Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks

A review of vibration-based damage detection in civil structures : from traditional methods to Machine Learning and Deep Learning applications

1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data

Structural health monitoring (SHM) techniques have been widely used in long-span bridges. However, due to limitations of computational ability and data analysis methods, the knowledge in ma...

Review of Bridge Structural Health Monitoring Aided by Big Data and Artificial Intelligence: From Condition Assessment to Damage Detection

Bayesian operational modal analysis: Theory, computation, practice

Summary

The dynamic characterization of structures is essential for assessing their response when subjected to dynamic loads in structural health monitoring. It mainly comprises the modal parameters, that is, the natural frequencies, damping ratios and mode shapes. These modal properties are attracting more attention when structures are under construction or operation for the researchers, structure owner and engineers. This paper presents the work on the operational modal analysis of a super tall building-the Shanghai Tower with a height of 632 m situated in Shanghai, China. A recently developed fast Bayesian method is utilized to perform modal identification, providing an effective means to identify the modal properties and assess their accuracy. In this study, ambient vibration tests are implemented in different construction stages. The corresponding modal properties and their associated uncertainties are identified and investigated, with interesting trends observed. Finite element models are also established to obtain the modal parameters in different stages and compared with the identified results. After the main structure is completed, a field test covering the eight corners of the core wall in a typical floor is performed to investigate the mode shapes. Afterward, a 12-h measurement is performed with the information of temperature and humidity recorded simultaneously. The variation of modal properties with changing environment is studied. The results obtained will be beneficial for understanding the modal properties of this super tall building and provide a baseline for future structural health monitoring. Copyright © 2016 John Wiley & Sons, Ltd.

Feng-Liang Zhang

Papers

Bayesian operational modal analysis: Theory, computation, practice

Structural health monitoring of Shanghai Tower during different stages using a Bayesian approach

Field observations on modal properties of two tall buildings under strong wind

Fundamental two-stage formulation for Bayesian system identification, Part II: Application to ambient vibration data

Fundamental two-stage formulation for Bayesian system identification, Part I: General theory