Research on Stratum Identification Method Based on TBM Tunneling Characteristic Parameters

In order to obtain continuous stratum information during TBM tunneling, using tunneling parameters, recognition is carried out through the K-nearest neighbor model, and model improved by entropy weight method improve rate. By analyzing correlation between characteristic parameters stratum, parameter vector which most sensitive obtained sensitivity analysis, based on algorithm established. Aiming at problem that has a large error in complex formation recognition, established, wrong data of recalculated. The rate new increased from 90.95% 98.55%. results show better effect for interval with single distribution, significantly improved, provides an effective parameters.