Back-Analysis of Parameters of Jointed Surrounding Rock of Metro Station Based on Random Forest Algorithm Optimized by Cuckoo Search Algorithm. (29th March 2022)

• Record Type: Journal Article
• Authors: Guo, Xinping; Jiang, Annan; Liu, Xiang
• Other Names: Fern ndez Fern ndez Francisco Javier Academic Editor.
• Is Part Of: Advances in materials science and engineering. Volume 2022(2022)
• Publication Date: 2022-03-29
• Subjects: Materials science -- Periodicals; Materials science; Periodicals; 620.11
• DOI: 10.1155/2022/1718773
• Languages: English
• ISSNs: 1687-8434

Abstract

Abstract : The efficiency and accuracy in determining mechanical parameters of joint of rock mass have significant influences on the safety of construction. In this paper, a new back-analysis method of joint parameters of the ubiquitous-joint model is proposed. This study combines the ubiquitous-joint model, random forest algorithm (RF), and cuckoo search algorithm (CS) to construct the parameters identification method of a jointed rock mass. The parameter determination is transformed into a global optimization problem. In this method, the mean square error between the measured displacement (stress) and the calculated displacement (stress) is taken as the objective function, and the joint parameters are taken as the decision variables. The method is applied to the project of Qingniwaqiao Metro Station of Dalian Metro Line 5. This method can be used for the back-analysis of parameters of a jointed rock mass in underground engineering construction.