Facility management involves a variety of processes with a large amount of data for managing and maintaining facilities. Processing and prioritizing work orders constitute a big part of facility management, given the large number of work orders submitted daily. Current practices for prioritizing work orders are mainly user-driven and lack consistency in collecting, processing, and managing a large amount of data. Decision-making methods have been used to address challenges such as inconsistency. However, they have challenges, including variations between comparisons during the actual prioritization task as opposed to those outside of the maintenance context. Data-driven methods can help bridge the gap by extracting meaningful and valuable information and patterns to support future decision-makings. Through a review of the literature, interviews, and survey questionnaires, this research explored different industry practices in various facilities and identified challenges and gaps with existing practices. Challenges include inconsistency in data collection and prioritizing work orders, lack of data requirements, and coping strategies and biases. The collected data showed the list of criteria and their rankings for different facilities and demonstrated the possible impact of facility type, size, and years of experience on criteria selection and ranking. Based on the results, this research proposed a methodology to automate the process of prioritizing work orders using Neural Networks. The research analyzed the work order data obtained from an educational facility, explained data cleaning and preprocessing approaches, and provided insights. The data exploration and preprocessing revealed challenges such as submission of multiple work orders as one, missing data for certain criteria, long durations for work orders' execution, and lack of correlation between collected criteria and the schedule. Through hyperparameter tuning, the optimum neural network configuration was identified. The developed neural network predicts the schedule of new work orders based on the existing data. The outcome of this research can be used to develop requirements and guidelines for collecting and processing work order data, improve the accuracy of work order scheduling, and increase the efficiency of existing practices using data-driven approaches. / Doctor of Philosophy / Facility Management (FM) is a profession that integrates various disciplines to ensure the comfort and safety of the occupants, efficiency of the built environment, and functionality of the building while meeting the main objectives of the owners. It involves various functions, including space management, communication, contract management, inspection, etc. Among many of these FM functions, maintenance-related tasks occupy 79% of the facility managers' responsibilities and %60 of the building cost in its whole lifecycle (design, construction, and operation). Prioritizing and processing work orders constitute a big part of facility maintenance management and requires a large amount of information submitted with hundreds of orders that need to be prioritized and turned into actions on a daily basis.
Although vast amounts of work orders are submitted daily, the process of prioritizing orders has been done manually or partially through management systems rendering the process very challenging. The existing practices are highly dependent on the extent of knowledge, experience, and judgment of responsible staff available, are impacted by human cognitive workload and coping strategies and are challenged by inconsistency in data collection and uncertainty in decision-making. Delays in processing work orders can lead to asset downtimes and failure impacting occupants' comfort, health, and safety while increasing the cost of operation. Additionally, based on the results of previous studies, the alternative comparison for prioritizing work orders varies and is more realistic when performed during the actual work order prioritization task as opposed to outside of the maintenance context.
Artificial Intelligence (AI) and Machine Learning (ML) algorithms have provided opportunities to benefit from the historical data collected and stored by the facilities. Since a large number of work orders are generated and stored by facilities, such methods can be used to address the challenges with existing practices to reduce errors, downtimes, and asset failures and improve the operation of the buildings by supporting automation within the systems.
This dissertation first aims to explore the existing practices for processing and prioritizing work orders and identifying their gaps and challenges. Second, it investigates the implementation of Artificial Neural Networks (ANNs) to automate the prioritization of future work orders. The ANN is one type of machine learning model which reflects and mimics the behavior of the human brain to understand the relationship between a set of data allowing computer programs to solve complex problems. This research will improve the existing practices for processing work orders by allowing the automation of future work order prioritization. It also provides the basis for the development of data requirements to further support existing practices.
| Identifer | oai:union.ndltd.org:VTETD/oai:vtechworks.lib.vt.edu:10919/112247 |
| Date | 20 October 2022 |
| Creators | Ensafi, Mahnaz |
| Contributors | Myers-Lawson School of Construction, Thabet, Walid Y., Yang, Eunhwa, Besiktepe, Deniz, Afsari, Kereshmeh, Gao, Xinghua |
| Publisher | Virginia Tech |
| Source Sets | Virginia Tech Theses and Dissertation |
| Language | English |
| Detected Language | English |
| Type | Dissertation |
| Format | ETD, application/pdf, application/pdf |
| Rights | In Copyright, http://rightsstatements.org/vocab/InC/1.0/ |
Page generated in 0.0027 seconds