Machine-Learning Model for Predicting Maintenance Costs of EPDM Roofing Systems
Publication: Journal of Performance of Constructed Facilities
Volume 37, Issue 6
Abstract
Facility managers often need to accurately predict the annual maintenance of their building roofs to develop reliable and cost-effective maintenance plans that maximize their performance and life expectancy. This article presents the development of a novel machine learning (ML) model using XGBoost to predict maintenance costs of ethylene propylene diene monomer (EPDM) roofing systems, and compare its performance to multivariate linear regression (MLR). The two models were developed in three main phases that focused on data collection and processing, model development, and performance evaluation. The collected data include 374 historical annual maintenance records of EPDM roofs that consist of maintenance cost, age, area, opening rate, and weather data. The performance of the two developed models was evaluated using four metrics: mean absolute percentage error (MAPE), accuracy, root square mean error (RMSE), and coefficient of determination (). The outcome of this performance evaluation illustrates that the average accuracy of the ML model in predicting maintenance costs of EPDM roofs (88.20%) was significantly higher than the MLR model (68.30%). This highlights the original contributions of the developed ML model. The ML model has novel capabilities to provide much-needed support for facility managers to improve the accuracy of estimating the annual maintenance costs of EPDM roofs to ensure the development of reliable maintenance plans for this type of roof.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
References
Abdallah, G. N. 2018. “Examining regional weather effects on single ply roofing membranes.” Master’s thesis, Dept. of Engineering, Youngstown State Univ.
Alashari, M., K. El-Rayes, M. Attalla, and M. Al-Ghzawi. 2022. “Multivariate time series and regression models for forecasting annual maintenance costs of EPDM roofing systems.” J. Build. Eng. 54 (Aug): 104618. https://doi.org/10.1016/j.jobe.2022.104618.
Anna, S. 2018. “The advantages and disadvantages of various roof coatings.” Accessed October 21, 2022. https://uploadarticle.com/the-advantages-and-disadvantages-of-various-roof-coatings/.
Au-Yong, C. P., A. S. Ali, and F. Ahmad. 2016. “Enhancing building maintenance cost performance with proper management of spare parts.” J. Qual. Maint. Eng. 22 (1): 51–61. https://doi.org/10.1108/JQME-01-2015-0001.
Bansal, D., D. J. Evans, and B. Jones. 2005. “A real-time predictive maintenance system for machine systems: An alternative to expensive motion sensing technology.” In Vol. 2005 of Proc., 2005 Sensors for Industry Conf., Sensors for Industry Conf., 39–44. New York: IEEE.
Bartels, R. 2015. “Re-interpreting R-squared, regression through the origin, and weighted least squares.” Accessed October 4, 2022. https://www.researchgate.net/publication/283333191_Re-interpreting_R-squared_regression_through_the_origin_and_weighted_least_squares.
Bell, M., and A. Moore. 2022. “XGBoost, a novel explainable AI technique, in the prediction of myocardial infarction, a UK Biobank cohort study.” Clin. Med. Insights Cardiol. 16 (Nov): 11795468221133611. https://doi.org/10.1101/2022.04.08.22273600.
Bordalo, R., J. de Brito, P. Gaspar, and A. Silva. 2011. “Service life prediction modelling of adhesive ceramic tiling systems.” Build. Res. Inf. 39 (1): 66–78. https://doi.org/10.1080/09613218.2010.532197.
Bouabdallaoui, Y., Z. Lafhaj, P. Yim, L. Ducoulombier, B. Bennadji, and E. López Droguett. 2021. “Predictive maintenance in building facilities: A machine learning-based approach.” Sensors 21 (4): 1044. https://doi.org/10.3390/s21041044.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Brownlee, J. 2016. “A gentle introduction to XGBoost for applied machine learning.” Machine Learning Mastery. Accessed February 17, 2021. https://machinelearningmastery.com/gentle-introduction-xgboost-applied-machine-learning/.
Cha, G.-W., H.-J. Moon, and Y.-C. Kim. 2021. “Comparison of random forest and gradient boosting machine models for predicting demolition waste based on small datasets and categorical variables.” Int. J. Environ. Res. Public Health 18 (16): 8530. https://doi.org/10.3390/ijerph18168530.
