A novel machine learning‐based algorithm to detect damage in high‐rise building structures

• Published in: The structural design of tall and special buildings Vol. 26; no. 18
• Main Authors: Rafiei, Mohammad Hossein, Adeli, Hojjat
• Format: Journal Article
• Language: English
• Published: Oxford Wiley Subscription Services, Inc 25.12.2017
• Subjects: Algorithms; Artificial intelligence; Classification; Concrete; Concrete construction; Damage detection; Data processing; Fast Fourier transformations; Feature extraction; Fourier transforms; Global health; health monitoring; High rise buildings; high‐rise building; Information processing; Learning algorithms; Machine learning; neural dynamics model of Adeli and Park; Neural networks; Noise reduction; Reinforced concrete; Signal processing; Structural damage; tall building; Wavelet transforms
• ISSN: 1541-7794; 1541-7808
• DOI: 10.1002/tal.1400

Summary A novel model is presented for global health monitoring of large structures such as high‐rise building structures through adroit integration of 2 signal processing techniques, synchrosqueezed wavelet transform and fast Fourier transform, an unsupervised machine learning technique, the restricted Boltzmann machine, and a recently developed supervised classification algorithm called neural dynamics classification (NDC) algorithm. The model extracts hidden features in the frequency domain of the denoised measured response signals recorded by sensors on different elevations or floors of a structure. The extracted features are used as an input of the NDC to detect and classify the global health of the structure into categories such as healthy, light damage, moderate damage, severe damage, and near collapse. The proposed model is validated using the data obtained from a 3D 1:20 scaled 38‐story reinforced concrete building structure. The results are compared with 3 other supervised classification algorithms: k‐nearest neighbor (KNN), probabilistic neural networks (PNN), and enhanced PNN (EPNN). NDC, EPNN, PNN, and KNN yield maximum average accuracies of 96%, 94%, 92%, and 82%, respectively.