Civil engineering structures are routinely exposed to corrosive environments, posing threats to their structural integrity. Traditional corrosion control methods often involve employing physical barriers, such as various coatings, to isolate the steel substrate from surrounding electrolytes. Among these methods, thermal spraying of alloy coatings has emerged as a prominent technique in safeguarding steel matrices against corrosion, particularly in industrial and marine settings. However, the inherent porosity of thermal spraying coatings compromises their corrosion resistance. Incorporating a polymer top layer offers a promising solution by sealing pores and augmenting overall performance. This study investigates corrosion on duplex-coated steel utilizing distributed fiber optic sensors based on optical frequency domain reflectometry. Experimental analyses involve embedding serpentine-arranged distributed fiber optic strain sensors within both thermal spraying layers and epoxy layers. Results demonstrate the efficiency of distributed sensors in identifying corrosion propagation paths by measuring the induced strain changes. Furthermore, the duplex coating exhibits significant enhancements in corrosion resistance for steel structures.
Each year, the global cost that is accounted to corrosion was estimated at $2.5 trillion. Corrosion not only imposes an economic burden, when corroded structures are under various loading conditions, it may also lead to structurally brittle failure, posing a potential threat to structural reliability and service safety. Although considerable studies investigated the combined effect of external loads and structural steel corrosion, many of the current findings on synergetic interaction between stress and corrosion are contrary. In this study, the combined effects of dynamic mechanical loads and corrosion on epoxy coated steel are investigated using the distributed fiber optic sensors based on optical frequency domain reflectometry. Experimental studies were performed using the serpentine-arranged distributed fiber optic strain sensors embedded inside the epoxy with three different scenarios including the impact loading-only, corrosion-only, and combined impact loading-corrosion tests. Test results demonstrated that the distributed fiber optic sensors can locate and detect the corrosion processing paths by measuring the induced strain changes. The combined impact loading-corrosion condition showed significantly accelerated corrosion progression caused by mechanical loads, indicating the significant interaction between dynamic mechanical loading and corrosion on epoxy coated steel.
Assessment of health state of large-scale infrastructure systems are crucial to ensure their operational safety. In this study, we propose the image-based conditional assessment of large-scale systems using deep learning approaches. The deep convolutional neural networks are optimally designed for satellite images to extract the sensitive features for assessment. The findings show that the machine learning methods exhibit great potential for infrastructure assessment, such as high bridges, and oil/gas pipeline assessment at both spatial and temporary scales over conventional methods.
corrosion still responds for huge maintenance cost of nationwide civil structures. In this study, we explored a machine learning approach to extract information from sensory data for early-age corrosion-induced damage identification and classification. Lamb-wave guided signals of steel samples collected from simulated corrosion damage were used for model training and calibration. The results showed that the machine learning method allowed effective information fusion for early-age corrosion.
As compared to conventional physics-based techniques, advances in sensors and computing technologies have been promoting data-enabled structural diagnosis and conditional assessment using machine learning techniques in structural health monitoring (SHM). Machine learning helps civil engineers to extract valuable information from large amount of data to make time-sensitive decision. The application of different machine learning techniques to large-scale civil structures is, however, still impeded by challenges. In this study, we use representative supervised support vector machine (shallow learning) and deep Bayesian deep belief network (deep learning) to demonstrate their merits and limitations in structural diagnosis and conditional assessment. A benchmark in the literature is used for the demonstration. The results showed that the shallow learning highly relies on the hand-crafted features, while optimization of kernels is another challenge during learning process. The deep learning could promote the learning accuracy without kernel design. Although the noise could lead to difficulty in data mining, the comparison demonstrated that the deep learning has less sensitivity to the impacts of noise interference than those of shallow learning.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.