Chai, T., and R. R. Draxler. 2014. “Root mean square error (RMSE) or mean absolute error (MAE): Arguments against avoiding RMSE in the literature.” Geosci. Model Dev. 7 (3): 1247–1250. https://doi.org/10.5194/gmd-7-1247-2014.
Chen, T., and C. Guestrin. 2016. “XGBoost: A scalable tree boosting system.” In Proc., ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, 13–17 August 2016, 785–794. New York: ACM Special Interest Group on Knowledge Discovery and Data Mining.
Cheng, J., W. Chen, K. Chen, and Q. Wang. 2020. “Data-driven predictive maintenance planning framework for MEP components based on BIM and IoT using machine learning algorithms.” Autom. Constr. 112 (Apr): 103087. https://doi.org/10.1016/j.autcon.2020.103087.
Cullen, M. 2005. “SPSS for psychologists: A guide to data analysis using SPSS for Windows.” Br. J. Educ. Psychol. 75 (1): 139–140. https://doi.org/10.1348/000709904X24519.
Cursi, F., and G.-Z. Yang. 2019. “A novel approach for outlier detection and robust sensory data model learning.” In Proc., Int. Conf. on Intelligent Robots and Systems (IROS), Intelligent Robots and Systems (IROS), 4250–4257. New York: IEEE.
Dairu, X., and Z. Shilong. 2021. “Machine learning model for sales forecasting by using XGBoost.” In Proc., 2021 IEEE Int. Conf. on Consumer Electronics and Computer Engineering (ICCECE), 480–483. New York: IEEE.
de Myttenaere, A., B. Golden, B. Le Grand, and F. Rossi. 2016. “Mean absolute percentage error for regression models.” Neurocomputing 192 (Jun): 38–48. https://doi.org/10.1016/j.neucom.2015.12.114.
Devulapalli, K. 2015. “Neural networks for classification and regression.” Biom. Biostat. Int. J. 2 (6): 183–185. https://doi.org/10.15406/bbij.2015.02.00046.
Elmousalami, H. H. 2020. “Artificial intelligence and parametric construction cost estimate modeling: State-of-the-art review.” J. Constr. Eng. Manage. 146 (1): 03119008. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001678.
Fernandes, S., M. Antunes, A. R. Santiago, J. P. Barraca, D. Gomes, and R. L. Aguiar. 2020. “Forecasting appliances failures: A machine-learning approach to predictive maintenance.” Information (Switzerland) 11 (4): 208. https://doi.org/10.3390/info11040208.
Ferreira, C., A. Silva, I. S. Dias, J. de Brito, and I. Flores-Colen. 2021. “The impact of imperfect maintenance actions on the degradation of buildings’ envelope components.” J. Build. Eng. 33 (Jan): 101571. https://doi.org/10.1016/j.jobe.2020.101571.
Grussing, M. N., and L. Y. Liu. 2014. “Knowledge-based optimization of building maintenance, repair, and renovation activities to improve facility life cycle investments.” J. Perform. Constr. Facil. 28 (3): 539–548. https://doi.org/10.1061/(ASCE)CF.1943-5509.0000449.
Guyer, J. 2009. “Introduction to roofing systems.” Accessed September 15, 2022. https://www.cedengineering.com/userfiles/An%20Introduction%20to%20Roofing%20Systems%20R1.pdf.
Ishak, N. H., A. H. Chohan, and A. Ramly. 2007. “Implications of design deficiency on building maintenance at post-occupational stage.” J. Build. Appraisal 3 (2): 115–124. https://doi.org/10.1057/palgrave.jba.2950061.
Islam, R., S. F. Mohamed, and T. H. Nazifa. 2019. “Factors influencing facilities management cost performance in building projects.” J. Perform. Constr. Facil. 33 (3): 04019036. https://doi.org/10.1061/(ASCE)CF.1943-5509.0001284.
Juszczyk, M. 2020. “On the search of models for early cost estimates of bridges: An SVM-based approach.” Buildings 10 (1): 2. https://doi.org/10.3390/buildings10010002.
