A hybrid GEP and WOA approach to estimate the optimal penetration rate of TBM in granitic rock mass

Li, Zimu and Bejarbaneh, Behnam Yazdani and Asteris, Panagiotis G. and Koopialipoor, Mohammadreza and Armaghani, Danial Jahed and Tahir, M. M. (2021) A hybrid GEP and WOA approach to estimate the optimal penetration rate of TBM in granitic rock mass. Soft Computing, 25 (17). pp. 11877-11895. ISSN 1432-7643, DOI https://doi.org/10.1007/s00500-021-06005-8.

Full text not available from this repository.


The efficiency of tunnel boring machines (TBMs) in underground projects has great significance for the mining and tunneling industries, demanding a reliable estimation of the TBM's performance in different geotechnical conditions. The current research work attempted to suggest an optimal predictor model of TBM performance as a reliable alternative to experimental and numerical techniques. To achieve this target, three data-mining techniques, namely neural network (NN), gene expression programming (GEP), and multivariate adaptive regression splines (MARS), were employed for modelling the TBM performance, and then the most robust predictive model was optimized via a metaheuristic search method known as whale optimization algorithm (WOA). For the modelling purpose, an experimental database was compiled by performing a field assessment program in a tunneling project in Malaysia and then conducting laboratory testing on the derived rock specimens. Based on the measured experimental data, the six most influential parameters were identified and served as model inputs to predict penetration rate (PR). In order to indicate the capability of the developed GEP and NN models, a stepwise linear regression model, i.e., MARS, was designed for PR prediction as well. The predictive capacity of the constructed models was quantified using a series of statistical indices, i.e., root mean squared error (RMSE), determination coefficient (R-2) and variance account for (VAF). Based on the computed indices for testing records, both the proposed GEP and NN models (with RMSE values of 0.1882 and 0.2120 and R-2 values of 0.9058 and 0.8735, respectively) yielded more accurate predictive results than the MARS model with RMSE of 0.2553 and R-2 of 0.8346. Hence, by achieving the most robust performance compared to the rest, GEP-based model can provide a new practical equation with a high level of accuracy. In other part of this study, the six input parameters of the GEP model and its equation were, respectively, defined as decision variables and objective function for the WOA technique to find the optimum values of PR. As a consequence of optimizing the GEP equation, the maximum value of PR rose from 3.75 m/h to 4.022 m/h, equivalent to an increase of 7.25% in PR value. The findings of this study verified the applicability of the proposed hybrid GEP and WOA approach in the site investigation phase of tunneling projects constructed by TBMs.

Item Type: Article
Uncontrolled Keywords: TBM performance; Penetration rate; Gene expression programming; Neural network; Multivariate adaptive regression splines; Whale optimization algorithm
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Faculty of Engineering > Department of Civil Engineering
Depositing User: Ms Zaharah Ramly
Date Deposited: 29 Jul 2022 02:40
Last Modified: 29 Jul 2022 02:40
URI: http://eprints.um.edu.my/id/eprint/28208

Actions (login required)

View Item View Item