Manuscript received March 12, 2021; revised July 24, 2021; accepted August 15, 2021; issue published September 28, 2021.
Abstract—The tunneling performance of Tunnel Boring Machine (TBM) is the key factor to affect its excavation effect and efficiency. This paper is based on the TBM tunnel project of Minle parking lot of Shenzhen Metro Line 6 phase II, using BP neural network and selecting 30 groups of sample data from the project cases as the research aims to predict the tunneling performance of TBM. The prediction curves corresponding to penetration, cutterhead thrust and cutterhead torque are obtained respectively, and the existing change rules are analyzed. At the same time, the prediction results of BP neural network are compared with the results of regression analysis and field measurement to verify the rationality and applicability of the BP neural network prediction algorithm. The results show that: (1) the error of BP neural network prediction algorithm is less than 3%, the overall results show that the method is suitable for TBM tunneling parameters prediction; (2) compared with the prediction results of regression analysis, it has smaller error, thus to a certain extent, BP neural network prediction algorithm has higher accuracy, which can provide reference for the prediction of TBM tunneling performance under similar geological conditions test.
Index Terms—Tunnel Boring Machine (TBM), tunneling performance, BP neural network, sample data, prediction algorithm
Cite: Chao Wang, Shifan Qiao, and Hongzhong Liu, "Application of BP Neural Network in TBM Tunneling Performance Prediction," International Journal of Structural and Civil Engineering Research, Vol. 10, No. 4, pp. 157-164, November 2021. doi: 10.18178/ijscer.10.4.157-164
Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.
Copyright © 2012-2023 International Journal of Structural and Civil Engineering Research, All Rights Reserved