Intelligent segment typesetting in shield tunneling based on artificial neural networks and transfer learning

Shield tunneling is the method most commonly used for underground projects. Segment typesetting, which involves determining the optimal assembly point for each segment ring and sequentially assembling them into a complete tunnel, is a critical step in shield tunneling. Currently, this typesetting process relies heavily on the operator’s experience at construction sites, which does not guarantee quality. Furthermore, research focuses mainly on the commonly used 16-point segment typesetting, largely ignoring other segment types. In addition, the reliability of these studies in site applications remains unsatisfactory. To address these issues, we propose an intelligent method for segment typesetting using an artificial neural network (ANN) and transfer learning. Due to insufficient historical data for ANN training, a dataset creation method was devised based on the Monte Carlo method and manual annotation. An ANN model was then developed to typeset 16-point segments, with its hyperparameters optimized through Bayesian optimization. Subsequently, the trained model was adapted to other segment types via transfer learning, using 10-point segments as a case study. Based on the test set established in this study, our proposed method showed superior performance compared with several commonly used machine learning methods and a representative and well-validated segment typesetting method. It was also validated using real data collected from construction sites, achieving an accuracy of 93.75% for 16-point segments and 91.43% for 10-point segments, both of which significantly surpass the results from manual typesetting on-site. The proposed method achieves accurate, rapid, and intelligent segment typesetting, which is adaptable to various segment types.