摘要
In pumped storage projects,the permeability of rock masses is a crucial parameter in engineering design and construction.The rock mass permeability coefficient(K)is influenced by various geological parameters,and previous studies aimed to establish an accurate relationship between K and geological parameters.This study uses the improved sparrow search algorithm(ISSA)to optimize the parameter settings of the deep extreme learning machine(DELM),constructing a prediction model with flexible parameter selection and high accuracy.First,the Spearman method is applied to analyze the correlation between geological parameters.A sample database is built by comprehensively selecting four geological indexes:burial depth,rock quality designation(RQD),fracture density characteristic index(FD),and rock mass integrity designation(RID).Hence,the defects of the sparrow search algorithm(SSA)are enhanced using the improved strategy,and the initial input weights of the DELM are optimized.Finally,the proposed ISSA–DELM model is employed to predict the permeability coefficient of rock mass in the entire study area.The results showed that the predictive performance of the model is superior to that of the DELM and SSA–DELM.Therefore,this model successfully provides insights into the distribution characteristics of rock mass permeability at engineering sites.
