A dynamic learning method based on the Gaussian process for tunnel boring machine intelligent driving

Introduction: The application of intelligent learning methods to the mining of characteristics and rules of time-series data has gained increasing attention with the rapid development of deep learning. One critical application of such methods is the intelligent assistant driving of tunnel boring machines (TBMs), for which the optimization of driving parameters is essential to improve construction efficiency. However, existing prediction models for TBM parameters are “static” and cannot dynamically capture parameter evolution during real-time driving cycles. Methods: In this study, we propose a novel dynamic learning model for TBM parameters by introducing the Gaussian process to address this problem. The model can learn decision-making experiences from historical driving cycles, dynamically update the model based on small sample data from current driving cycles, and simultaneously achieve driving parameter prediction. We focused on real-time prediction of TBM parameters in a tunnel project in western China. Results: The results show that the average relative errors of predicted total thrust and torque values were 1.9% and 2.7%, respectively, and the prediction accuracy was higher than that of conventional models such as random forest and long short-term memory. The model fully exploited updating of small samples of parameters, reducing the average time cost of the model to 29.7 s, which satisfies the requirements of efficient application. Discussion: The dynamic learning strategy of time-series data adopted in this study provides a reference for other similar engineering applications. The proposed model can improve the prediction accuracy of TBM parameters, thus facilitating the optimization of driving parameters and enhancing the construction efficiency of tunnels. Conclusion: In summary, this study establishes a dynamic learning model of TBM parameters that can dynamically capture parameter evolution and achieve accurate real-time driving parameter prediction. The proposed model can contribute to the development of intelligent assistant driving of TBMs and similar engineering applications.

[1]  Xiaoli Zhu,et al.  A propensity score matching analysis of neutrophil to lymphocyte ratio forecasts the survival of individuals undergoing the transjugular intrahepatic portosystemic shunt. , 2023, Biotechnology & genetic engineering reviews.

[2]  Yaoru Liu,et al.  Prediction of shield jamming risk for double-shield TBM tunnels based on numerical samples and random forest classifier , 2022, Acta Geotechnica.

[3]  Shui-Hua Jiang,et al.  Intelligent assistant driving method for tunnel boring machine based on big data , 2021, Acta Geotechnica.

[4]  Panagiotis G. Asteris,et al.  A hybrid GEP and WOA approach to estimate the optimal penetration rate of TBM in granitic rock mass , 2021, Soft Computing.

[5]  Chengjin Qin,et al.  Rock mass type prediction for tunnel boring machine using a novel semi-supervised method , 2021, Measurement.

[6]  Panagiotis G. Asteris,et al.  TBM performance prediction developing a hybrid ANFIS-PNN predictive model optimized by imperialism competitive algorithm , 2021, Neural Computing and Applications.

[7]  Zaobao Liu,et al.  Hard-rock tunnel lithology prediction with TBM construction big data using a global-attention-mechanism-based LSTM network , 2021 .

[8]  Zuyu Chen,et al.  Tunnel boring machines (TBM) performance prediction: A case study using big data and deep learning , 2021 .

[9]  Mahdi Hasanipanah,et al.  Potential efficacy and application of a new statistical meta based-model to predict TBM performance , 2021 .

[10]  Jian Zhou,et al.  Proposing several hybrid PSO-extreme learning machine techniques to predict TBM performance , 2021, Engineering with Computers.

[11]  Wang Xinyu,et al.  Prediction model of rock mass class using classification and regression tree integrated AdaBoost algorithm based on TBM driving data , 2020 .

[12]  Haiqing Yang,et al.  A new hybrid grey wolf optimizer-feature weighted-multiple kernel-support vector regression technique to predict TBM performance , 2020, Engineering with Computers.

[13]  Zuyu Chen,et al.  Diagnosing tunnel collapse sections based on TBM tunneling big data and deep learning: A case study on the Yinsong Project, China , 2020 .

[14]  Zhenyu Liu,et al.  TBM performance prediction with Bayesian optimization and automated machine learning , 2020 .

[15]  Yunhong Che,et al.  Data-driven state of charge estimation for lithium-ion battery packs based on Gaussian process regression , 2020, Energy.

[16]  Manoj Khandelwal,et al.  Estimation of the TBM advance rate under hard rock conditions using XGBoost and Bayesian optimization , 2020 .

[17]  Xu Guo,et al.  TBM penetration rate prediction based on the long short-term memory neural network , 2020 .

[18]  Yao Yu,et al.  Prediction of building electricity usage using Gaussian Process Regression , 2020 .

[19]  Panagiotis G. Asteris,et al.  A Gene Expression Programming Model for Predicting Tunnel Convergence , 2019, Applied Sciences.

[20]  Yi Li,et al.  Modified Gaussian Process Regression Models for Cyclic Capacity Prediction of Lithium-Ion Batteries , 2019, IEEE Transactions on Transportation Electrification.

[21]  Panagiotis G. Asteris,et al.  Supervised Machine Learning Techniques to the Prediction of Tunnel Boring Machine Penetration Rate , 2019, Applied Sciences.

[22]  Zengda Guan,et al.  Improved support vector regression models for predicting rock mass parameters using tunnel boring machine driving data , 2019, Tunnelling and Underground Space Technology.

[23]  Jianrong Tan,et al.  Prediction of geological conditions for a tunnel boring machine using big operational data , 2019, Automation in Construction.

[24]  Danial Jahed Armaghani,et al.  Development of a new hybrid ANN for solving a geotechnical problem related to tunnel boring machine performance , 2019, Engineering with Computers.

[25]  Junhong Zhao,et al.  Dynamic load prediction of tunnel boring machine (TBM) based on heterogeneous in-situ data , 2018, Automation in Construction.

[26]  Masoud Monjezi,et al.  TBM performance estimation using a classification and regression tree (CART) technique , 2018, Bulletin of Engineering Geology and the Environment.

[27]  Andreas Krause,et al.  A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions , 2016, bioRxiv.

[28]  Vu Trieu Minh,et al.  Regression Models and Fuzzy Logic Prediction of TBM Penetration Rate , 2017 .

[29]  Jamal Rostami,et al.  Application of non-linear regression analysis and artificial intelligence algorithms for performance prediction of hard rock TBMs , 2016 .

[30]  S. D. Mohammadi,et al.  Prediction of TBM penetration rate using intact and mass rock properties (case study: Zagros long tunnel, Iran) , 2015, Arabian Journal of Geosciences.

[31]  Mohammad Ataei,et al.  Predicting penetration rate of hard rock tunnel boring machine using fuzzy logic , 2014, Bulletin of Engineering Geology and the Environment.

[32]  Zhiye Zhao,et al.  Prediction model of tunnel boring machine performance by ensemble neural networks , 2007 .

[33]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[34]  Chengjin Qin,et al.  An accurate and adaptative cutterhead torque prediction method for shield tunneling machines via adaptative residual long-short term memory network , 2022 .

[35]  Liao Jianbin,et al.  A TBM advance rate prediction method considering the effects of operating factors , 2021 .

[36]  Jian Zhou,et al.  Optimization of support vector machine through the use of metaheuristic algorithms in forecasting TBM advance rate , 2021, Eng. Appl. Artif. Intell..

[37]  Mostafa Sharifzadeh,et al.  A Comparison of Artificial Neural Network and Multiple Regression Analysis in TBM Performance Prediction , 2012 .