Torsional capacity evaluation of RC beams using an improved bird swarm algorithm optimised 2D convolutional neural network. (15th December 2022)

• Record Type: Journal Article
• Authors: Yu, Yang; Liang, Shiwei; Samali, Bijan; Nguyen, Thuc N.; Zhai, Chenxi; Li, Jianchun; Xie, Xingyang
• Is Part Of: Engineering structures. Volume 273(2022)
• Publication Date: 2022-12-15
• Subjects: Torsional strength -- Reinforced concrete (RC) beams -- Convolutional neural network -- Bird swarm algorithm; Structural engineering -- Periodicals; Structural analysis (Engineering) -- Periodicals; Construction, Technique de la -- Périodiques; Génie parasismique -- Périodiques; Pression du vent -- Périodiques; Earthquake engineering; Structural engineering; Wind-pressure; Periodicals; 624.105
• DOI: 10.1016/j.engstruct.2022.115066
• Languages: English
• ISSNs: 0141-0296

Abstract

Highlights: Data-driven model based on CNN for predicting torsional strength of RC beams. Proposed method outperforms existing methods by means of multiple evaluation metrics. Sensitivity analysis was conducted to study the network inputs and output relationship. A GUI was developed for the design of RC beams in practice. Abstract: This study presents the application of deep learning technology in torsional capacity evaluation of reinforced concrete (RC) beams. A data-driven model based on 2D convolutional neural network (CNN) is established, where model inputs contain the beam width, beam height, stirrup width, stirrup height, concrete compressive strength, steel ratio of longitudinal reinforcement, yield strength of longitudinal reinforcement, steel ratio of transverse reinforcement, yield strength of transverse reinforcement and stirrup spacing. To enhance the prediction accuracy of the proposed model, an improved bird swarm algorithm (IBSA) is leveraged to optimise the hyperparameters of CNN in the training phase. A comprehensive dataset, comprising 268 groups of laboratory tests of RC beams collected from published articles, is used for model development and validation. The results show that the proposed 2D CNN with hyperparameter optimisation exhibits high performance in predicting torsional strength of RC beams, which outperforms other machine learning models, building codes and empirical formula in terms of a series of evaluation metrics.