Pipejacking clogging detection in soft alluvial deposits using machine learning algorithms

Abstract

‘Clogging’ is a common issue encountered during tunnelling in clayey soils which can impede tunnel excavation, cause unplanned downtimes and lead to significant additional project costs. Clogging can result in a drastic reduction in performance due to reduced jacking speeds and the time needed for cleaning if it cannot be fully mitigated. The data acquired by modern tunnel boring machines (TBMs) have grown significantly in recent years presenting a substantial opportunity for the application of data-driven artificial intelligence (AI) techniques. In this study, a baseline assessment of clogging in slurry-supported pipejacking is performed using a combination of TBM parameters and semi-empirical diagrams proposed in the literature. The potential for one-class support vector machines (OCSVM), isolation forest (IForest) and robust covariance (Robcov) to assess the tendency for clogging is then explored in this work. The proposed approach is applied to a pipejacking case history in Taipei, Taiwan, involving tunnelling in soft alluvial deposits. The results highlight an exciting potential for the use of AI techniques to detect clogging during slurry-supported pipejacking.