Enhanced wear prediction of tunnel boring machine disc cutters for accurate remaining useful life estimation using a hybrid model

Abstract

In tunnel construction with tunnel boring machines (TBMs), accurate prediction of the remaining useful life (RUL) of disc cutters is critical for timely maintenance and replacement to avoid delays and cost overruns. This paper introduces a novel hybrid model, integrating fundamental and data-driven approaches, to enhance wear prediction of TBM disc cutters and enable accurate RUL estimation. The fundamental model is improved by incorporating composite wear mechanisms and load estimation techniques, showcasing superior prediction accuracy compared to single-mechanism models. Additionally, the hybrid model innovatively incorporates a data-driven supplementary residual term into the improved fundamental model, leading to a high-performance wear prediction model. Using actual field data from a highway tunnel project in Shenzhen, the performance of the hybrid model is rigorously tested and compared with pure fundamental and data-driven models. The hybrid model outperforms the other models, achieving the highest accuracy in predicting TBM disc cutter wear (mean absolute error (MAE) = 0.53, root mean square error (RMSE) = 0.64). Furthermore, this study thoroughly analyzes the hybrid model’s generalization capability, revealing significant impacts of geological conditions on prediction accuracy. The model’s generalization capability is also improved by expanding and updating the data sets. The RUL estimation results provided by the hybrid model are straightforward and effective, making it a valuable tool by which construction staff can monitor TBM disc cutters.