Assessment of risks of tunneling project in Iran using artificial bee colony algorithm

Abstract

The soft computing techniques have been widely applied to model and analyze the complex and uncertain problems. This paper aims to develop a novel model for the risk assessment of tunneling projects using artificial bee colony algorithm. To this end, the risk of the second part of the Emamzade Hashem tunnel was assessed and analyzed in seven sections after testing geotechnical characteristics. Five geotechnical and hydrological properties of study zone are considered for the clustering of geological units in front of tunneling project including length of tunnel, uniaxial compressive strength, rock mass rating, tunneling index Q, density and underground water condition. These sections were classified in two low-risk and high-risk groups based on their geotechnical characteristics and using clustering technique. It was resulted that three sections with lithologies Durood Formation, Mobarak Formation, and Ruteh Formation are placed in the high risk group and the other sections with lithologies Baroot Formation, Elika Formation, Dacite tuff of Eocene, and Shear Tuff, and Lava Eocene are placed in the low risk group. In addition, the underground water condition and density with 0.722 and 1 Euclidean distances have the highest and lowest impacts in the high risk group, respectively. Therefore, comparing the obtained results of modelling and actual excavation data demonstrated that this technique can be applied as a powerful tool for modeling risks of tunnel and underground constructions.