Relevance feature selection of modal frequency-ambient condition pattern recognition in structural health assessment for reinforced concrete buildings

Abstract

Modal frequency is an important indicator for structural health assessment. Previous studies have shown that this indicator is substantially affected by the fluctuation of ambient conditions, such as temperature and humidity. Therefore, recognizing the pattern between modal frequency and ambient conditions is necessary for reliable long-term structural health assessment. In this article, a novel machine-learning algorithm is proposed to automatically select relevance features in modal frequency-ambient condition pattern recognition based on structural dynamic response and ambient condition measurement. In contrast to the traditional feature selection approaches by examining a large number of combinations of extracted features, the proposed algorithm conducts continuous relevance feature selection by introducing a sophisticated hyperparameterization on the weight parameter vector controlling the relevancy of different features in the prediction model. The proposed algorithm is then utilized for structural health assessment for a reinforced concrete building based on 1-year daily measurements. It turns out that the optimal model class including the relevance features for each vibrational mode is capable to capture the pattern between the corresponding modal frequency and the ambient conditions.

Broad Bayesian learning (BBL) for nonparametric probabilistic modeling with optimized architecture configuration

“…Modeling the ambient influence on the structural health indicators is crucial for reliable structural health monitoring (Brownjohn, 2007; Giagopoulos et al., 2019; Kuok & Yuen, 2012; Li, Yi, Ren, Li, & Huo, 2014; Liu, Lu, Yin, & Noori, 2016; Mu, Yuen, & Kuok, 2016). Due to the nature of complex and volatile mechanism, constructing a representative parametric input–output relationship to describe the subtle environmental effects on materials properties and structural behavior under severe wind loading can be a nontrivial task (Catbas, Susoy, & Frangopol, 2008; Kuok & Yuen, 2016; Lam, Zhang, Ni, & Hu, 2017; Lei, Su, & Shen, 2013).…”

Copula-Based Uncertainty Quantification (Copula-UQ) for Multi-Sensor Data in Structural Health Monitoring

“…Temperature is a critical loading factor for structures [ 32 ]. Variation of temperatures in structures significantly influences the material properties (for example, Young’s modulus [ 32 ]), static characteristics (for example, deflection and deformation [ 32 ]), dynamic characteristics (for example, structural frequencies [ 33 , 34 , 35 ], damping ratios and mode shapes [ 36 ]) and boundary conditions [ 37 ]. Temperatures, including ambient air temperature and structural component temperature, of a multi-sensor of a structure are uncertain due to the fact that they are affected by not only the ambient factors, including air temperature variation, solar radiation intensity, humidity and wind speed, but also the complex processes of heat transfer [ 38 ].…”

Propagative broad learning for nonparametric modeling of ambient effects on structural health indicators

“…However, long-term structural health monitoring of in-service infrastructures demonstrated that the structural health indicators are sensitive to varying operating conditions. 8,9,[14][15][16] Inevitable operating interferences, such as temperature and humidity, [17][18][19][20][21] wind velocity, [22][23][24][25] traffic loading, 26,27 and base excitation, 28 can induce significant contributions to the variation of structural health indicators. In order to make reliable judgments of the deterioration of structural integrity, modeling the ambient interferenceinduced variation of the structural health indicators is essential.…”