Krill herd algorithm-based neural network in structural seismic reliability evaluation

• Published in: Mechanics of advanced materials and structures Vol. 26; no. 13; pp. 1146 - 1153
• Main Authors: Asteris, Panagiotis G., Nozhati, Saeed, Nikoo, Mehdi, Cavaleri, Liborio, Nikoo, Mohammad
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 03.07.2019; Taylor & Francis Ltd
• Subjects: Algorithms; Artificial intelligence techniques; artificial krill herd algorithm; Artificial neural networks; Back propagation; Back propagation networks; Elasticity; Genetic algorithms; Krill; krill herd; Network reliability; Neural networks; Optimization; Parameters; Regression models; Reliability analysis; Reliability engineering; seismic reliability assessment of structures; Structural reliability
• ISSN: 1537-6494; 1537-6532
• DOI: 10.1080/15376494.2018.1430874

In this research work, the relative displacement of the stories has been determined by means of a feedforward Artificial Neural Network (ANN) model, which employs one of the novel methods for the optimization of the artificial neural network weights, namely the krill herd algorithm. For the purpose of this work, the area, elasticity, and load parameters were the input parameters and the relative displacement of the stories was the output parameter. To assess the precision of the feedforward (FF) model optimized using the Krill Herd Optimization (FF-KH) algorithm, comparison of results has been performed relative to the results obtained by the linear regression model, the Genetic Algorithm (GA), and the back propagation neural network model. The comparison of results has been carried out in the training and test phases. It has been revealed that the artificial neural network optimized with the krill herd algorithm supersedes the afore-mentioned models in potential, flexibility, and precision.