Reinforcement Learning Based Monitoring and Control of Indoor Carbon Dioxide Concentration Integrating Occupancy Presence

Xie, Xiang; Lu, Qiuchen; Parlikad, Ajith Kumar; Puri, Ramprakash Srinivasan

doi:10.1061/9780784482865.028

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, an increasing number of studies are adopting AI techniques and ML algorithms to address design (Feng et al, 2019), construction (Ensafi et al, 2022), and facility management challenges (Awada et al, 2020;Feng et al, 2017;Tabrizi et al, 2012). Researchers have implemented AI and ML to address different aspects of building operation phase including air quality (Xie et al, 2020), energy consumption (Hajj-Hassan et al, 2020;Lu & Feng, 2020), and cost analysis (Liu et al, 2020;Gao et al, 2019).…”

Section: Literature Reviewmentioning

confidence: 99%

Work order prioritization using neural networks to improve building operation

2024

ITcon

View full text Add to dashboard Cite

Current practices for prioritizing maintenance work orders are mainly user-driven and lack consistency in collecting, processing, and managing the large amount of data. While decision-making methods have been used to address some of the existing challenges such as inconsistency, they also have challenges including variation between comparison during the actual prioritization task as opposed to those outside of maintenance context. The data analytics and machine learning methods can help with extracting meaningful and valuable information, finding patterns, and drawing conclusions from the available data. Such methods have benefits including faster prioritization performance leading to less failure and downtimes, reduced impact of knowledge loss, decreased cognitive workload, identification of errors for adjusting the system, and determination of important factors impacting work order processing to support the development of data requirements. This paper summarizes the background on existing gaps in processing maintenance work orders and provides an overview of machine learning methods to support prioritizing work order. The paper then discusses the work order data of an educational facility as a case study, presents information on data exploration and data cleaning approach, and provides insights gained from their maintenance work order data. The insights gained present challenges such as submission of multiple work orders as one, missing data for certain criteria, long durations for addressing some of the work orders, and the correlation between criteria collected by the facility and the schedule. The paper continues by implementing artificial neural networks to benefit from work order data collected for automatically prioritizing the future work orders. The results present the optimum neural network structure based on mean squared error estimated and provides the best value for each parameter used for the development of the model. The accuracy and efficiency of the developed model was validated by the facility experts of the educational facility.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Work order prioritization using neural networks to improve building operation

2024

ITcon

View full text Add to dashboard Cite

show abstract

Reinforcement Learning Based Monitoring and Control of Indoor Carbon Dioxide Concentration Integrating Occupancy Presence

Cited by 1 publication

References 14 publications

Work order prioritization using neural networks to improve building operation

Work order prioritization using neural networks to improve building operation

Contact Info

Product

Resources

About