A grout sleeve connection is a typical kind of joint in prefabricated structures. However, for construction and manufacturing reasons, defects in this kind of joint are usually inevitable. The joint quality of a prefabricated structure has a significant influence on its overall performance and can lead to structural failure. Due to the complexity of various types of materials used in grout sleeve connections, traditional non-destructive testing methods, such as Acoustic Emission (AE), Ultrasonic Testing (UT), Guided Wave Testing (GW), are facing great challenges. The recent development of deep learning technology provides a new opportunity to solve this problem. Deep learning can learn the inherent rules and abstract hierarchies of sample data, and it has a powerful ability to extract the intrinsic features of training data in complex classification tasks. This paper illustrates a deep learning framework for the identification of joint defects in prefabricated structures. In this method, defect features are extracted from the acceleration time history response of a prefabricated structure using a convolutional neural network. The proposed method is validated by vibration experiments on a half-scaled, two-floor prefabricated frame structure with column rebars spliced by different defective grout sleeves.
Defect and damage identification is a crucial task in structural health monitoring (SHM) systems. Recent advances in deep neural networks (DNNs) show success in identification from data for a wide range of SHM systems. However, this approach faces challenges in terms of robustness and scalability with respect to data scarcity. Data collection for the training of DNNs from both the field and laboratory experiments is costly. To address this issue, we employ transfer learning (TL) through the use of deep convolutional neural networks (CNNs) for defect identification in the context of a sensor network’s vibration data. A deep TL (DTL) paradigm is used herein so that a pretrained CNN, primarily trained for generalized defect identification tasks where sufficient training data exist (source domain), can be re-trained partially (fine-tuned) as a later secondary process that targets this application domain (target domain) specifically. Different DTL cases are compared, and training data are enhanced with numerical simulation data. The efficacy and robustness of this method are demonstrated on defect identification for full-scale prefabricated concrete shear wall structures with different levels of data scarcity. This method utilizes dynamic responses collected using a sensor network. This is an extension of deep learning vision for non-vision tasks. Defect features are extracted from the dataset of dynamic responses using this DTL frame. Experimental results show that this approach can improve identification models on datasets with few samples.
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.