Application of extreme learning machine in behavior of beam to column connections. (June 2020)

• Record Type: Journal Article
• Authors: Cao, Yan; Wakil, Karzan; Alyousef, Rayed; Jermsittiparsert, Kittisak; Si Ho, Lanh; Alabduljabbar, Hisham; Alaskar, Abdulaziz; Alrshoudi, Fahed; Mustafa Mohamed, Abdeliazim
• Is Part Of: Structures. Volume 25(2020)
• Page Start: 861
• Page End: 867
• Publication Date: 2020-06
• Subjects: Moment -- Forecasting -- Extreme learning machine -- Beam to column connection; Structural engineering -- Periodicals; 624.1
• DOI: 10.1016/j.istruc.2020.03.058
• Languages: English
• ISSNs: 2352-0124

Abstract

Abstract: The effectiveness and performance of beam to column connections have been highly affected by the type and properties of structures. An effective and stable design of beam to column connections is critical because in many cases, a single connection must be able to carry several types of loads at the same time. When designing these connections, it is important to consider erection, serviceability, strength, and cost-effectiveness as an efficient design that must be economic in practice. In this study, experimental results for the designed beam to column connection in concrete frames have been applied while evaluating the outcomes. Development and applying of Extreme Learning Machine (ELM) for moment prediction of beam to column connections are the objectives of this study. By understanding and integrating the relevant simulation outcomes and other statistical indicators, the reliability of the computational models has been analyzed.