Facility operations costs are enormous and organizational leaders seek opportunities to reduce the cost, especially considering the average lifecycle of a facility is 50 years and organizations depend on a functioning facility to conduct their daily business. A majority, 70-80%, of the costs of a facility asset are realized during the operation and maintenance phase of the facility life cycle (Abideen et al., 2022; Khan et al., 2022; Marocco & Garofolo, 2021). A National Institute of Standards and Technology (NIST) study 2018 summarized that $50B is spent annually on operations and maintenance in the continental United States (Thomas, 2018).
How artificial intelligence can be used with predictive maintenance to reduce facility operations and maintenance costs.
Database search for peer-reviewed literature in the last 5 years.
Study selection using predetermined inclusion/exclusion criteria.
Quality appraisal of peer-reviewed literature.
Coding and thematic analysis.
Establishing artificial intelligence in facility operations provides:
The potential for remote monitoring of facility system conditions.
Unbiased and data-backed facility system repair, investment, and response decisions.
Increased facility system online time.
Collectively, this review argues that the current body of literature provides evidence that AI offers additional capabilities to facility management on various portions of the entire facilities program. Opportunities include such things as remote monitoring, automated control of facility systems, immediate awareness of emergent conditions, predictive maintenance instead of break fixes, and countless labor-saving opportunities that reduce staffing. AI once fully operationalized can monitor the entire facility system and will relay emergent situations to alert remote operators (Ahern et al., 2023; Carlo et al., 2021; Rojek et al., 2023; Sattari et al., 2022). Traditionally, facility plant operators remain near the building management system to be alerted to an emergent condition. Today, remote devices connected to the building management system offer a level of separation but not to the extent that is possible with the enhanced use of AI. AI, when properly trained to monitor the facility system’s operational characteristics, connected to a remote device, and directly connected to the CMMS, may recognize problems in the facility operations before an error occurs and produce a work request to send a technician to perform proactive maintenance. Through this scenario-based immediate response, facility system operational time may be increased, downtime decreased, and additional resources saved.
AI will expand our capability to retain, analyze, make predictions, and make informed decisions from collected data. Not only helping operators to make decisions, but AI is currently performing cognitive functions traditionally reserved for humans. In the facility management profession, operationalized AI can provide unbiased repair responses and investment decisions. The full operational capability will be achieved when AI is monitoring the operational characteristics of the facility systems, records the data, analyzes the data, develops recommendations based on the data, and presents the recommendations to facility management professionals to make decisions.
In addition, data analysis through AI will make and implement automated decisions based on operational parameters by adjusting flow characteristics as required to maintain facility system set points. With AI, more data can be analyzed and better decision-making through data is possible. Also, through analysis of work requests, time shall be saved from prioritizing work requests because it is automated, reducing labor. The use of AI will increase facility system online time enabling the facility asset to be used for its intended purpose.
With data being the most significant obstacle, strategically transition the organization and facility management to maintain, collect, and make data-driven decisions.
Think big about Artificial intelligence in facility management but implement it small, especially in areas of the facility where data is plentiful.
If not already in progress, conduct a facility condition assessment and transition from reactive to predictive maintenance.
Abideen, D. K., Yunusa-Kaltungo, A., Manu, P., & Cheung, C. (2022). A systematic review of the extent to which BIM is integrated into operation and maintenance. Sustainability, 14(8692), 8692. https://doi.org/10.3390/su14148692
Ahern, M., O’Sullivan, D. T. J., & Bruton, K. (2023). Implementation of the IDAIC framework on an air handling unit to transition to proactive maintenance. Energy and Buildings, 284, 112872. https://doi.org/https://doi.org/10.1016/j.enbuild.2023.112872
Carlo, F. Di, Mazzuto, G., Bevilacqua, M., Ciarapica, F. E., Ortenzi, M., Donato, L. Di, Ferraro, A., & Pirozzi, M. (2021). A process plant retrofitting framework in Industry 4.0 perspective. IFAC-PapersOnLine, 54(1), 67–72. https://doi.org/https://doi.org/10.1016/j.ifacol.2021.08.007
Khan, N. M., Cao, K., Emad, M. Z., Hussain, S., Rehman, H., Shah, K. S., Rehman, F. U., & Muhammad, A. (2022). Development of Predictive Models for Determination of the Extent of Damage in Granite Caused by Thermal Treatment and Cooling Conditions Using Artificial Intelligence. Mathematics (2227-7390), 10(16), 2883. http://10.0.13.62/math10162883
Marocco, M., & Garofolo, I. (2021). Integrating disruptive technologies with facilities management: A literature review and future research directions. Automation in Construction, 131. http://10.0.3.248/j.autcon.2021.103917
Rojek, I., Jasiulewicz-Kaczmarek, M., Piechowski, M., & Mikołajewski, D. (2023). An artificial intelligence approach for improving maintenance to supervise machine failures and support their repair. In Applied Sciences (Vol. 13, Issue 8). https://doi.org/10.3390/app13084971
Sattari, F., Lefsrud, L., Kurian, D., & Macciotta, R. (2022). A theoretical framework for data-driven artificial intelligence decision-making for enhancing the asset integrity management system in the oil & gas sector. Journal of Loss Prevention in the Process Industries, 74, 104648. https://doi.org/https://doi.org/10.1016/j.jlp.2021.104648
Thomas, D. S. (2018). The costs and benefits of advanced maintenance in manufacturing NIST AMS 100-18. 1–45. https://doi.org/10.6028/NIST.AMS.100-18