Assessment of Anomaly Detection Methods Applied to Microtunneling

Abstract

The proliferation of data collected by modern tunnel boring machines presents a substantial opportunity for the application of data-driven anomaly detection (AD) techniques that can adapt dynamically to site specific conditions. Based on jacking forces measured during microtunneling, this paper explores the potential for AD methods to provide a more accurate and robust detection of incipient faults. A selection of the most popular AD methods proposed in the literature, comprising both clustering- and regression-based techniques, are considered for this purpose. The relative merits of each approach is assessed through comparisons to three microtunneling case histories in which anomalous jacking force behavior was encountered. The results highlight an exciting potential for the use of anomaly detection techniques to reduce unplanned downtimes and operation costs.