Search

Due to the severe outdoor PM2.5 pollution in China, many people have installed air‐cleaning systems in homes. To make the systems run automatically and intelligently, we developed a recurrent neural network (RNN) that uses historical data to predict the future indoor PM2.5 concentration. The RNN architecture includes an autoencoder and a recurrent part. We used data measured in an apartment over the course of an entire year to train and test the RNN. The data include indoor/outdoor PM2.5 concentration, environmental parameters and time of day. By comparing three different input strategies, we found that a strategy employing historical PM2.5 and time of day as inputs performed best. With this strategy, the model can be applied to predict the relatively stable trend of indoor PM2.5 concentration in advance. When the input length is 2 h and the prediction horizon is 30 min, the median prediction error is 8.3 µg/m3 for the whole test set. For times with indoor PM2.5 concentrations between (20,50] µg/m3 and (50,100] µg/m3, the median prediction error is 8.3 and 9.2 µg/m3, respectively. The low prediction error between the ground‐truth and predicted values shows that the RNN can predict indoor PM2.5 concentrations with satisfactory performance. [ABSTRACT FROM AUTHOR]

Abstract In order to investigate the current indoor air quality (IAQ) in China, we installed IAQ monitoring sensors in 117 homes. According to the results, only about 2% of homes were able to maintain an indoor PM2.5 concentration below 75 μ g / m 3 during the monitoring period, and 10% of homes were able to keep the nighttime carbon dioxide (CO 2) concentration below 1000 ppm. In regard to the relationships between pollutant concentrations and outdoor environmental parameters, we found that when nighttime outdoor temperatures were between 10°C and 22°C, the CO 2 concentrations essentially decreased as the temperature increased. In regard to the indoor/outdoor (I/O) ratios of PM2.5, the naturally ventilated homes had a median I/O ratio of around 0.88–0.97 when the outdoor PM2.5 concentration was lower than 75 μ g / m 3. The homes with portable air cleaners were able to maintain 89%, 71% and 56% of days with indoor PM2.5 concentrations lower than 25 μ g / m 3 in severe cold, cold and hot summer and cold winter zones, respectively. If we want to maintain both indoor CO 2 and PM2.5 concentrations below guidelines (CO 2 : 1000 ppm, PM2.5: 25 μ g / m 3 ) for more than 95% of days during the whole year, the mechanical ventilation may be a good choice. But the efficiency of the particle filters in mechanical ventilation systems should be improved, with minimize efficiency of 86%, 85%, 74%, 58%, and 62% for severe cold, cold, hot summer and cold winter, moderate and hot summer and warm winter zones, respectively. Highlights • About 2% of homes were able to maintain an indoor PM2.5 concentration below 75 μg/m3. • About 10% of homes were able to keep the nighttime CO 2 concentration below 1000 ppm. • The median PM2.5 I/O ratios for NV homes were between 0.88 – 0.97 when outdoor PM2.5 concentration was lower than 75 μg/m3. [ABSTRACT FROM AUTHOR]

Abstract A mechanical ventilation system in a residential building provides a more reliable, controllable, and comfortable means of ventilation than natural ventilation through an open window. However, the operation of a mechanical ventilation system consumes energy and may generate noise and secondary air pollutants. Thus, it is worthwhile to study residents' actual ventilation patterns. This study investigated the usage of natural and mechanical ventilation in 46 apartments across five different climate zones in China by on-site monitoring and a questionnaire survey. On average, the daily natural and mechanical ventilation durations were 11 h and 7.2 h, respectively. Large differences existed among climate regions and seasons. From north to south, as the climate became warmer, the usage of natural ventilation increased. From a seasonal perspective, the natural ventilation duration was the longest in summer and the shortest in winter. The trend of mechanical ventilation usage was opposite to that of natural ventilation. Generally, as the outdoor air temperature increased, the duration of natural ventilation increased and the duration of mechanical ventilation decreased. This study found that occupants prioritized their thermal comfort needs over healthy indoor air quality (IAQ). However, occupants were willing to spend money on energy when the health requirement could be met by mechanical ventilation. This study provides further understanding of occupants' ventilation behavior, and the results can serve as more accurate boundary conditions for analyses of IAQ, energy consumption, and thermal comfort in Chinese residential buildings. Highlights • The usage of natural and mechanical ventilation in 46 Chinese apartments was monitored for a year. • From north to south, as climate became warmer, natural ventilation increased and mechanical ventilation decreased. • Residents prioritized their thermal comfort needs over healthy indoor air quality (IAQ). • Occupants were willing to spend on energy when the health requirement could be met by mechanical ventilation. [ABSTRACT FROM AUTHOR]

