Machine learning based prediction model for plastic hinge length calculation of reinforced concrete structural walls

Abstract

Reinforced concrete structural walls (RCSWs) are integral part of buildings and other structures and are used to carry in-plane and out-plane loads. For assessment purposes and to ensure safety and resilience of the structure, the curvature, capacity, and strain demands of RCSWs need to be estimated. Nonlinear numerical models are increasingly used in earthquake engineering design and assessment, where it is critical to develop high fidelity simulation tools to precisely forecast the global and local behavior of RCSWs. Plastic deformations concentrated in small regions, i.e. plastic hinges, and characterized through the concept of plastic hinge length (PHL), are conventionally used to define the inelastic response of RCSWs. In this study machine learning (ML) algorithms were leveraged in evaluating the PHL of RCSWs. A database containing 721 planar and nonplanar RCSW samples were utilized for training and testing ML models. Four different algorithms were employed, namely: XGBoost, CatBoost, Random Forest (RF), and genetic programming. The RF model outperformed other ML counterparts. The results of the best ML model were also compared against empirical equations available in literature and nonlinear regression analysis. The proposed ML model provided much better predictions than the existing relationships. Predictions of most empirical models were found to be extremely over (or under) conservative. The proposed ML model was also presented via an online tool where users can obtain the PHL of any RCSW simply by inputting wall parameters and clicking a run button.

Optimizing Gene Expression Programming to Predict Shear Capacity in Corrugated Web Steel Beams

“…This resurgence of interest in corrugated web steel systems has coincided with a growing trend in the structural engineering community towards embracing machine learning techniques for modeling and analysis. Researchers have proposed the use of machine learning algorithms, such as K-Nearest Neighbors, XGBoost, CatBoost, Random Forest, and support vector machines, to develop more accurate formulae for structural design and to enhance SHM for bridges [6][7][8].…”

“…Machine learning algorithms have been used to predict shear capacity, fundamental period, and deflection of structures, as well as to discriminate between healthy and non-healthy states of bridges [9,10]. Additionally, machine learning has been applied to estimate the plastic hinge length of reinforced concrete structural walls, providing better predictions than existing empirical equations [7,10]. Artificial neural networks (ANNs) have also been used to predict the punching shear capacity of fiber-reinforced concrete (FRC) and fiber-reinforced polymer (FRP) concrete slabs [11,12].…”

A Bearing Fault Diagnosis Method Based on a Residual Network and a Gated Recurrent Unit under Time-Varying Working Conditions

“…Traditional fault diagnoses usually use signal processing based on frequency and time-domain features and then use various classifiers for signal diagnosis. Typical classifiers include Bayesian classifiers [ 5 , 6 ], support vector machines [ 7 ], Random Forest [ 8 ] etc. Although these methods are easy to implement, they require specialized knowledge to extract the features and select the classifiers, and their accuracy and reliability also require high data quality and signal characteristics.…”

The Temperature-Induced Deflection Data Missing Recovery of a Cable-Stayed Bridge Based on Bayesian Robust Tensor Learning

“…In addition, a significant correlation was found between the temperature-induced deflections and temperature of bridges [7,8]. Many scholars have also conducted research on structural condition assessments based on monitoring data and machine learning [9][10][11][12].…”