Improving Data-Driven Infrastructure Degradation Forecast Skill with Stepwise Asset Condition Prediction Models

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 these 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 poorly-fit, continuous functions. This research presents four stepwise 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 8549 facilities across 61 U.S. military bases within the United States. The stepwise Weighted Slope model more accurately predicted asset degradation 92% of the time, as compared to the industry standard’s continuous self-correcting prediction model. These results suggest that using historical condition data, alongside or in-place of manufacturer expected service life, may increase the accuracy of degradation and failure prediction models. Additionally, as data quantity increases over time, the models presented are expected to improve prediction skills. The resulting improvements in forecasting enable decision makers to manage facility assets more proactively and achieve better returns on facility investments.

Cette oeuvre a été publiée sous la license Creative Commons Attribution 4.0 (CC-BY 4.0). Il est autorisé de partager et adapter l'oeuvre tant que l'auteur est crédité et la license est indiquée (avec le lien ci-dessus). Vous devez aussi indiquer si des changements on été fait vis-à-vis de l'original.