There is high risk of water inrush and ground collapse accidents when tunnelling in karst areas. Based on the case study of an urban metro tunnel, this paper focuses on karst cave treatment and waterproofing strategies for earth pressure balancing (EPB) shield tunnelling in karst areas containing large amounts of karst caves and fissures. When the shield machine enters the karst area, water gush easily occurs, posing serious threats to tunnelling safety. The distribution characteristic of limestone fractures, karst caves, and fissures in the karst area were analyzed according to the geological survey results. Further, water inrush risk and engineering difficulties were analyzed. Subsequently, a compound karst cave treatment and waterproofing strategy for EPB shield tunnelling was proposed and implemented. Water inflow is successfully reduced and ground collapse accident is avoided using the compound karst cave treatment and waterproofing strategy.

Based on the left tunnel of the Liuxiandong Station to Baimang Station section of Shenzhen Metro Line 13 (China), a prediction model for the advanced rate of dual-mode shield tunneling in complex strata was established to explore intelligent tunneling technology in complex ground. Firstly, geological parameters of the complex strata and on-site monitoring parameters of EPB/TBM dual-mode shield tunneling were collected, with tunneling parameters, shield tunneling mode, and strata parameters selected as input features. Subsequently, the Isolation Forest algorithm was employed to remove outliers from the original advance parameters, and an improved mean filtering algorithm was applied to eliminate data noise, resulting in the steady-state phase parameters of the shield tunneling process. The base model was chosen as the Long-Short Term Memory (LSTM) recurrent neural network. During the model training process, particle swarm optimization (PSO), genetic algorithm (GA), differential evolution (DE), and Bayesian optimization (BO) algorithms were, respectively, combined to optimize the model’s hyperparameters. Via rank analysis based on evaluation metrics, the BO-LSTM model was found to have the shortest runtime and highest accuracy. Finally, the dropout algorithm and five-fold time series cross-validation were incorporated into the BO-LSTM model, creating a multi-algorithm-optimized recurrent neural network model for predicting tunneling speed. The results indicate that (1) the Isolation Forest algorithm can conveniently identify outliers while considering the relationship between tunneling speed and other parameters; (2) the improved mean filtering algorithm exhibits better denoising effects on cutterhead speed and tunneling speed; and (3) the multi-algorithm optimized LSTM model exhibits high prediction accuracy and operational efficiency under various geological parameters and different excavation modes. The minimum Mean Absolute Percentage Error (MAPE) prediction result is 8.3%, with an average MAPE prediction result below 15%.