http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Loy-Benitez, Jorge,Li, Qian,Ifaei, Pouya,Nam, Kijeon,Heo, SungKu,Yoo, Changkyoo Elsevier 2018 Building and environment Vol.144 No.-
<P><B>Abstract</B></P> <P>Within subway stations, the use of a mechanical ventilation system is a common strategy for improving the indoor air quality (IAQ). These ventilation systems use outdoor air to dilute pollutants on the subway platforms. However, a fixed fan speed in manual subway station ventilation systems does not consider variations in IAQ dynamics caused by disturbances yielded by the outdoor air quality (OAQ). Since the IAQ in subway stations has become a major public health concern, this study aims to analyze the IAQ dynamics at different OAQ conditions to design a new dynamic ventilation control system. The proposed method implemented a Gain Scheduling control strategy over OAQ variations at the D-Subway Station in the Seoul metropolitan area. A set of one feedback (FB) and two feedforward (FF) controllers was implemented. The results showed that the proposed control system tuned with the internal model control (IMC) method achieved an energy saving of 9% in comparison to the manual ventilation system. It was estimated a decrease in energy consumption of 158 kWh/day, representing an emission reduction of 268 kgCO<SUB>2</SUB>/day. Following, an energy cost reduction of 4325 USD yearly was estimated. Additionally, the indoor particulate matter level is maintained below a control limit considered to be unhealthy for sensitive groups (150 μg/m<SUP>3</SUP>).</P> <P><B>Highlights</B></P> <P> <UL> <LI> A dynamic gain scheduled ventilation control system dependent on outdoor air conditions was proposed for subway platforms. </LI> <LI> The indoor air quality dynamics were explored and adjusted depending on the outdoor air quality. </LI> <LI> The proposed ventilation control system reduced energy consumption by 9% in comparison to the manual ventilation system. </LI> <LI> Annual GHG emissions could be decreased by 97,820 kg CO<SUB>2</SUB> with the proposed ventilation control system. </LI> <LI> The proposed control system shows energy-saving potential adaptability for standard subway stations. </LI> </UL> </P> <P><B>Graphical abstract</B></P> <P>[DISPLAY OMISSION]</P>
Loy-Benitez, Jorge,Vilela, Paulina,Li, Qian,Yoo, ChangKyoo Academic Press 2019 Ecotoxicology and environmental safety Vol.169 No.-
<P><B>Abstract</B></P> <P>Particulate matter with aerodynamic diameter less than 2.5 µm (PM<SUB>2.5</SUB>) in indoor public spaces such as subway stations, has represented a major public health concern; however, forecasting future sequences of quantitative health risk is an effective method for protecting commuters’ health, and an important tool for developing early warning systems. Despite the existence of several predicting methods, some tend to fail to forecast long-term dependencies in an effective way. This paper aims to implement a multiple sequences prediction of a comprehensive indoor air quality index (CIAI) traced by indoor PM<SUB>2.5</SUB>, utilizing different structures of recurrent neural networks (RNN). A standard RNN (SRNN), long short-term memory (LSTM) and a gated recurrent unit (GRU) structures were implemented due to their capability of managing sequential, and time-dependent data. Hourly indoor PM<SUB>2.5</SUB> concentration data collected in the D-subway station, South Korea, were utilized for the validation of the proposed method. For the selection of the most suitable predictive model (i.e. SRNN, LSTM, GRU), a point-by-point prediction on the PM<SUB>2.5</SUB> was conducted, demonstrating that the GRU structure outperforms the other RNN structures (RMSE = 21.04 µg/m<SUP>3</SUP>, MAPE = 32.92%, R<SUP>2</SUP> = 0.65). Then, this model is utilized to sequentially predict the concentration and quantify the health risk (i.e. CIAI) at different time lags. For a 6-h time lag, the proposed model exhibited the best performance metric (RMSE = 29.73 µg/m<SUP>3</SUP>, MAPE = 29.52%). Additionally, for the rest of the time lags including 12, 18 and 24 h, achieved an acceptable performance (MAPE = 29–37%).</P> <P><B>Highlights</B></P> <P> <UL> <LI> A quantitative health risk prediction is used as a tool for the early abnormal detection of indoor PM<SUB>2.5</SUB>. </LI> <LI> Various RNN structures with memory cells are used for the sequential quantitative health risk prediction for PM<SUB>2.5</SUB> effects. </LI> <LI> Performance metrics showed that the most suitable RNN structure is the GRU. </LI> <LI> Forecasting of CIAI is conducted sequentially at different time lags, including 6, 12, 18 and 24 h. </LI> <LI> Results showed that sequential prediction is suitable even for long time lags and future time steps. </LI> </UL> </P> <P><B>Graphical abstract</B></P> <P>[DISPLAY OMISSION]</P>
Heo, SungKu,Nam, KiJeon,Loy-Benitez, Jorge,Li, Qian,Lee, SeungChul,Yoo, ChangKyoo Elsevier 2019 Energy and buildings Vol.202 No.-
<P><B>Abstract</B></P> <P>Mechanical ventilation has been widely implemented to alleviate poor indoor air quality (IAQ) in confined underground public facilities. However, due to time-varying IAQ properties that are influenced by unpredictable factors, including outdoor air quality, subway schedules, and passenger volumes, real-time control that incorporates a trade-off between energy saving and IAQ is limited in conventional rule-based and model-based approaches. We propose a data-driven and intelligent approach for a smart ventilation control system based on a deep reinforcement learning (DeepRL) algorithm. This study utilized a deep Q-network (DQN) algorithm of DeepRL to design the ventilation system. The DQN agent was trained in a virtual environment defined by a gray-box model to simulate an IAQ system in a subway station. Performance of the proposed method over three weeks was evaluated by a comprehensive indoor air-quality index (CIAI) and energy consumption under different outdoor air quality scenarios. The results show that the proposed DeepRL-based ventilation control system reduced energy consumption by up to 14.4% for the validation dataset time interval and improved IAQ from unhealthy to acceptable.</P> <P><B>Highlights</B></P> <P> <UL> <LI> DRL was used to design an autonomous ventilation control system for a subway station. </LI> <LI> A DQN algorithm was used to train an agent to regulate IAQ in a subway station. </LI> <LI> A box model was calibrated to simulate the IAQ system and generate a training dataset. </LI> <LI> State and reward functions targeting IAQ were designed for training a DQN agent. </LI> <LI> The proposed method reduced ventilation energy consumption by 14.4% to within a healthy IAQ. </LI> </UL> </P> <P><B>Graphical abstract</B></P> <P>[DISPLAY OMISSION]</P>