•54.9% of the annual global irradiance is composed by its diffuse part in HK.•Hourly diffuse irradiance was predicted by accessible variables.•The importance of variable in prediction was assessed by ...machine learning.•Simple prediction equations were developed with the knowledge of variable importance.
The paper studies the horizontal global, direct-beam and sky-diffuse solar irradiance data measured in Hong Kong from 2008 to 2013. A machine learning algorithm was employed to predict the horizontal sky-diffuse irradiance and conduct sensitivity analysis for the meteorological variables. Apart from the clearness index (horizontal global/extra atmospheric solar irradiance), we found that predictors including solar altitude, air temperature, cloud cover and visibility are also important in predicting the diffuse component. The mean absolute error (MAE) of the logistic regression using the aforementioned predictors was less than 21.5W/m2 and 30W/m2 for Hong Kong and Denver, USA, respectively. With the systematic recording of the five variables for more than 35years, the proposed model would be appropriate to estimate of long-term diffuse solar radiation, study climate change and develope typical meteorological year in Hong Kong and places with similar climates.
As a common engineering practice, the buildings are usually evaluated under the Typical Meteorological Year (TMY), which represents the common weather situation. The warm and cool conditions, ...however, can affect the building performance considerably, yet building performances under such conditions cannot fully be given by the conventional TMY. This paper gives approaches to constructing the weather data that represents several warm and cool conditions and compares their differences by studying the cumulative cooling demands of a typical building in a hot and humid climate. Apart from the Extreme Weather Year (EWY), the Near-Extreme Weather Year (NEWY) and Common warm/cool Years (CY) data are proposed according to the occurrence distributions of the weather over the long term. It was found that the cooling demands of NEWY and EWY differ by 4.8% from the cooling needs of TMY. The difference between the cooling demands of NEWY and CY for most calendar months can be 20% and 15%, respectively. For the hot months, the cooling demands under NEWY and CY take 7.4–11.6% and 2.3–5.6% differences from those under TMY. The uncertainties of building performance due to the ever-changing weather conditions can be essential to the robustness of building performance evaluations.
Kernel principal component analysis (KPCA) has been widely used in nonlinear process monitoring since it can capture the nonlinear process characteristics. However, it suffers from high computational ...complexity and poor scalability while dealing with real-time process monitoring and large-scale process monitoring. In this paper, a novel dimension reduction technique, local and global randomized principal component analysis (LGRPCA), is proposed for nonlinear process monitoring. The proposed LGRPCA method first maps the input space onto a feature space to reveal nonlinear patterns through random Fourier features. With the aid of random Fourier features, the proposed LGRPCA method is scalable and with much lower computational and storage costs. To exploit the underlying local and global structure information in the feature space, local structure analysis is integrated into the framework of global variance information extraction. The resulting LGRPCA can provide an improved representation of input data than the traditional KPCA. Thus, the proposed LGRPCA method is quite suitable for real-time process monitoring and large-scale process monitoring. <inline-formula> <tex-math notation="LaTeX">T^{2} </tex-math></inline-formula> and squared prediction error (SPE) statistic control charts are built for fault detection using the proposed LGRPCA method. Furthermore, contribution plots to LGRPCA-based <inline-formula> <tex-math notation="LaTeX">T^{2} </tex-math></inline-formula> and SPE (<inline-formula> <tex-math notation="LaTeX">Q </tex-math></inline-formula>) statistics are established to identify the root cause variables through a sensitivity analysis principle. The superior performance of the proposed LGRPCA-based nonlinear process monitoring method is demonstrated through a numerical example and the comparative study of the Tennessee Eastman benchmark process.
This study exams the impact of climate change on outdoor design conditions and peak loads of five Chinese cities over the five major climate zones for the winter and summer conditions. The design ...dry-bulb temperature (DDBT) and the coincident wet-bulb temperature (CWBT) for two 30-year periods; 1971–2000 and 1984–2013 were analysed. It was found that the DDBT of the period 1984–2013 was higher than that of the period 1971–2000, whereas the CWBT and the corresponding outdoor enthalpy of the period 1984–2013 was lower than that of 1971–2000 at the various cumulative frequencies. This trend implies that the increment in conductive heat gain through the building envelope due to the rising temperature can be lower than the reduction in fresh air load due to the lower outdoor air enthalpy. In this case, the peak cooling loads may reduce in all five cities under study, and this is different from the widely held view that global warming will lead to more stringent outdoor design conditions, higher peak cooling loads and larger heating, ventilation and air conditioning (HVAC) plants than the current or historical status. The implications to the “free-cooling” of HVAC systems with enthalpy control are discussed as well.
Hot and humid areas experience constant high temperatures and high humidity during summer, causing widespread concern about outdoor thermal discomfort. This paper investigates the effects of ...landscape design strategies on outdoor thermal environments during typical summer and winter weather conditions in the hot–humid areas of China. The physiological equivalent temperature (PET) is used for evaluating the thermal performance of the proposed outdoor environments. ENVI-met software was validated via field measurements for this study and was used to evaluate the outdoor thermal environment under typical summer and winter weather conditions. Three kinds of common landscape elements were analyzed: tree species, pavement, and water bodies. The results show that (1) by properly arranging landscape elements, the PET can be reduced by up to 1.6 °C in summer without sacrificing relevant thermal comfort during winter. (2) Arbors with high leaf area density (LAD) values performed better than those with a low LAD value for improved outdoor thermal comfort. (3) The influence of pavement on outdoor thermal comfort differs when under conditions with and without shade. This study provides practical suggestions for landscape design in open spaces within hot–humid areas.
