During the past decades, significant efforts have been dedicated to develop reliable methods in structural health monitoring. The health assessment for the target structure of interest is achieved through the interpretation of collected data. At the beginning of the 21st century, the rapid advances in sensor technologies and data acquisition platforms have led to the new era of Big Data, where a huge amount of heterogeneous data are collected by a variety of sensors. The increasing accessibility and diversity of the data resources provide new opportunities for structural health monitoring, while the aggregation of information obtained from multiple sensors to make robust decisions remains a challenging problem. This article presents a comprehensive review of the recent data fusion applications in structural health monitoring. State-of-the-art theoretical concepts and applications of data fusion in structural health monitoring are presented. Challenges for data fusion in structural health monitoring are discussed, and a roadmap is provided for future research in this area.
1 January 2019 in Journal of Engineering Mechanics
Health monitoring of civil infrastructures is a key application of Internet of things (IoT), while edge computing is an important component of IoT. In this context, swarms of autonomous inspection robots, which can replace current manual inspections, are examples of edge devices. Incorporation of pretrained deep learning algorithms into these robots for autonomous damage detection is a challenging problem since these devices are typically limited in computing and memory resources. This study introduces a solution based on network pruning using Taylor expansion to utilize pretrained deep convolutional neural networks for efficient edge computing and incorporation into inspection robots. Results from comprehensive experiments on two pretrained networks (i.e., VGG16 and ResNet18) and two types of prevalent surface defects (i.e., crack and corrosion) are presented and discussed in detail with respect to performance, memory demands, and the inference time for damage detection. It is shown that the proposed approach significantly enhances resource efficiency without decreasing damage detection performance.
2 February 2021 in Structural and Multidisciplinary Optimization
In engineering acoustics, the propagation of elastic flexural waves in plate and shell structures is a common transmission path of vibrations and structure-borne noises. Phononic metamaterials with a frequency band gap can effectively block elastic waves in certain frequency ranges, but often require a tedious trial-and-error design process. In recent years, deep neural networks (DNNs) have shown competence in solving various inverse problems. This study proposes a deep-learning-based workflow for phononic plate metamaterial design. The Mindlin plate formulation was used to expedite the forward calculations, and the neural network was trained for inverse design. We showed that, with only 360 sets of data for training and testing, the neural network attained a 2% error in achieving the target band gap, by optimizing five design parameters. The designed metamaterial plate showed a −1 dB/mm omnidirectional attenuation for flexural waves around 3 kHz.