REAL-TIME ROCK MASS QUALITY PREDICTION USING ONLINE TRANSFER LEARNING IN TBM TUNNELLING
Accurate and real-time perception of rock mass quality during Tunnel Boring Machine (TBM) excavation is essential for ensuring operational safety, optimizing support measures, and minimizing construction risks. This challenge becomes even more critical in newly constructed tunnels, where limited prior geological investigations restrict the ability to promptly evaluate surrounding rock conditions. To address this issue, this study proposes a physical feature–shared online transfer learning framework that enables cross-engineering rock mass quality prediction using monitored data from previously completed tunnels. Framework Overview The proposed framework integrates three core components: 1️⃣ Online Data Stream Processor A real-time data acquisition and processing module was developed to handle continuous TBM monitoring data. This processor performs: Real-time data collection Data segmentation Stream-based feature extraction Importantly, it extracts physical shared...