Work Optimization with Association Rule Mining of Accelerated Deterioration in Building Components
Publication: Journal of Performance of Constructed Facilities
Volume 34, Issue 3
Abstract
The objective of enterprise building infrastructure management is to provide optimal allocation of maintenance, rehabilitation, and repair (MR&R) resources and to preserve the condition of building components over a planning horizon. While most approaches in the literature have studied it as a finite resource allocation problem, the presence of an underlying building network configuration has not been fully explored. The development of a network model encompassing interrelated building components introduces challenges as well as opportunities for MR&R decision making and optimized building preservation, which cannot adequately be managed using the existing decision-making frameworks. One challenge to enterprise building portfolio management is lack of understanding of the effect of one component’s condition state on another. Building component network-level optimization is not available as in other infrastructure domains, which makes calculating the benefit of component work activities on other building components very difficult to determine. This research focuses on using structured query language (SQL) based association rule mining to find frequent patterns of observed condition deterioration among different component types. This work introduces a new metric, negative effective deterioration, which is based on actual deterioration observed from inspection data relative to expected condition states. Frequent patterns of antecedent and consequent component pairs having negative effective deterioration states are discovered, and support and confidence factors indicate the strength of these network-level connections. The building component network model can improve enterprise work planning by considering the effects of negative effective deterioration on other components. This work uses case studies and data from the US Department of Defense (DoD), which owns and operates over 275,000 buildings totaling nearly 2.2 billion gross square feet (GSF) and $705 billion in plant replacement value. This paper presents a conceptual model to support building system condition assessment and MR&R decision making. This process can decrease the long-term deferred deficiency backlog by focusing limited MR&R resources not only on the components in the worst condition, but on those that would have the most adverse effect on the condition of associated components.
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 generated or used during the study are proprietary or confidential in nature and may only be provided with restrictions (e.g., anonymized data). The raw dataset consists of Sustainment Management System BUILDER data, which belongs to the US Air Force (ERDC-CERL 2018). Summary data could be provided as anonymized.
References
Agrawal, R., T. Imieliński, and A. Swami. 1993. “Mining association rules between sets of items in large databases.” ACM SIGMOD Rec. 22 (2): 207–216. https://doi.org/10.1145/170036.170072.
Alves, R., and O. Belo. 2005. Integrating pattern growth mining on SQL-server RDBMS. Braga, Portugal: Univ. of Minho.
Charette, R., and H. Marshall. 1999. Uniformat II elemental classification for building specifications, cost estimating, and cost analysis. West Conshohocken, PA: ASTM.
DoD (Department of Defense). 2013. “Memorandum of record.” In Memorandum standardizing facility condition assessments for the entire Department of Defense. Washington, DC: DoD.
DoD (Department of Defense). 2017. Base structure report; fiscal year 2017 baseline: A summary of the Department of Defense’s real property inventory. Washington, DC: DoD.
ERDC-CERL (Engineer Research and Development Center–Construction Engineering Research Laboratory). 2018. Sustainment management system BUILDER SQL data: United States Air Force instance. Vicksburg, MS: ERDC.
General Accounting Office. 2016. Summary of fiscal year 2016 federal real property profile (FRPP) open data set. Washington, DC: General Accounting Office.
Grussing, M. 2014. “Life cycle asset management methodologies for buildings.” J. Infrastruct. Syst. 20 (1): 04013007. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000157.
Grussing, M. N., D. R. Uzarski, and L. R. Marrano. 2006. “Condition and reliability prediction models using the Weibull probability distribution.” In Applications of advanced technology in transportation, 19–24. Reston, VA: ASCE.
Han, J., J. Pei, and Y. Yin. 2000. “Mining frequent patterns without candidate generation.” ACM SIGMOD Rec. 29 (2): 1–12. https://doi.org/10.1145/335191.335372.
Madanat, S., R. Mishalani, and W. H. W. Ibrahim. 1995. “Estimation of infrastructure transition probabilities from condition rating data.” J. Infrastruct. Syst. 1 (2): 120–125. https://doi.org/10.1061/(ASCE)1076-0342(1995)1:2(120).
Ottoman, G. R., W. B. Nixon, and S. T. Lofgren. 1999. “Budgeting for facility maintenance and repair. I: Methods and models.” J. Manage. Eng. 15 (4): 71–83. https://doi.org/10.1061/(ASCE)0742-597X(1999)15:4(71).
Shang, X. 2005. SQL based frequent pattern mining. Magdeburg, Germany: Magdeburg Universitätsbibliothek.
Sidlo, C., and A. Lukacs. 2005. “Shaping SQL-based frequent pattern mining algorithms.” In Proc., 4th International Workshop on Knowledge Discovery in Inductive Databases, 188–201. Budapest, Hungary: Hungarian Academy of Sciences.
USACE-CERL (USACE–Construction Engineering Research Laboratory). 2018a. SMS BUILDER sustainment management systems (SMS) software user manual. Washington, DC: USACE.
USACE-CERL (USACE–Construction Engineering Research Laboratory). 2018b. “SMS BUILDER website.” Accessed October 18, 2018. http://sms.erdc.dren.mil.
Wang, S. 2014. “Optimization models for network-level transportation asset preservation strategies.” Doctoral dissertation, Dept. of Civil Engineering, Univ. of Toledo.
Wong, J. K., and H. Li. 2008. “Application of the analytic hierarchy process (AHP) in multi-criteria analysis of the selection of intelligent building systems.” Build. Environ. 43 (1): 108–125. https://doi.org/10.1016/j.buildenv.2006.11.019.
Xuequn, S., S. Kai-Uwe, and G. Ingolf. 2000. SQL based frequent pattern mining with FP-growth. Magdeburg, Germany: Univ. of Magdeburg.
Information & Authors
Information
Published In
Copyright
©2020 American Society of Civil Engineers.
History
Received: Jun 28, 2019
Accepted: Nov 25, 2019
Published online: Mar 23, 2020
Published in print: Jun 1, 2020
Discussion open until: Aug 23, 2020
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.