of the source of SHG is uncertain. Experiments utilised an automatic scanner system for consistent control. The concrete specimen investigated herein contained pre-corroded plates which hint at heightened nonlinear effects when corrosion occurs post-embedment due to corrosion-induced cracking. These findings encourage further investigation into SH-waves for nonlinear ultrasonic detection of concrete-embedded steel liner plates and the development of instrumentation tailored to such methods.

Corrosion and Protection of Chinese Bronze Relics: A Review

The corrosion problem affecting ancient Chinese bronze relics and the protective measures required post-excavation are crucial for the study of historical cultural heritage and for ensuring heritage revitalization and sustainable development. This work includes a statistical analysis, clusters information, and thoroughly examines international research on bronze relic corrosion and protection. It delves into the timeline and trends of research, the main countries leading the research efforts, the research content, and the relationships between these factors. A comprehensive review is provided on the corrosion principles, materials, detection methods, and protection techniques for bronze. The study explores the corrosion principles and processes of bronze from a materials science perspective both before and after excavation. It summarizes non-destructive detection methods and examines specific factors that influence corrosion. Furthermore, the article reviews current corrosion protection methods for bronze and related protection materials, including commonly used strategies such as surface corrosion inhibitors and organic resin coatings for protection. It also discusses the potential application of advanced corrosion protection methods in the realm of metal materials in recent years to safeguard bronze. Proposing innovative solutions, the study suggests the possibility of constructing biomimetic superhydrophobic surfaces to create a barrier isolating humid air from contacting bronze materials, thereby reducing the adhesion of corrosive media to the substrate and significantly diminishing the likelihood of corrosion. In conclusion, the article looks towards the future, considering the challenges and potential development directions for the corrosion protection of bronze and related protection materials.

Composite fluorescence probe towards a smart coating for early corrosion detection of carbon steel

Herein, a composite fluorescent probe was developed as a smart indicator in acrylic resin-based coatings for the early detection of steel corrosion. The Fe3+-sensitive Rhodamine B derivative probe (Rxbxja) was synthesized, and the SiO2 nanoparticle-supported probe S-Rxbxja was prepared through the hydrolysis of tetraethyl orthosilicate (TEOS). The successful synthesis of S-Rxbxja was confirmed using a variety of techniques i.e. SEM and FTIR. A fluorescence microscope was utilized to assess the self-reporting performance of coatings. EIS and seawater immersion tests were employed to evaluate the corrosion resistance of the coating. The fluorescence test results revealed the absence of premature fluorescence in the composite coating, owing to the exceptional compatibility between S-Rxbxja and the coating. The scratched area in the 0.5 wt% sensor-doped coatings exhibited fluorescent and colorimetric dual-channel signals after soaking in 3.5 wt% NaCl solution for 2 h before any visible corrosion phenomenon. The EIS results demonstrated that the |Z|0.01Hz value of composite coating maintained 107 Ω cm2 even after being immersed in a 3.5 wt% NaCl solution for 7 days, indicating the excellent anti-corrosion properties of the S-Rxbxja coating. Moreover, mechanical property tests showed that the S-Rxbxja coating had excellent mechanical properties due to the introduction of SiO2 nanoparticles.

Artificial intelligence-based ship hull plate corrosion monitoring using Convolutional Neural Network (CNN): comparison of YOLOv8 and Detectron2 architecture models

ABSTRACT Detecting and monitoring structural damage is crucial to prevent significant damage to ship structures caused by corrosion. This study aims to measure the performance of corrosion detection using Convolutional Neural Networks (CNN) by comparing YOLOv8 and Detectron2 models analyzed at various data augmentation settings. The results show that Detectron2 with the ResNet101 backbone performs better than Detectron2 ResNet50 and YOLOv8 models. The result found that applied augmentation data settings, such as vertical & horizontal flip, rotation, and increasing & decreasing colour saturation, highlight their importance in training robust corrosion detection models. These findings contribute to developing corrosion detection methods, showing that the Detectron2 model with instance segmentation can overcome the complexity and variety of corrosion shapes more effectively than YOLOv8 model. The instance segmentation model has proven to be the more effective CNN model for detecting abstract objects, such as corrosion damage in ship hulls.

Corrosion degree detection of ferromagnetic materials using a hybrid machine learning approach and self-magnetic flux leakage technology

Corrosion of ferromagnetic materials can lead to performance degradation or even failure in engineering structures. Therefore, detecting the degree of corrosion in these materials is crucial. Traditional detection methods are primarily manual and lack precision, highlighting the need for developing automated, high-precision detection techniques. In this paper, we developed a novel self-magnetic flux leakage (SMFL) scanner. We enhanced the Marine Predator Algorithm (MPA) by integrating Chaos Opposition (CO) and Group Learning (GL), resulting in the COGL-MPA-XGB model. This model optimizes Extreme Gradient Boosting parameters for accurate corrosion prediction, achieving a 96% coefficient of determination (R2) and a mean error of 1.87. We tested the method on 170 rod-shaped steel samples with varying degrees of corrosion, evaluating its effectiveness through ablation experiments and comparisons with three other machine learning models. The results show that the combined SMFL and hybrid model strategy reduces the maximum detection error by 73.7% and offers a new perspective for quantitative corrosion detection.

