Search

There is a growing need for accurate and interpretable machine learning models of thermal comfort in buildings. Physics-informed machine learning could address this need by adding physical consistency to such models. This paper presents metamodeling of thermal comfort in non-air-conditioned buildings using physics-informed machine learning. The studied metamodel incorporated knowledge of both quasi-steady-state heat transfer and dynamic simulation results. Adaptive thermal comfort in an office located in cold and hot European climates was studied with the number of overheating hours as index. A one-at-a-time method was used to gain knowledge from dynamic simulation with TRNSYS software. This knowledge was used to filter the training data and to choose probability distributions for metamodel forms alternative to polynomial. The response of the dynamic model was positively skewed; and thus, the symmetric logistic and hyperbolic secant distributions were inappropriate and outperformed by positively skewed distributions. Incorporating physical knowledge into the metamodel was much more effective than doubling the size of the training sample. The highly flexible Kumaraswamy distribution provided the best performance with R2 equal to 0.9994 for the cold climate and 0.9975 for the hot climate. Physics-informed machine learning could combine the strength of both physics and machine learning models, and could therefore support building design with flexible, accurate and interpretable metamodels. [ABSTRACT FROM AUTHOR]

The Mandya district of Karnataka, India, houses a unique Jain settlement constructed about 1000 years ago. Recent excavations by the Archaeological Survey of India (ASI) indicate a high degree of engineering skills among the builders of this settlement. Adapting to heat-stresses in a region where the Monsoons often failed was and is still a matter of concern. Ingenious methods were adopted to modulate bioclimatic responses to maintain thermal comfort indices. The Aretippurians used composite building fabrics which modulated heat transfer to the interiors. Indeed, the thermal transmittances for these composite fabrics were low to moderate for both the temple complexes as well as the dormitories; these were 0.27 Wm−1K−1 and 0.23 Wm−1K−1, respectively. A site visit revealed that a unique and engineered micro-climate was also made to prevail on this hilltop settlement housing several hundred Jain settlers. A granite skirted reservoir was indeed the pièce-de-résistance promoting hydraulic air-conditioning for eight months of the year around the premises with copious winds blowing over a large and exposed rain-fed reservoir. This fanned chilled air across the open plan temples, courtyards, and lived-in areas. This paper explores bioclimatic responses for around 120 residents to the prevailing indoor settings modulated by an engineered microclimate. This was possible because of the staggered layout, unique building forms, use of mixed building fabric, and carefully chosen glazing ratios which yielded salubrious settings. Clearly, this entailed a complex interplay between the intercepted solar insolation, structure-driven turbulence, and the transfer of heat across the original composite walls within and around the complex, requiring a systematic experimental as well as modelling study. The experimental part of the project involved the calculation of the thermal transmittivity across the walls made up of fired bricks, granite, and limestone, and the theoretical part involved the use of appropriate software to reconstruct air flow and heat distribution across floors, walls, and ceilings to proxy the original flow pattern yielding the comfortable PMV (predicted mean vote) and PET (physiological equivalent temperature) values within these premises. This exercise may well lead to further explorations on indoor comfort adaptations in tropical settings with the use of many edifying vernacular idioms in ancient settlements which prevail even in modern layouts. [ABSTRACT FROM AUTHOR]

Since indoor clothing insulation is a key element in thermal comfort models, the aim of the present study is proposing an approach for predicting it, which could assist the occupants of a building in terms of recommendations regarding their ensemble. For that, a systematic analysis of input variables is exposed, and 13 regression and 12 classification machine learning algorithms were developed and compared. The results are based on data from 3352 questionnaires and 21 input variables from a field study in mixed-mode office buildings in Spain. Outdoor temperature at 6 a.m., indoor air temperature, indoor relative humidity, comfort temperature and gender were the most relevant features for predicting clothing insulation. When comparing machine learning algorithms, decision tree-based algorithms with Boosting techniques achieved the best performance. The proposed model provides an efficient method for forecasting the clothing insulation level and its application would entail optimising thermal comfort and energy efficiency. [ABSTRACT FROM AUTHOR]

It has been found in recent years that using setpoint temperatures based on adaptive thermal comfort models is a successful method of energy conservation. Recent studies using adaptive setpoint temperatures incorporate international models from ASHRAE Standard 55 and EN16798-1. This study, however, has instead considered a regional Brazilian adaptive comfort model. This study investigates the energy demand arising from the use of a local Brazilian comfort model in order to assess the energy implications from the use of the worldwide ASHRAE Standard 55 adaptive model and various fixed setpoint temperatures. All of Brazil's climate zones, full air-conditioning, mixed-mode building operating modes, present-day climate change scenarios, and future scenarios—specifically Representative Concentration Pathways (RCP) 2.6, 4.5, and 8.5 for the years 2050 and 2100—have all been taken into account in building energy simulations. The use of adaptive setpoint temperatures based on the Brazilian local model considering mixed-mode has been found to significantly reduce energy consumption when compared to static setpoint temperatures (average energy-saving values ranging from 52% to 58%) and the ASHRAE 55 adaptive model (average values ranging from 15% to 21%). Considering climate change and the mixed-mode Brazilian model, the overall energy demand for the three groups of climatic zones (annual average outdoor temperatures ≤ 21 °C, > 21 and ≤ 25 °C and > 25 °C) ranged between 2% decrease and 5% increase, 4% and 27% increase, and 13% and 45% increase, respectively. It is concluded as a consequence that setting setpoint temperatures based on the Brazilian local adaptive comfort model is a very efficient energy-saving method. [ABSTRACT FROM AUTHOR]

