This study proposes an unsupervised, online structural health monitoring framework robust to the sensor configuration, that is, the number and placement of sensors. The proposed methodology leverages generative adversarial networks (GANs). The GAN's discriminator network is the novelty detector, while its generator provides additional data to tune the detection threshold. GAN models are trained with the fast Fourier transform of structural accelerations as input, avoiding the need for any structure-specific feature extraction. Dense, convolutional (convolutional neural network), and long short-term memory (LSTM) units are evaluated as discriminators under different GAN training loss patterns, that is, the differences between discriminator and generator training losses. Resultsshow that the LSTM-based discriminators and the suggested threshold tuning technique to be robust even in loss patterns with overfitted discriminators, a probable outcome of limited training sets. The framework is evaluated on two benchmark datasets. With only 100 s of training data, it achieved 95% novelty detection accuracy, distinguishing between different damage classes and identifying their resurgence under varying sensor configurations. Finally, the majorityvote-ensemble of discriminator-generator pairs at different training epochs is introduced to reduce false alarms, improve novelty detection accuracy and stability.

This study proposes a novelty-classification framework that applies to structural health monitoring (SHM) and sensor output validation (SOV) problems. The proposed framework has simple high-dimensional features with several advantages. First, the feature extraction method is extensively applicable to instrumented structures. Second, the high-dimensional features’ utilization alleviates one of the main issues of supervised novelty classifications, namely, imbalanced datasets and low-sampled data classes. Recurrent Neural Networks are employed for the classification of high-dimensional features. Furthermore, generative adversarial networks (GAN) are trained with low-sampled data classes’ high-dimensional features for generating new data objects. The generated data objects are combined with the initial training set for improving classification results. The proposed framework is studied on two SHM and SOV datasets. The SHM dataset has twenty-one data classes, with a total test accuracy of 99.60% compared to another study with 88.13% accuracy. The SOV classification shows improved results with a mean accuracy of 96.5% compared to three other studies with mean accuracy values of 93.5%, 92.97%, and 71.1%. Furthermore, the integration of GAN’s generated data objects with low-sampled classes improved those classes’ mean F1 score from 44.77% to 64.58% and from 73.39% to 90.84% on SOV and SHM case studies, respectively. The integration of GAN-generated data objects with the initial low-sampled data classes for accuracy improvement shows more potential in the SHM dataset than the SOV case, which can be due to the signal pattern-based labeling logic of SOV datasets.

No abstract

No abstract

This paper presents an alternative to segmentation of point clouds tailored specifically to large-scale steel buildings. Typical segmentation approaches process the 3D point data directly and focus on large blocky structures such as concrete; these are not generalizable to smaller, more complex geometries found in steel elements. The method takes advantage of image processing techniques by utilizing 2D "slices" of the point cloud, rather than the original 3D point cloud. Centroids of targeted structural cross sections are extracted from these slices using 2D convolution as a template-matching operation, and then projected back to 3D. From this, member centroidal axes are extracted using a custom linear region growing algorithm to create a 1D beam line model, including connections. Experimental results from scans of four prefabricated steel buildings indicate that the method is robust to variations in framing systems, clutter (e.g., obstructions, nonstructural elements), and point cloud sparsity.