Machine learning-based acoustic emission technique for corrosion-induced damage monitoring in reinforced concrete structures

Early-stage detection of corrosion in reinforcement embedded inside concrete, generally considered as the major problem in structures under extreme marine environments, can help to schedule timely maintenance/repair and to avoid any catastrophic failure. However, quantitative evaluation of the degree of deterioration, especially at a very early stage, i.e., before its appearance on the surface, is extremely difficult due to the complex process in heterogeneous material. This study aims to characterize the critical damage stages in reinforced concrete specimens under accelerated conditions using the Acoustic emission (AE) damage quantification methods supported by machine learning (ML) techniques. The stages of corrosion-induced damage are predicted by a two-step predictive model that involve both regression and classification tasks. Three supervised regression models — support vector regression (SVR), relevance vector machine (RVM) and kernel ridge regression (KRR) —are first adopted to evaluate the amount of current. Then the output from regression model is given as an input to the classification problem to predict the discrete class label output. Characterized damage stages are validated based on mass loss and crack width measurements. The results show that the corrosion initiation (at day 3) and crack formation (at day 7) can be determined from the sudden change in acoustic parameters. Further, a double layer (supervised-unsupervised) model is proposed which is found be more effective in correctly detecting the progression of damage. The findings indicate that the proposed approach that combines corrosion detection by analysing AE signals with ML technique can accurately and robustly predict corrosion severity.

Corrosion image classification method based on EfficientNetV2

Corrosion is one of the key factors leading to material failure, which can occur in facilities and equipment closely related to people's lives, causing structural damage and thus affecting the safety of people's lives and property. To identify corrosion more effectively across multiple facilities and equipment, this paper utilizes a corrosion binary classification dataset containing various materials to develop a CNN classification model for better detection and distinction of material corrosion, using a methodological paradigm of transfer learning and fine-tuning. The proposed model implementation initially uses data augmentation to enhance the dataset and employs different sizes of EfficientNetV2 for training, evaluated using Confusion Matrix, ROC curve, and the values of Precision, Recall, and F1-score. To further enhance the testing results, this paper focuses on the impact of using the Global Average Pooling layer versus the Global Max Pooling layer, as well as the number of fine-tuning layers. The results show that the Global Average Pooling layer performs better, and EfficientNetV2B0 with a fine-tuning rate of 20 %, and EfficientNetV2S with a fine-tuning rate of 15 %, achieve the highest testing accuracy of 0.9176, an ROC-AUC value of 0.97, and Precision, Recall, and F1-Score values exceeding 0.9. These findings can be served as a reference for other corrosion classification models which uses EfficientNetV2.

Application of Machine Learning and Deep Learning Techniques for Corrosion and Cracks Detection in Nuclear Power Plants: A Review

Application of Machine Learning and Deep Learning Techniques for Corrosion and Cracks Detection in Nuclear Power Plants: A Review

On-Site Electrochemical Detection of Corrosion in Substation Grounding System

On-Site Electrochemical Detection of Corrosion in Substation Grounding System

In-situ EIS for corrosion detection in LiFSI-based Li-ion batteries

LiFSI-based electrolytes are frontiers amongst candidates for future generation of high-voltage and high-temperature capable Li-ion batteries. Arguably, the biggest disadvantage of these electrolytes is their undesirable ability to corrode aluminium current collectors. Hence, suppressing the Al corrosion in such electrolytes has become a widely discussed topic. Despite that, there is a lack of studies focusing on in-situ approaches for the detection of such corrosion, even though such approaches are essential for the effective evaluation of the performance of Li-ion batteries containing novel LiFSI-based electrolytes. This work demonstrates the usage of EIS for the detection of corrosion of Al current collectors in NMC/Graphite cells containing 1.0 M LiFSI in EC:DMC (1:1, v/v). When cycled up to 4.2 V at 50 °C, cathode-side Nyquist plots displayed induction loops developing over the cycles, which were ascribed to the corrosion of Al current collectors, and whose presence was confirmed by SEM imaging. When the cut-off voltage was decreased to 3.7 V to maintain a native protective Al2O3 layer and hence suppress the corrosion, neither the induction loops in Nyquist plots nor pitting holes in SEM images were observed, confirming the link between the induction loops and the corrosion. This work aims to support designing and understanding of future experiments focused on suppressing the corrosion of Al current collectors in LiFSI-based high-voltage Li-ion batteries capable of operation at higher temperatures.

Early Detection and Monitoring of Corrosion in Reinforced Concrete Structures Using Coupled Time-Frequency Analysis

Early Detection and Monitoring of Corrosion in Reinforced Concrete Structures Using Coupled Time-Frequency Analysis