Thermal comfort study was carried out in the hostels of National Institute of Technology Calicut, Kerala, which is located in a warm humid climatic zone of India. Measurements of ambient temperature, globe temperature, relative humidity, air velocity and illuminance were carried out in eight hostels, and in parallel a paper-based survey was conducted among students to know about their Thermal Preference Vote (TPV) and Thermal Sensation Vote (TSV) based on an ASHRAE seven-point scale. Predicted Mean Vote (PMV) and Predicted Percentage Dissatisfied (PPD) have been evaluated based on Fanger's theory of thermal comfort by utilizing the field measurements. Preferred operative temperature and neutral effective temperature were obtained based on the Predicted Mean Vote (PMV). Similarly the preferred operative temperature and neutral effective temperature were identified, for both Thermal Sensation Vote (TSV) and Thermal Preference Vote (TPV). Thermal comfort conditions for 80% satisfaction were also determined in each case. Correlations between the Predicted Mean Vote (PMV) and the Thermal Sensation Vote (TSV) as well as between the Predicted Mean Vote (PMV) and the Thermal Preference Vote (TPV) were obtained. [ABSTRACT FROM AUTHOR]

Predicting the thermal sensations of building occupants is challenging, but useful for indoor environment conditioning. In this study, a data-driven thermal sensation prediction model was developed using three quality-controlled thermal comfort databases. Different machine-learning algorithms were compared in terms of prediction accuracy and rationality. The model was further improved by adding categorical inputs, and building submodels and general models for different contexts. A comprehensive data-driven thermal sensation prediction model was established. The results indicate that the multilayer perceptron (MLP) algorithm achieves higher prediction accuracy and more rational results than the other four algorithms in this specific case. Labeling AC and NV scenarios, climate zones, and cooling and heating seasons can improve model performance. Establishing submodels for specific scenarios can result in better thermal sensation vote (TSV) predictions than using general models with or without labels. With 11 submodels corresponding to 11 scenarios, and three general models without labels, the final TSV prediction model achieved higher prediction accuracy, with 64.7%–90.7% fewer prediction errors (reducing SSE by 3.2–4.9) than the predicted mean vote (PMV). Possible applications of the new model are discussed. The findings of this study can help in development of simple, accurate, and rational thermal sensation prediction tools. [ABSTRACT FROM AUTHOR]

The outdoor thermal environment is an important factor when measuring the livability of a city. Residents will avoid intense heat by reducing their outdoor activities, which decreases the vitality of a city and increases the energy consumed for air conditioning. Outdoor thermal comfort has a great impact on outdoor activities; therefore, we need to evaluate and design the urban outdoor thermal environments in cold regions to improve the outdoor thermal comfort level. In this study, we conducted a questionnaire survey to assess the outdoor thermal comfort and adaptive thermal comfort in four different urban forms in Xi'an during July 2019, and measuring meteorological parameters, such as the temperature, relative humidity, wind speed, and black bulb temperature. The results are showed as follows. (1) In the cold study area, urban residents generally perceived the outdoor climate as relatively hot during the summer. (2) The participants exhibited psychological and physical adaptations in terms of their thermal comfort. In particular, when the PET was 30 °C, the MTCV was about 1.25 points higher in the later summer period than the early summer period. (3) The neutral PET differs among regions, and it is affected by the climate zone and latitude. Comparisons of our results with thermal comfort studies in different regions such as Singapore and Umeå in north Sweden showed that the thermal comfort is correlated with the regional climate and latitude. The neutral PET is higher in tropical regions. Our findings support the theoretical understanding of adaptive thermal comfort in cold regions and they provide a reference for formulating policies related to adaptive thermal comfort. [ABSTRACT FROM AUTHOR]

This research has investigated physical variables affecting indoor thermal comfort and subjective responses of thermal comfort of students in a university in Korea in which the weather is oceanic temperate climate, and has been performed to contribute to the research fields of Sustainable Thermal Standard and Adaptive Thermal Comfort (ATC). This research is based on the ISO 7730-2005 standard and the ATC theories and 4 main variables of PMV such as dry bulb temperature (Ta), relative humidity (RH), black bulb temperature (Tg), and air velocity (Va) are measured once a week during two regular semesters. A clothing insulation, a thermal sensation vote (TSV), an acceptability of thermal environment, and a preference for cooling and heating are investigated at the same time using a questionnaire. This study was carried out for 26 weeks during the spring season, from March to June 2009, and the autumn season, from September to December 2009. The main achievements of this study are as follows. Monthly Mean Outdoor Temperature (MMOT) and Operative Temperature (OT) in the classroom during research periods are 7.4∼23.3°C and 17.5∼29.0°C, respectively. The acceptability ratio of thermal environment shows over 80% when the range of OT in the classroom is 17∼25°C, and the range can be applicable to operative index of heating and cooling of classroom. The mean TSV of respondents is almost 'neutral (0)' when the PMV in the classroom moves to 'neutral (0)' and 'slightly cool (−1)', and the TSV is almost '+1.5' when the PMV moves to 'slightly warm (+1)'. The acceptability ratio of thermal environment is slightly different from ASHRAE Standard 55-2004. So it is necessary to more investigate standard range of acceptability of thermal environment in oceanic temperate climate region using much more databases. [ABSTRACT FROM AUTHOR]