Periodic Local Multi-way Analysis and Monitoring of Indoor Air Quality in a Subway System Considering the Weekly Effect

Kang, OnYu; Liu, Hongbin; Kim, Minjeong; Kim, Jeong Tai; Wasewar, Kailas L.

doi:10.1177/1420326x12470285

Cited by 14 publications

(8 citation statements)

References 32 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the four main types of models, other statistical models were also applied in IAQ studies including PCR and PARAFAC . The PCR model consisting of a PCA followed by a regression was used to predict indoor PM concentrations in schools.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning and statistical models for predicting indoor air quality

et al. 2019

View full text Add to dashboard Cite

Indoor air quality (IAQ), as determined by the concentrations of indoor air pollutants, can be predicted using either physically based mechanistic models or statistical models that are driven by measured data. In comparison with mechanistic models mostly used in unoccupied or scenario-based environments, statistical models have great potential to explore IAQ captured in large measurement campaigns or in real occupied environments. The present study carried out the first literature review of the use of statistical models to predict IAQ. The most commonly used statistical modeling methods were reviewed and their strengths and weaknesses discussed.Thirty-seven publications, in which statistical models were applied to predict IAQ, were identified. These studies were all published in the past decade, indicating the emergence of the awareness and application of machine learning and statistical modeling in the field of IAQ. The concentrations of indoor particulate matter (PM 2.5 and PM 10 ) were the most frequently studied parameters, followed by carbon dioxide and radon. The most popular statistical models applied to IAQ were artificial neural networks, multiple linear regression, partial least squares, and decision trees. K E Y W O R D Sartificial neural networks, data mining, IAQ, partial least squares, particulate matter, regression | 705 WEI Et al.

show abstract

Section: Resultsmentioning

confidence: 99%

“…and PARAFAC 72. The PCR model consisting of a PCA followed by a regression was used to predict indoor PM concentrations in schools.…”

mentioning

confidence: 99%

Machine learning and statistical models for predicting indoor air quality

et al. 2019

View full text Add to dashboard Cite

show abstract

“…To monitor the process data using the sub-PCA method, the loading matrix (P * ) and singular-value diagonal matrix (S * ) are uniformed as follows: (9) and (10) where is the eigenvalue matrix of the covariance matrix ( ) T for the time-slice matrix. The loading matrix P * can be divided into two parts: the principal component subspace loading matrix ( ) and the residual space loading matrix ( ) to reduce the dimensionality of the original data, which is also true for S * .…”

Section: Sub-principal Component Analysis (Sub-pca)mentioning

confidence: 99%

“…In general, IAQ data in subway systems have periodic patterns, such as diurnal and weekly cycle variations, since subway utilization patterns, including the number of passengers and train schedules, are varied throughout a day or a week [9,10]. To consider the hourly variations, the IAQ data in the subway system were formed into a three-dimensional matrix with sample numbers, measured variables, and sample time.…”

Section: Introductionmentioning

confidence: 99%

Localized indoor air quality monitoring for indoor pollutants’ healthy risk assessment using sub-principal component analysis driven model and engineering big data

Shi

Kim

Lee

et al. 2015

Korean J. Chem. Eng.

Self Cite

View full text Add to dashboard Cite

Indoor air quality (IAQ) in subway systems shows periodic dynamics due to the number of passengers, train schedules, and air pollutants accumulated in the system, which are considered as an engineering big data. We developed a new IAQ monitoring model using a sub-principal component analysis (sub-PCA) method to account for the periodic dynamics of the IAQ big data. In addition, the IAQ data in subway systems are different on the weekdays and weekend due to weekly effect, since the patterns of the number of passengers and their access time on the weekdays and weekend are different. Sub-PCA-based local monitoring was developed for separating the weekday and weekend environmental IAQ big data, respectively. The monitoring results for the test data at the Y-subway station clearly showed that the proposed method could analyze an environmental IAQ big data, improve the monitoring efficiency and greatly reduce the false alarm rate of the local on-line monitoring by comparison with the multi-way PCA.

show abstract

“…The concentration of air pollutants inside the underground subway station can vary in periodic diurnal pattern in accordance with the number of passengers and subway frequency (as shown in Figure 1). 19,20 In this study, an IDP 24,25 was used to determine the optimal set-points of the ventilation control system at every time intervals when the IAQ periodic pattern varies. The implementation allows the IDP to search for the optimal set-point for ventilation control during a one-day period which is separated into several time segments of equal intervals.…”

Section: Theory On Idpmentioning

confidence: 99%

Economical control of indoor air quality in underground metro station using an iterative dynamic programming-based ventilation system

Kim

Braatz

Kim

2016

Indoor and Built Environment

Self Cite

View full text Add to dashboard Cite

A set-point of ventilation control system plays an important role for efficient ventilation inside metro stations, since it affects level of indoor air pollutants and ventilation energy consumption concurrently. In this study, to maintain indoor air quality (IAQ) at a comfortable range with a lower ventilation energy consumption, the optimal set-points of the ventilation control system were determined. The concentration of air pollutants inside the station shows a periodic diurnal variation in accordance with the number of passengers and subway frequency. To consider the diurnal variation of IAQ, an iterative dynamic programming (IDP) that searches for a piecewise control policy by separating whole system duration into several stages was applied. The optimal set-points of the ventilation control system in underground D-subway station, Korea were determined at every 3, 2, and 1 h, respectively. Then, according to the set-point changes, the ventilation controller was adjusted to an appropriate ventilation fan speed, correlating to the amount of outdoor PM10 that flows into the station. The results showed that the ventilation control system with the IDP-based optimal set-points has a better economical ventilation performance than manual ventilation system, with a 4.6% decrease in energy consumption, maintaining a comfortable IAQ level inside the station.

show abstract

Periodic Local Multi-way Analysis and Monitoring of Indoor Air Quality in a Subway System Considering the Weekly Effect

Cited by 14 publications

References 32 publications

Machine learning and statistical models for predicting indoor air quality

Machine learning and statistical models for predicting indoor air quality

Localized indoor air quality monitoring for indoor pollutants’ healthy risk assessment using sub-principal component analysis driven model and engineering big data

Economical control of indoor air quality in underground metro station using an iterative dynamic programming-based ventilation system

Contact Info

Product

Resources

About