Comparative study of predicted and actual rock mass condition in Himalayan railway tunnels

Abstract

Rishikesh-Karnprayag BG Rail Link project in Uttarakhand Himalaya, presents excavation challenges due to the complex geological setting. This study investigates discrepancies between predicted and actual rock mass conditions, encountered during the excavation of the package-5 tunnel. Despite thorough pre-construction investigation, through bore log data, in-situ tests and geophysical surveys, substantial deviations in rock quality were observed during the construction. Deviation in rock mass conditions force change in support classes, ultimately overrunning the project cost. This study aims to investigate the disparity between the predicted and actual rock mass conditions, with respect to overburden thickness. RMR, Q-System and ÖNORM B 2203, have been utilized to discern the rockmass character. A total of 632 data points were collected in the field. Lithology, presence of shear zones, and overburden thickness have been discussed to understand variance between predicted and actual rockmass condition, during the excavation. Study highlights the presence of shear zones and other uncertainties play a crucial role in discrepancies between predicted and actual conditions. At shallower depths, overestimation of rockmass is identified, with actual RMR values being lesser, along with high deviations. As overburden depth increases, the predicted and actual rockmass distributions become more aligned and fall close to each other. Additionally, four different predictive models—Random Forest (RF), Linear Regression (LR), Support Vector Regression (SVR), and K-Nearest Neighbors (KNN) are also employed in this study to estimate actual rockmass, using predicted rockmass and overburden thickness as features. This research will ultimately aid in better planning and cost management for future Himalayan tunneling projects.