Addressing the Cold-Start Challenge in Building Predictive Maintenance: Translating Facility Manager Expertise into Criticality Indices
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Modern smart buildings rely on complex mechanical and electrical systems such as HVAC units, pumps, and lifts to function effectively. However, determining the criticality of these assets for Predictive Maintenance (PdM) prioritisation is often constrained by the ’cold start’ problem, where newly commissioned buildings lack the historical failure data required for data-driven ranking. While industry standards provide generic equipment lists, they often fail to capture the context-specific operational risks recognised by Facility Managers. This knowledge is typically tacit, subjective, and poorly documented, limiting its integration into interoperable digital strategies.
This paper presents a method to translate qualitative human expertise into a quantitative engineering metric. The approach begins with qualitative interviews to elicit latent decision-making criteria specifically safety, business continuity, and occupant comfort. These insights inform a psychometric survey mapped to standardised asset classes using the Brick Schema ontology, enabling consistent asset categorisation across buildings. To process these inputs, the study employs a Mamdani fuzzy inference system with centroid defuzzification, which handles the linguistic uncertainty of human responses and produces a continuous criticality index for each asset class. The research shows how qualitative expert judgement can be structured into a reproducible Criticality Index (CI) and Asset Health Index (AHI). These indices allow asset owners to prioritise PdM resources based on a transparent, expert-informed assessment of operational risk rather than generic heuristics, providing a semantically grounded foundation for deploying predictive algorithms in data-scarce environments.
How to Cite
##plugins.themes.bootstrap3.article.details##
cold-start problem, criticality assessment, predictive maintenance, fuzzy logic, Mamdani inference, Asset Health Index, Brick ontology, facility management
Ascione, F., Bianco, N., De Masi, R. F., Mastellone, M., Mauro, G. M., & Vanoli, G. P. (2020). The role of occupant behavior in affecting the feasibility of energy refurbishment of residential buildings: Typical effective retrofits compromised by typical wrong habits. Energy and Buildings, 223, 110217.
Balaji, B., Bhattacharya, A., Fierro, G., Gao, J., Gluck, J., Hong, D., et al. (2018). Brick: Metadata schema for portable smart building applications. Applied Energy, 226, 1273–1292.
Binder, F., & Strauss, A. (2025). Fuzzy-logic-based decision system for optimising infrastructure maintenance. Structure and Infrastructure Engineering, 1–15.
Bouabdallaoui, Y., Lafhaj, Z., Yim, P., Ducoulombier, L., & Bennadji, B. (2021). Predictive maintenance in building facilities: A machine learning-based approach. Sensors, 21(4), 1044.
Florian, E., Sgarbossa, F., & Zennaro, I. (2021). Machine learning-based predictive maintenance: A cost-oriented model for implementation. International Journal of Production Economics, 236, 108114.
Gispert, D. E., Yitmen, I., Sadri, H., & Taheri, A. (2025). Development of an ontology-based asset information model for predictive maintenance in building facilities. Smart and Sustainable Built Environment, 14(3), 740–757.
Guzmán-Torres, J. A., Domínguez-Mota, F. J., Alonso-Guzmán, E. M., Martínez-Molina, W., & Tinoco-Guerrero, G. (2025). A digital twin approach-based method for classification of salt damage in building evaluation. Mathematics and Computers in Simulation, 233, 433–447.
Hakimi, O., Liu, H., & Abudayyeh, O. (2025). Deep learning-driven multi-level data fusion for predictive maintenance of concrete bridge decks. Automation in Construction, 175, 106180.
Hermansa, M., Kozielski, M., Michalak, M., Szczyrba, M., & Wróbel, Ł. (2022). Sensor-based predictive maintenance with reduction of false alarms: A case study in heavy industry. Sensors, 22(1), 226.
Hoffmann, M. W., Wildermuth, S., Gitzel, R., et al. (2020). Integration of novel sensors and machine learning for predictive maintenance in medium-voltage switchgear. Sensors, 20(7), 2099.
