Research on Tunneling Parameters of Composite Strata Based on GA-BP Models
To explore the relationship between geological parameters of mixed granite composite strata and shield tunneling parameters,based on the tunnel project of Dongguan Metro Line 1,the geological exploration data and on-site tunneling data of Songshanhu Station-Dalang Station,a BP neural network is used to construct the prediction model,and the genetic algorithm is used to optimize the model and realize the prediction from stratum parameters to tunneling parameters.The results show that after data preprocessing and genetic algorithm optimization,the average error is less than 6%,and the maximum error is less than 25%,which basically meet the engineering requirements.The BP neural network model,optimized by a genetic algorithm,is used to predict the tunneling parameters,which can guide the actual project well and provide references for the unmanned and intelligent construction of the shield machine in the future.
万方数据
