Abstract. Structural health monitoring using ultrasonic guided waves relies on accurate interpretation of guided wave propagation to distinguish damage state indicators. However, traditional physics based models do not provide an accurate representation, and classic data driven techniques, such as a support vector machine, are too simplistic to capture the complex nature of ultrasonic guide waves. To address this challenge, this paper uses a deep learning interpretation of ultrasonic guided waves to achieve fast, accurate, and automated structural damaged detection. To achieve this, full wavefield scans of thin metal plates are used, half from the undamaged state and half from the damaged state. This data is used to train our deep network to predict the damage state of a plate with 99.98% accuracy given signals from just 10 spatial locations on the plate, as compared to that of a support vector machine (SVM), which achieved a 62% accuracy.
Continuous fiber ceramic matrix composites (CFCCs) are currently being developed for a variety of high-temperature applications, including use in advanced heat engines. For such composites, knowledge of porosity distribution and presence of defects is important for optimizing mechanical and thermal behavior of the components. The assessment of porosity and its distribution is also necessary during composite processing to ensure component unifo4ty. To determine the thermal properties of CFCC materials, and particularly for detecting defects and nonuniformities, we have developed an infrared thermal imaging method to provide a "single-shot'' full-field measurement of thermal diffusivity distributions in large components. This method requires that the back surface of a specimen receives a thermal pulse of short duration and that the temperature of the front surface is monitored as a function of time. The system has been used to measure thermal diffusivities of several CFCC materials with known porosity or density values, including SYT.,RAMICm SiC/SiNC composite samples from Dow Corning and SiUSiC and enhanced SiC/SiC samples from DuPont Lanxide Composites, to determine the relationship of thermal diffusivity to component porosity or density.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.