Enhancing Seismic Design of Non-structural Components Implementing Artificial Intelligence Approach: Predicting Component Dynamic Amplification Factors

Abstract

The seismic performance of non-structural components (NSCs) has been the focus of intensive study during the last few decades. Modern building codes define design forces on components using too simple relationships. The component accelerates faster than the floor acceleration to which it is connected. Therefore, component dynamic amplification factors (CDAFs) are calculated in this work to quantify the amplification in the acceleration of NSCs for the various damping ratios and tuning ratios of the NSC, and the primary structural periods. From the analysis results, it was observed that CDAF peaks are either underestimated or overestimated by the code-based formulae. A prediction model to ascertain the CDAFs was also developed using artificial neural networks (ANNs). Following that, the suggested model is contrasted with the established relationships from the past research. The ANN model's coefficient of correlation (𝑅) was 0.97. Hence, using an ANN algorithm reduces the necessity of laborious and complex analysis.

Utilizing Artificial Neural Networks and Random Forests to Forecast the Dynamic Amplification Factors of Non-Structural Components

“…Biological neural networks function as simplified constructs that offer an analytical depiction of artificial neural networks (ANNs). With their ability to handle large datasets, tackle complex problems, and navigate ambiguous situations, neural networks have proven to be more accurate tools for calculations and predictions compared to conventional computational methods [75][76][77][78]. The primary challenge in constructing this model lies in determining the optimal architecture, including the number of hidden layers, epochs, batch size, and more.…”