Karlsson, A., and R. Claesson. 2022. “Natural hazards impact on real estate value: A semi-quantitative risk assessment of the climatic impact on commercial buildings in Milan, Italy.” Accessed September 27, 2022. https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-314255.
Khuncumchoo, N., G. Augenbroe, and L. Thomas-Mobley. 2007. “Roof maintenance record analysis toward proactive maintenance policies.” In Proc., Construction and Building Research Conf. of the Royal Institution of Chartered Surveyors. Atlanta: American Society of Heating, Refrigerating and Air-Conditioning Engineers.
Kim, H. S., and S. Y. Sohn. 2010. “Support vector machines for default prediction of SMEs based on technology credit.” Eur. J. Oper. Res. 201 (3): 838–846. https://doi.org/10.1016/j.ejor.2009.03.036.
Kim, J., T. Kim, Y. Yu, and K. Son. 2018. “Development of a maintenance and repair cost estimation model for educational buildings using regression analysis.” J. Asian Archit. Build. Eng. 17 (2): 307–312. https://doi.org/10.3130/jaabe.17.307.
Kim, J., S. Yum, S. Son, K. Son, and J. Bae. 2021. “Modeling deep neural networks to learn maintenance and repair costs of educational facilities.” Buildings 11 (4): 165. https://doi.org/10.3390/buildings11040165.
Krstić, H., and S. Marenjak. 2017. “Maintenance and operation costs model for university buildings.” Tehnicki Vjesnik 24:193–200. https://doi.org/10.17559/TV-20140606093626.
Kubas, G. 2022. “Tackling ponding water on the roof.” Facility Executive, August 23, 2022.
Le, A. T. H., N. Domingo, E. Rasheed, and K. S. Park. 2018. “Building maintenance cost planning and estimating: A literature review.” In Proc., 34th Annual ARCOM Conf., ARCOM 2018, 697–706. Manchester, UK: Association of Researchers in Construction Management.
Lee, V., L. Liu, and R. Jim. 2014. Decision trees: Theory and algorithms. 1st ed. Singapore: World Scientific Publishing.
Lewis, M. 2007. Stepwise versus hierarchical regression: Pros and cons. Washington, DC: Department of Education.
Li, C., and S. Guo. 2011. “Development of a cost predicting model for maintenance of university buildings.” In Proc., 2011 2nd Int. Congress on Computer Applications and Computational Science, 215–221. New York: IEEE.
Li, C. S., P. J. Chen, and S. J. Guo. 2010. “Application of back-propagation artificial neural network to predict maintenance costs and budget for university buildings.” In Vol. 3 of Proc., 2010 Sixth Int. Conf. on Natural Computation (ICNC), 1546–1551. New York: IEEE. https://doi.org/10.1109/ICNC.2010.5583722.
Lin, Y., L. Zhao, X. Liu, W. Yang, X. Hao, L. Tian, and N. Nord. 2021. “Design optimization of a passive building with green roof through machine learning and group intelligent algorithm.” Buildings 11 (5): 192. https://doi.org/10.3390/buildings11050192.
Lounis, Z., M. Lacasse, D. Vanier, and B. Kyle. 1999. “Towards standardization of service life prediction of roofing membranes.” ASTM Spec. Tech. Publ. 1349 (Jan): 3–18.
Ma, J., Z. Yu, Y. Qu, J. Xu, and Y. Cao. 2020. “Application of the XGBoost machine learning method in pm2.5 prediction: A case study of Shanghai.” Aerosol Air Qual. Res. 20 (1): 128–138. https://doi.org/10.4209/aaqr.2019.08.0408.
Morgado, J., I. Flores-Colen, J. De Brito, and A. Silva. 2017. “Maintenance planning of pitched roofs in current buildings.” J. Constr. Eng. Manage. 143 (7): 05017010. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001316.
Prieto, A. J., K. Verichev, A. Silva, and J. Brito. 2020. “On the impacts of climate change on the functional deterioration of heritage buildings in South Chile.” Build. Environ. 183 (Oct): 107138. https://doi.org/10.1016/j.buildenv.2020.107138.
