Implementation of Hybrid ANN-GWO Algorithm for Estimation of the Fundamental Period of RC-Frame Structures

The fundamental period (TFP) of vibration is one of the most important parameters in structural design since it is used to assess the dynamic response of the structures. It is the time taken by a structure or system to vibrate back and forth in its most natural way, without any external forces applied. Simultaneously, TFP depends on the mass distribution and stiffness of the structure, which is largely influenced by infill walls in RC frame structures, and which is why their careful design is necessary. This study aims to develop a fast, accurate, and efficient machine learning (ML) method for the prediction of the fundamental period of masonry-infilled reinforced concrete (RC) frame structures. Hybridization of the stochastic gradient descent (SGD) based artificial neural network (ANN), and meta-heuristic grey wolf optimization (GWO) algorithm is proposed as an effortless computational method. This approach provided even more reliable solutions than the robust second-order procedure based on single ML models. A total of 2178 samples of infilled RC frames were collected from available literature, where the number of storeys (NoSt), number of spans (NoSp), length of spans (LoSp), opening percentage (OP), and masonry wall stiffness (MWS) were considered as input parameters for predicting the output TFP results. The accuracy and exploration efficiency of the proposed ANN-GWO paradigm have demonstrated superiority over existing seismic design codes and other conventional ML methods.