Premium
A novel machine learning‐based algorithm to detect damage in high‐rise building structures
Author(s) -
Rafiei Mohammad Hossein,
Adeli Hojjat
Publication year - 2017
Publication title -
the structural design of tall and special buildings
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.895
H-Index - 43
eISSN - 1541-7808
pISSN - 1541-7794
DOI - 10.1002/tal.1400
Subject(s) - restricted boltzmann machine , pattern recognition (psychology) , artificial intelligence , computer science , k nearest neighbors algorithm , probabilistic neural network , artificial neural network , probabilistic logic , fourier transform , machine learning , wavelet transform , boltzmann machine , algorithm , wavelet , mathematics , time delay neural network , mathematical analysis
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.