Rasul, M. G., and L. K. R. Arutla. 2020. “Environmental impact assessment of green roofs using life cycle assessment.” Energy Rep. 6 (Feb): 503–508. https://doi.org/10.1016/j.egyr.2019.09.015.
Robins, R. 2023. “Dealing with metal roof penetrations.” Metal Construction News, February 1, 2023.
Rossiter, W. Jr., and J. Martin. 2017. “Factors affecting the service life of seams of EPDM roof membranes.” Accessed August 24, 2022. https://www.nist.gov/publications/factors-affecting-service-life-seams-epdm-roof-membranes.
Shehadeh, A., O. Alshboul, R. E. Al Mamlook, and O. Hamedat. 2021. “Machine learning models for predicting the residual value of heavy construction equipment: An evaluation of modified decision tree, LightGBM, and XGBoost regression.” Autom. Constr. 129 (Sep): 103827. https://doi.org/10.1016/j.autcon.2021.103827.
Shohet, I. M. 2006. “Key performance indicators for strategic healthcare facilities maintenance.” J. Constr. Eng. Manage. 132 (4): 345–352. https://doi.org/10.1061/(ASCE)0733-9364(2006)132:4(345).
Silva, C. M., I. Flores-Colen, and A. Coelho. 2015. “Green roofs in Mediterranean areas: Survey and maintenance planning.” Build. Environ. 94 (P1): 131–143. https://doi.org/10.1016/j.buildenv.2015.07.029.
Smith, G. 2015. Essential statistics, regression, and econometrics. 2nd ed. Cambridge, MA: Academic Press.
Tippins, B. 2012. “White EPDM: Rising star among sustainable options.” International Institute of Building Enclosure Consultants (IIBEC). Accessed August 3, 2022. https://iibec.org/wp-content/uploads/2012-02-tippins.pdf.
Wu, B. 2021. “Prediction of drug indication list by machine learning.” Master’s thesis, Faculty of Social Sciences, Uppsala Universiteit.
Wu, J., Y. Li, and Y. Ma. 2021. “Comparison of XGBoost and the neural network model on the class-balanced datasets.” In Proc., IEEE 3rd Int. Conf. on Frontiers Technology of Information and Computer, ICFTIC 2021, 457–461. New York: IEEE.
Yu, Y., K. Son, J.-M. Kim, and T. Kim. 2018. “A probabilistic analysis on the repair and replacement cost of educational facilities.” Korean Inst. Educ. Facil. 25 (1): 3–12. https://doi.org/10.7859/kief.2018.25.1.003.
Zakariah, M. 2014. “Classification of large datasets using random forest algorithm in various applications: Survey.” Int. J. Eng. Innov. Technol. 4 (3): 189–198.
Zhong, J., Y. Sun, M. Xie, J. Yang, W. Peng, and X. Tang. 2018. “XGBFEMF: An XGBoost-based framework for essential protein prediction.” IEEE Trans. Nanobiosci. 17 (3): 243–250. https://doi.org/10.1109/TNB.2018.2842219.
Zou, M., W. G. Jiang, Q. H. Qin, Y. C. Liu, and M. L. Li. 2022. “Optimized XGBoost model with small dataset for predicting relative density of Ti-6Al-4V parts manufactured by selective laser melting.” Materials 15 (15): 5298. https://doi.org/10.3390/ma15155298.
Information & Authors
Information
Published In
Journal of Performance of Constructed Facilities
Volume 37 • Issue 6 • December 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Nov 8, 2022
Accepted: May 24, 2023
Published online: Aug 25, 2023
Published in print: Dec 1, 2023
Discussion open until: Jan 25, 2024
ASCE Technical Topics:
- Architectural engineering
- Artificial intelligence and machine learning
- Benefit cost ratios
- Building management
- Business management
- Climates
- Computer programming
- Computing in civil engineering
- Data collection
- Engineering fundamentals
- Environmental engineering
- Errors (statistics)
- Financial management
- Maintenance and operation
- Mathematics
- Meteorology
- Methodology (by type)
- Model accuracy
- Models (by type)
- Practice and Profession
- Research methods (by type)
- Roofs
- Statistics
- Structural engineering
- Structural systems
- Weather forecasting
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.