University of Twente Student Theses

Login

Forecasting yearly unplanned maintenance on underground waste containers based on maintenance history and demographics

Ven, F.R. (2020) Forecasting yearly unplanned maintenance on underground waste containers based on maintenance history and demographics.

[img] PDF
1MB
Abstract:Municipal solid waste is ubiquitous: every city, municipality, and country has to deal with waste generated by its inhabitants. A common collection method is to let citizens deposit their waste in large waste containers from which it is then collected. This thesis researches the unplanned (e.g. corrective) maintenance needs of large ($5m^3$) underground waste containers and attempts to forecast those maintenance needs. Literature on the subjects of maintenance forecasting and municipal solid waste generation is studied to identify possible predictors. The identified predictors are validated using a linear regression model in a case-study of the municipality of Amsterdam. The case-study shows that asset age, specific asset types, and the number of assets are meaningful indicators of upcoming maintenance. The final predictive model has an expected error of 32\% of the target variable. While the prediction error is too high for practical use, this thesis breaks ground on prediction on these specific types of assets and thoroughly documents the subject and open work for use in future work.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science MSc (60300)
Link to this item:https://purl.utwente.nl/essays/85277
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page