Comparison Metrics for Time-Histories: Application to Bridge Aerodynamics

Abstract

Wind effects can be critical for the design of lifelines such as long-span bridges. The existence of a significant number of aerodynamic force models, used to assess the performance of bridges, poses an important question regarding their comparison and validation. This study utilizes a unified set of metrics for a quantitative comparison of time-histories in bridge aerodynamics with a host of characteristics. Accordingly, nine comparison metrics are included to quantify the discrepancies in local and global signal features such as phase, time-varying frequency and magnitude content, probability density, nonstationarity and nonlinearity. Among these, seven metrics available in the literature are introduced after recasting them for time-histories associated with bridge aerodynamics. Two additional metrics are established to overcome the shortcomings of the existing metrics. The performance of the comparison metrics is first assessed using generic signals with prescribed signal features. Subsequently, the metrics are applied to a practical example from bridge aerodynamics to quantify the discrepancies in the aerodynamic forces and response based on numerical and semi-analytical aerodynamic models. In this context, it is demonstrated how a discussion based on the set of comparison metrics presented here can aid a model evaluation by offering deeper insight. The outcome of the study is intended to provide a framework for quantitative comparison and validation of aerodynamic models based on the underlying physics of fluid-structure interaction. Immediate further applications are expected for the comparison of time-histories that are simulated by data-driven approaches.

Stochastic non-stationary characteristics of vehicle-induced bridge vibrations

“…To further quantify the non-stationary properties, the recurrence plot analysis [17][18][19] is conducted. Recurrence plots were originally designed to graphically show recurring patterns and non-stationary patterns in time series.…”

“…Then, the response is further evaluated by using higher order spectrum. 18,19 Furthermore, the response is evaluated by using improved parameters in the context of contemporary non-linear dynamics theory. For comparison, the Fourier spectrum of the free decay response is depicted in the context of linear dynamics to make a preliminary assessment of the vibrational modal properties of the system.…”

The Tracking of Modal Parameters for a Reinforced Concrete Building During Low-Medium Intensity Earthquakes

“…4; the identification within each window was done through the "robust combined algorithm" proposed by Van Overschee and De Moor in [12]. The accuracy of the identified model in reproducing the building response is evaluated comparing the predicted and measured time histories of accelerations through the comparison metrics proposed by Kavrakov et al [20], which consider several signal properties such as phase, peak, root mean square, and frequency contents. A detailed explanation of the approach can be found in Gara et al (2021) [21].…”

Data-driven Aerodynamic Analysis of Structures using Gaussian Processes

“…To assess the prediction of the aerodynamic forces of the GP-NFIR model, we use a set of nine comparison metrics for time-histories that are presented in Kavrakov et al (2020), which includes an open-source Matlab code. Here, we briefly list and revisit these metrics.…”

“…Within these, the wavelet-based metrics are computed using the Morlet wavelet with a central reduced frequency of K c =1.6π and normalization time of T c =1/1.6 for the phase metric (cf. Kavrakov et al (2020) for further info). The metrics support the previous conclusion as their values are M ≥0.95 for all the signal features captured by them.…”