Automated Productivity Analysis of Pilot Tube Microtunneling Installations through Workflow Recognition in the Time-Series Data of Hydraulic Pressure
Publication: ICPTT 2014: Creating Infrastructure for a Sustainable World
Abstract
Monitoring the productivity of trenchless construction processes, such as Pilot Tube Microtunneling (PTMT) installations, is necessary for proactive control of construction operations. For example, engineers can correlate construction operation parameters (e.g., forces) with contextual information (e.g., soil type) for identifying factors influencing the PTMT productivity. Awareness of these correlations can help engineers select and control the equipment accordingly. Such correlations, however, are hidden in large amounts of field data. Tedious manual data collection and processing cannot capture and analyze details of PTMT workflows. This paper presents an automated data collection and interpretation approach for supporting detailed PTMT productivity analysis. This approach uses a data logger to automatically record the hydraulic pressures of equipment used during the PTMT. A two-step pattern recognition method can detect time-series patterns of the hydraulic pressure and identify cycles of operation in three stages of the PTMT:(1) pilot tube installation; (2) casing installation; and, (3) product pipe installation. The first step uses an Artificial Neural Network (ANN) to classify the time-series as belonging to a certain stage of PTMT. The second step uses an Adaptive Anomaly Detection Algorithm (AADA) to split the time-series into sections corresponding to operational cycles. A case study demonstrates that this automated approach can reliably recognize operational cycles of construction equipment in PTMT workflows.
Get full access to this article
View all available purchase options and get full access to this chapter.
Information & Authors
Information
Published In
Copyright
© 2014 American Society of Civil Engineers.
History
Published online: Dec 8, 2014
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.