Hosamo, H. H., Mazzetto, S., Matveev-Matis, E., & Svennevig, P. R. (2023). Digital twin framework for automated fault source detection for comfort performance evaluation. Energy and Buildings, 281, 112732.
Hosamo, H. H., Svennevig, P. R., Svidt, K., Han, D., & Nielsen, H. K. (2022). A digital twin predictive maintenance framework of AHUs based on automatic fault detection and diagnostics. Energy and Buildings, 261, 111988.
Hosseini Gourabpasi, A., & Nik-Bakht, M. (2024). BIM-based automated fault detection and diagnostics of HVAC systems in commercial buildings. Journal of Building Engineering, 87, 109022.
Hu, W., & Cai, Y. (2024). A semi-supervised method for digital twin-enabled predictive maintenance in the building industry. Neural Computing and Applications, 36, 15759–15775.
Hu, W., Wang, X., Tan, K., & Cai, Y. (2023). Digital twin-enhanced predictive maintenance for indoor climate: A parallel LSTM-autoencoder failure prediction approach. Energy and Buildings, 301, 113738.
Ilangkumaran, M., & Kumanan, S. (2009). Selection of maintenance policy for textile industry using hybrid multi-criteria decision-making approach. Journal of Manufacturing Technology Management, 20(7), 1009–1031.
Iqbal, R., Doctor, F., More, B., Mahmud, S., & Yousuf, U. (2018). Big data analytics and computational intelligence for cyber–physical systems: Recent trends and state-of-the-art applications. Future Generation Computer Systems, 105, 766–778.
Kang, J. S., Chung, K., & Hong, E. J. (2021). Multimedia knowledge-based bridge health monitoring using digital twin. Multimedia Tools and Applications.
Li, H., Hong, T., & Sofos, M. (2023). A systematic comparison and evaluation of building ontologies for deploying data-driven analytics in smart buildings. Energy and Buildings, 298, 113207.
Ma, X., Shi, Z., Guo, F., Chen, Z., & Wei, J. (2023). Digital twin model for chiller fault diagnosis based on SSAE and transfer learning. Building and Environment, 243, 110718.
Motamedi, A., Hammad, A., & Asen, Y. (2014). Knowledge-assisted BIM-based visual analytics for failure root cause detection in facilities management. Automation in Construction, 43, 73–83.
Panteli, C., Kylili, A., & Fokaides, P. A. (2020). Building information modelling applications in smart buildings: From design to commissioning and beyond: A critical review. Journal of Cleaner Production, 265, 121766.
Pedral Sampaio, R., Aguiar Costa, A., & Flores-Colen, I. (2022). A systematic review of artificial intelligence applied to facility management in the building information modeling context and future research directions. Buildings, 12(11), 1939.
Prieto, A. J., Macías-Bernal, J. M., Chávez, M. J., & Alejandre, F. J. (2017a). Fuzzy modeling of the functional service life of architectural heritage buildings. Journal of Performance of Constructed Facilities, 31(5), 04017041.
Prieto, A. J., Macías-Bernal, J. M., Silva, A., & Ortiz, P. (2019). Fuzzy decision-support system for safeguarding tangible and intangible cultural heritage. Sustainability, 11(14), 3953.
Prieto, A. J., Silva, A., de Brito, J., Macías-Bernal, J. M., & Alejandre, F. J. (2017b). Multiple linear regression and fuzzy logic models applied to the functional service life prediction of cultural heritage. Journal of Cultural Heritage, 27, 20–35.
Sahu, A., Sinha, S., & Banka, H. (2024). Fuzzy inference system using genetic algorithm and pattern search for predicting roof fall rate in underground coal mines. International Journal of Coal Science & Technology, 11, 1.
Seiti, H., & Hafezalkotob, A. (2019). Developing the R-TOPSIS methodology for risk-based preventive maintenance planning: A case study in a rolling mill company. Computers & Industrial Engineering, 128, 622–636.
SFG20. (2025). Standard maintenance specification for building engineering services. Retrieved from https://www.sfg20.co.uk
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.