Forecasting Face Support Pressure During EPB Shield Tunneling in Soft Ground Formations Using Support Vector Regression and Meta-heuristic Optimization Algorithms

One of the crucial tasks during the EPB shield tunnelling is estimating the optimum tunnel face pressure (FP), which ensures self-drilling safety, helps to reduce surface settlement and prevents the entire tunnel from collapsing. This study aims to propose an optimized and state-of-the-art machine learning model to predict the EPB-FP as accurately as possible. To this end, a support vector regression SVR model and six metaheuristic optimization algorithms of particle swarm optimization (PSO), grey wolf optimization (GWO), multiverse optimization (MVO), moth flame optimization (MFO), sine cosine algorithm (SCA), and social spider optimization (SSO) were developed to predict the FP in the EPB tunnelling. 250 data sets, including seven input parameters and one output parameter (FP) were utilized in the models obtained from the Tehran metro Line 3. Finally, the performance prediction of the models from high to low was SVR–PSO,SVR–GWO,SVR–MVO,SVR–MFO,SVR–SCA,SVR–SSO, and SVR with ranking scores of 55,49,45,39,37,30, and 21, respectively. Therefore, the SVR–PSO hybrid model produced the most accurate results and it was recommended to predict the FP in the EPB tunnelling. In addition, using the mutual information test, the surface load (SL) parameter was identified as the most influential parameter on the FP. This work’s significance is that it allows geotechnical engineers to accurately estimate the FP during the EPB tunnelling, which ensures the safety of the excavation itself, helps to minimize surface settlement, and ultimately prevents the collapse of the entire tunnel. Also, it can prevent the time-consuming and cost overruns that the FP may cause during the EPB tunnelling.