The indoor air quality (IAQ) impacts occupants' health significantly. It is important to know the actual IAQ under different source strengths and occupants' air purifier usage strategies. To achieve this goal, we conducted a Monte Carlo simulation to calculate the indoor pollutant concentrations under different conditions. It is confirmed that our simulation is reliable by comparing the simulation results with actual measurement results. According to the simulation results, we found that indoor nighttime CO 2 , formaldehyde and PM2.5 were lowest in summer. In spring and winter, the nightly indoor CO 2 concentration should be kept below 1000 ppm for F3 homes (formaldehyde semission rate: 0.03–0.06 m g / ( m 2 ⋅ h)) and below 900 ppm for F4 homes (formaldehyde emission rate: 0.06–0.12 m g / ( m 2 ⋅ h)) to ensure that the nighttime formaldehyde concentration is lower than 80 μ g / m 3 for one-occupant room. The mean indoor PM2.5 concentration among all sample rooms decreased from 53.2 μ g / m 3 to 36.8 μ g / m 3 under strategy I (using air purifiers every day) and to 45.8 μ g / m 3 under strategy II (only using when outdoor PM2.5 concentration larger 75 μ g / m 3 ). Under the condition of keeping the nighttime CO 2 concentration below 1000 ppm, the fraction of healthy days increased from 33.1% to 59.4% and 46.9% for one- and two-occupant rooms under strategy I, respectively. The fraction of unhealthy days decreased from 18.2% to about 7% and 11% under strategy I and strategy II, respectively. Additionally, the suitable clean air change rate was 3–4 h−1 under current usage time. • We evaluate the current IAQ with the latest technical standard in China. • The C CO2 , C PM2.5 and C HCHO are lowest in summer for homes in Tianjin. • Keeping the indoor C CO2 lower than 1000 ppm is insufficient in some cases. • The suitable clean air change rate is 3–4 h−1 under current usage habits. [ABSTRACT FROM AUTHOR]

The natural ventilation rate in bedrooms at night has been found to be insufficient at times. To create good indoor air quality with minimal energy consumption, we need to know when the ventilation rate will be insufficient. To achieve this goal, we monitored indoor CO 2 concentrations in bedrooms in 24 apartments, together with related outdoor parameters. With this dataset, we built an artificial neural network (ANN) model to predict when the ventilation rate would be insufficient. The sample sizes for the training set and test set are 2760 sample days and 690 sample days, respectively. The overall accuracy levels of this ANN model are 80.2% and 79.3% for the training set and test set, respectively. According to the model, the indoor CO 2 concentration level is significantly affected by the building floor on which the apartment is located and nighttime outdoor temperature. Apartments on an upper floor usually had lower probability of the indoor CO 2 concentration reaching 1000 ppm than apartments on a lower floor. Furthermore, the probability dropped to its lowest point at 15–20∘C, and it rose significantly when the nighttime outdoor temperature increased or decreased. Increasing wind strength decreased the probability only when the outdoor temperature was greater than approximately 20∘C. In contrast, when the temperature was low, increasing wind strength may have caused the probability to increase because of the uncomfortable sensation created by increasing wind velocity. Throughout the year, the probability is estimated to be high in the middle of summer and winter. • We developed a model to predict the ventilation effect for residential buildings. • Window-opening behaviour was considered to predict the actual ventilation effect. • We identified the change pattern of the probability of insufficient ventilation. [ABSTRACT FROM AUTHOR]