Lamb wave approaches have been accepted as efficiently non-destructive evaluations in structural health monitoring for identifying damage in different states. Despite significant efforts in signal process of Lamb waves, physics-based prediction is still a big challenge due to complexity nature of the Lamb wave when it propagates, scatters and disperses. Machine learning in recent years has created transformative opportunities for accelerating knowledge discovery and accurately disseminating information where conventional Lamb wave approaches cannot work. Therefore, the learning framework was proposed with a workflow from dataset generation, to sensitive feature extraction, to prediction model for lamb-wave-based damage detection. A total of 17 damage states in terms of different damage type, sizes and orientations were designed to train the feature extraction and sensitive feature selection. A machine learning method, support vector machine (SVM), was employed for the learning model. A grid searching (GS) technique was adopted to optimize the parameters of the SVM model. The results show that the machine learning-enriched Lamb wave-based damage detection method is an efficient and accuracy wave to identify the damage severity and orientation. Results demonstrated that different features generated from different domains had certain levels of sensitivity to damage, while the feature selection method revealed that time-frequency features and wavelet coefficients exhibited the highest damage-sensitivity. These features were also much more robust to noise. With increase of noise, the accuracy of the classification dramatically dropped.

While nanoparticles from the carbon family have been incorporated effectively for polymer matrixes, there is no clear information available for understanding the impacts of the morphology of different carbon nanoparticles on the performance of carbon-based nanocomposites. Therefore, this study aimed to provide a comprehensive, comparative investigation to systematically assess the impacts of nanoparticles on the tribological, mechanical, and electrochemical properties of the epoxy coatings using three representative 0D, 1D, and 2D nanoparticles: Fullerene-C60 (C60), graphene nanoplatelets (GNPs), and carbon nanotubes (CNTs). The anti-corrosion performance of the nanocomposites in both the short and long term was characterized. The mechanical properties were examined by abrasion, adhesion, and tensile tests. Fourier-transform infrared spectroscopy (FTIR) was conducted to determine their chemical structures, while scanning electron microscopy (SEM) was used to determine their surface texture. The electrochemical impedance spectroscopy (EIS) results revealed that the coatings reinforced by C60 and GNP had better anti-corrosion performance than that of the CNT/epoxy samples. The incorporation of C60 and CNT led to a considerable improvement in tensile properties, while improved abrasion resistance was observed in all types of nanofiller/epoxy groups. C60-loaded composites exhibited a significant enhancement in tensile properties as compared to CNT or GNP composites.

Corrosion and corrosion-induced damage have resulted mostly in malfunctions and sometimes even in failures of metallic structures, including oil and gas pipelines. In this study, new high-performance composite coatings were developed by incorporating nanoparticles in the polymer resins with applications to oil and gas pipelines. The graphene nanoplatelets under different concentrations were used to prepare the epoxy-based nanocomposites and were then evaluated through mechanical and electrical tests. The integration of high-speed disk and ultrasonication were adopted as the dispersion technique to overcome nanoparticle agglomeration. Electron microscopy techniques were used to investigate the agglomeration. The new composites were qualitatively and quantitatively evaluated in terms of contact angle, surface roughness, adhesion to the substrate, corrosion resistance, and abrasion resistance. The results suggested that the composite with 0.5~1.0 wt.% of the graphene nanofillers led to the largest improvement in both mechanical and electrochemical properties. Distribution of nanoparticles in the matrix was observed using scanning electron microscopy and surface roughness using atomic force microscopy. Large agglomeration that was observed at the higher concentrations mainly resulted in the reduction of corrosion resistance and abrasion resistance.

Corrosion accounts for huge maintenance cost in the pipeline community. Promotion of protective coatings used for oil/gas pipeline corrosion control, in terms of high corrosion resistance as well as high damage tolerance, are still in high demand. This study was to explore the inclusion of nanoparticle fullerene-C60 in protective coatings for oil/gas pipeline corrosion control and mitigation. Fullerene-C60/epoxy nanocomposite coatings were fabricated using a solvent-free dispersion method through high-speed disk (HSD) and ultrasonication. The morphology of fullerene-C60 particles was characterized by transmission electron microscopy (TEM), and dynamic light scattering (DLS). The data analysis indicated that the nanoparticles were effectively dispersed in the matrix. The performance of the nanocomposites was investigated through their mechanical and electrochemical properties, including corrosion potential, tensile strength, strain at failure, adhesion to substrate, and durability performance. Dogbone shaped samples were fabricated to study the tensile properties of the nanocomposites, and improvement of strength, ultimate strain, and Young’s modulus were observed in the C60/epoxy specimens. The results demonstrated that the C60/epoxy composite coatings also had improvements in adhesion strength, suggesting that they could provide high damage tolerance of coatings for engineering applications. Moreover, the electrochemical impedance spectroscopy (EIS) results generated from the accelerated durability test revealed that the developed fullerene-C60 loaded composite coatings exhibited significantly improved corrosion resistance. The nanocomposite with 0.5 and 1.0 wt.% of C60 particles behaved as an intact layer for corrosion protection, even after 200-h salt spray exposure, as compared to the control coating without nanofiller in which severe damage by over 50% reduction was observed.

Welding is widely used in the connection of metallic structures, including welded joints in oil/gas metallic pipelines and other structures. The welding process is vulnerable to the inclusion of different types of welding defects, such as lack of penetration and undercut. These defects often initialize early-age cracking and induced corrosion. Moreover, welding-induced defects often accompany other types of mechanical damage, thereby leading to more challenges in damage detection. As such, identification of weldment defects and interaction with other mechanical damages at their early stage is crucial to ensure structural integrity and avoid potential premature failure. The current strategies of damage identification are achieved using ultrasonic guided wave approaches that rely on a change in physical parameters of propagating waves to discriminate as to whether there exist damaged states or not. However, the inherently complex nature of weldment, the complication of damages interactions, and large-scale/long span structural components integrated with structure uncertainties pose great challenges in data interpretation and making an informed decision. Artificial intelligence and machine learning have recently become emerging methods for data fusion, with great potential for structural signal processing through decoding ultrasonic guided waves. Therefore, this study aimed to employ the deep learning method, convolutional neural network (CNN), for better characterization of damage features in terms of welding defect type, severity, locations, and interaction with other damage types. The architecture of the CNN was set up to provide an effective classifier for data representation and data fusion. A total of 16 damage states were designed for training and calibrating the accuracy of the proposed method. The results revealed that the deep learning method enables effectively and automatically extracting features of ultrasonic guided waves and yielding high precise prediction for damage detection of structures with welding defects in complex situations. In addition, the effectiveness and robustness of the proposed methods for structure uncertainties using different embedding materials, and data under noise interference, was also validated and findings demonstrated that the proposed deep learning methods still exhibited a high accuracy at high noise levels.