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

Bayesian Methods: A Social and Behavioral Sciences Approach

Reconstruction of structural health monitoring data is a challenging task, since it involves time series data forecasting especially in the case with a large block of missing data In this study, w

https://journals.sagepub.com/doi/pdf/10.1177/1475921718794953

Bayesian multi-task learning methodology for reconstruction of structural health monitoring data:

A novel methodology for modal parameters identification of large smart structures using MUSIC, empirical wavelet transform, and Hilbert transform

Dynamic strain estimation for fatigue assessment of an offshore monopile wind turbine using filtering and modal expansion algorithms

A Bayesian approach for condition assessment and damage alarm of bridge expansion joints using long-term structural health monitoring data

Real-time defect detection of high-speed train wheels by using Bayesian forecasting and dynamic model

The actual wind load information is helpful in evaluating the health status of high-rise structures. However, as a type of distributed load, the wind load is very difficult to be measured directly. A possible solution is to reconstruct it from the structural response measurements. This is often an ill-posed inverse problem. In this article, such ill posedness is solved by using a stable input estimator. With the help of the proposed application-oriented algorithm selection guidance, a type of state and input estimator is formulated. This type of estimator is designed based on the Kalman filter scheme, and is capable of estimating the unknown inputs and the system states within one sampling time. This actually facilitates the online simultaneous reconstruction of the wind load and the structural responses. The 600 m tall Canton Tower is situated in a typhoon active area, and a structural health monitoring system has already been integrated onto this tower. These two points make the Canton Tower an ideal test bed for validating the above illustrated online reconstruction strategy for the wind load and the structural responses. An operational modal analysis (OMA) is first performed to identify the modal properties of the Canton Tower under the Typhoon Nanmadol in 2011. Then a reduced-order finite element model (FEM) of the Canton Tower is updated according the OMA results. Finally, the equivalent fluctuating lateral loads and moments, which act on the nodes of the reduced-order FEM are reconstructed using the acceleration measurements recorded during Tyhoon Kai-tak in 2012. The reconstruction results are validated by comparing the simultaneously reconstructed structural acceleration with the corresponding sensor measurements. The mean component of the loads and moments are calculated using the real-time wind speed measurements and the available aerodynamic force coefficients. It is noted here that the focus of this article is not to develop a totally new theory, but rather to explore the application of a state and input estimator in the foreground to a practical complex structure.

Online Simultaneous Reconstruction of Wind Load and Structural Responses—Theory and Application to Canton Tower

https://iopscience.iop.org/article/10.1088/1361-665X/ab79b9/pdf

Structural modal identification and health monitoring of building structures using self-sensing cementitious composites

The Canton Tower is a high-rise slender structure with a height of 610 m. A structural health monitoring system has been instrumented on the structure, by which data is continuously monitored. This paper presents an investigation on the identified modal properties of the Canton Tower using ambient vibration data collected during a whole day (24 hours). A recently developed Fast Bayesian FFT method is utilized for operational modal analysis on the basis of the measured acceleration data. The approach views modal identification as an inference problem where probability is used as a measure for the relative plausibility of outcomes given a model of the structure and measured data. Focusing on the first several modes, the modal properties of this supertall slender structure are identified on non-overlapping time windows during the whole day under normal wind speed. With the identified modal parameters and the associated posterior uncertainty, the distribution of the modal parameters in the future is predicted and assessed. By defining the modal root-mean-square value in terms of the power spectral density of modal force identified, the identified natural frequencies and damping ratios versus the vibration amplitude are investigated with the associated posterior uncertainty considered. Meanwhile, the correlations between modal parameters and temperature, modal parameters and wind speed are studied. For comparison purpose, the frequency domain decomposition (FDD) method is also utilized to identify the modal parameters. The identified results obtained by the Bayesian method, the FDD method and a finite element model are compared and discussed.

Y. W. Wang

Papers

A Bayesian approach for condition assessment and damage alarm of bridge expansion joints using long-term structural health monitoring data

Real-time defect detection of high-speed train wheels by using Bayesian forecasting and dynamic model

Online Simultaneous Reconstruction of Wind Load and Structural Responses—Theory and Application to Canton Tower

Structural modal identification and health monitoring of building structures using self-sensing cementitious composites

Operational modal analysis of Canton Tower by a fast frequency domain Bayesian method