Research On Prediction Of TBM Performance Of Deep-buried Tunnel Based On Machine Learning

In the 21 st century,tunnel construction has become an important development direction for infrastructure construction worldwide.Compared with the traditional drilling and blasting method,Tunnel Boring Machine(TBM)is widely used in the construction of long and large tunnels due to its advantages of fast driving speed and small construction disturbance,which is beneficial to environmental protection and many other advantages.Quantitative analysis and predicting of TBM performance is related to the TBM efficient driving,project schedule and cost estimation,which is of great significance in actual project guiding.Based on the relevant data in the construction process of the south of the Qinling tunnel of Hanjiang-to-Weihe River Diversion Project,this thesis obtains the main influencing factors of the TBM performance of the deep-buried tunnel.According to the characteristics of deep-buried tunnel excavation,the TBM penetration rate prediction model is established through machine learning method to provide reference for tunnel construction under similar conditions.The main research results of this thesis can be listed as follows:(1)By establishing the database of TBM performance in the south of the Qinling tunnel of Hanjiang-to-Weihe River Diversion Project,Quantitative analysis of influencing factors of TBM performance efficiency in the south of the Qinling tunnel of Hanjiang-to-Weihe River Diversion Project,TBM mechanical parameters such as total thrust,torque,revolutions per minute and rock mass parameters such as uniaxial compressive strength,volumetric joint count are the main influencing factors of TBM performance efficiency.(2)The random forest algorithm is used to select the features of the factors affecting the TBM penetration rate,and the four factors with large influence weights,including total thrust,pevolutions per minute,uniaxial compressive strength and volumetric joint count,are used as TBM penetration rate prediction models input parameters,which can improve the prediction accuracy and convergence speed of the model,and enhance the engineering practicality of the prediction model.(3)Establish three types of TBM penetration rate prediction models: multiple regression model(MR),Back Propagation Neural Network Model(BPNN)and Support Vector Regression Model(SVR).The prediction accuracy of the three models is compared and analyzed.The BPNN prediction model exhibits better prediction performance and generalization ability than the multiple regression model and SVR model,which manifest higher prediction accuracy and prediction stability.