Full Length Article Application of several optimization techniques for estimating TBM advance rate in granitic rocks Danial Jahed Armaghani a , Mohammadreza Koopialipoor b , Aminaton Marto c , Saffet Yagiz d, * a Geotropik e Center of Tropical Geoengineering, Faculty of Civil Engineering, Universiti Teknologi Malaysia, Skudai, 81310, Malaysia b Faculty of Civil and Environmental Engineering, Amirkabir University of Technology, Tehran,15914, Iran c Environmental & GreenTechnology Department, Malaysia-Japan International Institute of Technology, Universiti Teknologi Malaysia, Kuala Lumpur, Malaysia d School of Mining and Geosciences, Nazarbayev University, Nur-Sultan, 010000, Kazakhstan article info Article history: Received 5 June 2018 Received in revised form 18 January 2019 Accepted 24 January 2019 Available online 3 May 2019 Keywords: Tunnel boring machines (TBMs) Advance rate Hybrid optimization techniques Particle swarm optimization (PSO) Imperialist competitive algorithm (ICA) abstract This study aims to develop several optimization techniques for predicting advance rate of tunnel boring machine (TBM) in different weathered zones of granite. For this purpose, extensive field and laboratory studies have been conducted along the 12,649 m of the Pahang e Selangor raw water transfer tunnel in Malaysia. Rock properties consisting of uniaxial compressive strength (UCS), Brazilian tensile strength (BTS), rock mass rating (RMR), rock quality designation (RQD), quartz content (q) and weathered zone as well as machine specifications including thrust force and revolution per minute (RPM) were measured to establish comprehensive datasets for optimization. Accordingly, to estimate the advance rate of TBM, two new hybrid optimization techniques, i.e. an artificial neural network (ANN) combined with both impe- rialist competitive algorithm (ICA) and particle swarm optimization (PSO), were developed for me- chanical tunneling in granitic rocks. Further, the new hybrid optimization techniques were compared and the best one was chosen among them to be used for practice. To evaluate the accuracy of the proposed models for both testing and training datasets, various statistical indices including coefficient of deter- mination (R 2 ), root mean square error (RMSE) and variance account for (VAF) were utilized herein. The values of R 2 , RMSE, and VAF ranged in 0.939e0.961, 0.022e0.036, and 93.899e96.145, respectively, with the PSO-ANN hybrid technique demonstrating the best performance. It is concluded that both the optimization techniques, i.e. PSO-ANN and ICA-ANN, could be utilized for predicting the advance rate of TBMs; however, the PSO-ANN technique is superior. Ó 2019 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/). 1. Introduction Assessment of tunnel boring machine (TBM) advancement is one of the main issues for schedule planning and cost of the project operating in rock mass. Due to this, estimation of TBM performance with actual and corrected parameters would be useful to reduce the cost and risk management of any tunneling projects. Over the last decades, many researchers have developed empirical and theo- retical models to predict TBM performance via the penetration rate, advance rate and field penetration index (FPI) (Roxborough and Phillips, 1975; Farmer and Glossop, 1980; Snowdon et al., 1982; Sanio, 1985; Hughes, 1986; Rostami and Ozdemir, 1993; Yagiz, 2002, 2008; Gong and Zhao, 2009). At present, most of re- searchers agree that TBM advancement could be affected by many factors categorized in three main groups: properties of intact rock and rock mass, and machine specifications. Both simple and hybrid artificial intelligence (AI) techniques are one of the approaches for solving various geotechnical problems (Singh et al., 2004; Verma and Singh, 2011; Khandelwal and Jahed Armaghani, 2016; Jahed Armaghani et al., 2017a; Koopialipoor et al., 2018a). In order to estimate the TBM performance parame- ters such as penetration rate, advance rate and FPI, many simple AI techniques, e.g. artificial neural network (ANN), particle swarm optimization (PSO), differential evolution (DE), gray wolf optimizer (GWO), and imperialist competitive algorithm (ICA), as well as several hybrid approaches like hybrid harmony search (HS-BFGS), have been utilized (Alvarez Grima et al., 2000; Benardos and Kaliampakos, 2004; Yagiz et al., 2009; Yagiz and Karahan, 2011; * Corresponding author. E-mail address: saffet.yagiz@nu.edu.kz (S. Yagiz). Peer review under responsibility of Institute of Rock and Soil Mechanics, Chi- nese Academy of Sciences. Contents lists available at ScienceDirect Journal of Rock Mechanics and Geotechnical Engineering journal homepage: www.rockgeotech.org Journal of Rock Mechanics and Geotechnical Engineering 11 (2019) 779e789 https://doi.org/10.1016/j.jrmge.2019.01.002 1674-7755 Ó 2019 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting by Elsevier B.V. This is an open access article under the CC BY- NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).