Comparison of artificial neural networks (ANN), support vector machine (SVM) and gene expression programming (GEP) approaches for predicting TBM penetration rate

Abstract

The history of tunnel boring machine (TBM) tunnelling dates back to nearly 50 years ago. Due to high construction cost, the investigation on TBM performance is regarded as one of the crucial issues which should be considered from different aspects. The prediction of TBM penetration rate is one of the most important part of every mechanized tunnelling project which plays a key role in selecting the machine as well. One of the major difficulties and challenges in TBM performance prediction is to apply novel approaches to predict the TBMs penetration rate. Considering the importance of this issue, the objective of this research work is to attain more realistic models for predicting TBM penetration rate in Iranian water conveyance tunneling. With this respect, a database comprises field data and machine parameters in Chamshir water conveyance tunneling project were established. The data were then analyzed through artificial neural networks (ANN), support vector machine (SVM) and gene expression programming (GEP). Results demonstrated that obtained values of the coefficient of determination (R2) and the root mean square error (RMSE) found to be 0.99 and 0.15 for ANN, 0.95 and 0.37 for SVM, 0.99 and 0.11 for GEP, respectively. These models can be applied to predict TBM penetration rate in the Chamshir water conveyance tunnel. Moreover, it can be concluded that the GEP method has the higher accuracy (maximum R2 and minimum RMSE) among all predictive models.