Building occupant presence during varying periods is crucial to the performance studies of buildings and city regions. However, the understanding of the building occupancies on the university campus ...remains limited. To address this gap, our study employs field measurements, payment records, course arrangements, and building access systems to depict the occupancy patterns of the canteen, dormitory, library, and teaching and lab buildings during weekdays and weekends. We found that the occupancy rates across different buildings are somehow interrelated, given that the total number of occupants on campus is generally constant. Notably, dormitory occupancy rates tend to be low during the morning and afternoon course hours, which inversely correlates with the high occupancy rates in the teaching and lab buildings during these periods. Similarly, canteens experience surges in occupancy during meal times, which coincide with a decrease in library usage. Moreover, we established appliance operation schedules for dormitories through surveys and on-site investigations. Water dispensers and electronic devices were identified as the primary energy consumers for both male and female occupants, with desk-top fans and hairdryers being significant energy users for male and female occupants, respectively. These findings are essential for energy studies within a campus setting, underlining the importance of considering occupant behaviors on a regional scale.
Kernel principal component analysis (KPCA) has been widely used for nonlinear process monitoring. However, since the principal components are linear combinations of all kernel functions, traditional ...KPCA suffers from poor interpretation and high-computation cost. To address this problem, obtaining sparse coefficients in KPCA is of paramount importance, particularly for real-time process monitoring and large-scale processes. In this paper, a new sparse kernel principal component analysis via sequential approach, named SSKPCA is proposed for nonlinear process monitoring. We first incorporate elastic net regularization into the framework of KPCA to establish a modified optimization problem. Then, a sequential approach is employed to derive the solution. Different from the existing sparse KPCA method based on elastic net regularization, the extra computations associated with the kernel matrix, such as matrix inversion and matrix square root are avoided in the optimizing procedure for solving the modified optimization problem. Therefore, the proposed SSKPCA method is more efficient in numerical implementation. The SSKPCA-based <inline-formula> <tex-math notation="LaTeX">T^{2} </tex-math></inline-formula> and squared prediction error (<inline-formula> <tex-math notation="LaTeX">Q </tex-math></inline-formula>) statistics are constructed for fault detection. Furthermore, the sensitivity analysis principle is adopted for fault identification. A comparative study of Tennessee Eastman Process (TEP) is carried out to illustrate the ability and efficiency of the proposed SSKPCA-based nonlinear process monitoring method.
Planting trees is an effective way to regulate the outdoor thermal environment and combat urban heat islands (UHIs). Tree species and layout can have a considerable effect on, for example, the ...outdoor shading and wind fields, and finally the distribution of the occupant thermal sensations in outdoor spaces. We studied the influence of common tree species and layouts on the outdoor thermal environment under typical summer and winter weather conditions in the hot–humid areas of China. Each arbor model was established by the physical parameters obtained from field measurements. Physiological equivalent temperature (PET) was used to evaluate the thermal performance of the outdoor environment. The ENVI-met software was validated with field measurements and then used to assess the outdoor thermal environment under typical summer and winter weather conditions. The results showed the following: (1) Without considering the tree species, the difference in maximum PET values for different planting distances in summer and winter was 1.14 and 2.13 °C, respectively. (2) Planting arbors with different planting methods in inactive spaces had little effect on the thermal environment of the surrounding active space. (3) Arbors with high leaf area density (LAD) values performed better in regulating outdoor thermal comfort than arbors with low LAD values. The maximum differences in PET values of different arbors in summer and winter were 0.98 and 1.37 °C, respectively. This study provides practical suggestions for arbor planting in square spaces in the hot–humid areas of China.
Determination of interior daylight illuminance is the key step in daylighting schemes. Recently, climate-based daylight metrics (CBDMs) which considers the real climatic data for the location has ...been adopted to evaluate the dynamic daylight performance. However, the usual method to calculate the CBDMs is full scale computer simulations which are quite time demanding and designated skills are required. Architects and building practitioners prefer simple methods to assess daylight performance particularly during initial design process when various building schemes and concepts are being appraised. Daylight factor (DF) is the traditional daylight metric and it has a strong relationship with room parameters which can be simply modified to fit the design criteria. This paper puts forward a series of simple mathematical expressions to correlate the CBDMs with DF metrics (DFMs). The vertical outdoor illuminance at the window center point and the 49 interior points were simulated via the RADIANCE software. The results showed that there are strong correlations between these daylight metrics. The proposed approach would be useful to building professionals conducted in visual comfort, fenestration and daylighting design and evaluation in the preliminary design phase.
An investigation into the effectiveness of bioretention cells (BCs) under potential climatic changes was conducted using representative concentration pathways. A case study of Guangzhou showed ...changes in peak runoff in climate change scenarios, with obvious growth in RCP8.5 and slight growth in RCP2.6. The performance of BCs on multiple parameters, including reduction of runoff volume, peak runoff, and first flush, were examined in different design storms using a hydrology model (SWMM). The effectiveness of BCs varied non-linearly with scale. Their performance fell by varying amounts in the various scenarios. BCs could provide sufficient effects in response to short-return-period and short-duration storms, but the performance of BCs decreased with heavy storms, especially considering climate change. Hence, BCs cannot replace grey infrastructure but should be integrated with them. The method developed in this study could be useful in the planning and design of low impact development in view of future climate changes.