Date of Award
Master of Science
Department of Systems Engineering and Management
Steven J. Schuldt, PhD
Organizations with large facility and infrastructure portfolios have used asset management databases for over ten years to collect and standardize asset condition data. Decision makers use this data to predict asset degradation and expected service life, enabling prioritized maintenance, repair, and renovation actions that reduce asset life-cycle costs and achieve organizational objectives. However, these asset condition forecasts are calculated using standardized, self-correcting distribution models that rely on continuous functions. This research presents four step wise asset condition forecast models that utilize historical asset inspection data to improve prediction accuracy: (1) Slope, (2) Weighted Slope, (3) Condition-intelligent Weighted Slope, and (4) Nearest Neighbor. Model performance was evaluated against BUILDER SMS, the industry-standard asset management database, using data for five roof types on 8,549 facilities across 61 U.S. military bases within the Contiguous United States. The step wise Weighted-slope model predicted asset degradation more accurately than BUILDER SMS 92 of the time. These results suggest that using historical condition data, alongside or in-place of manufacturer expected service life, may increase degradation and failure prediction accuracy. Additionally, the developed models are expected to improve prediction skills as data quantity increases over time. These results are expected to enable decision makers to achieve more accurate construction management and infrastructure investment objectives.
DTIC Accession Number
Lamm, Kurt R., "Data- Driven Asset Degradation Modeling: An Enterprise-wide Roof System Case Study" (2021). Theses and Dissertations. 4950.