Pub Date : 2024-11-03DOI: 10.1016/j.buildenv.2024.112265
Hua Wang , Jian Bi , Mei Hua , Ke Yan , Afshin Afshari
Supervised learning methods demonstrated high classification accuracy for air handling unit (AHU) automated fault detection and diagnosis (FDD) scenarios with well-shaped training datasets. However, for imbalanced training datasets, i.e., much less real-world fault training data samples against an enormous amount of normal data samples, the supervised learning-based methods failed to produce satisfactory FDD results. To address the above-mentioned issue, this study proposes a semi-supervised conditional Wasserstein generative adversarial network with gradient penalty (CWGAN-GP) to generate high-quality synthetic fault training samples. The semi-supervised learning-based AHU AFDD framework is completed by identifying high-quality synthetic fault samples and inserting them into the training pool iteratively. With different numbers of real-world fault samples, comparative experiments are conducted on datasets collected by ASHRAE project RP-1312 in the summer and winter seasons. The experimental results show that the proposed AFDD method has obvious advantages over the traditional method with limited numbers of real-world fault samples. Moreover, the proposed CWGAN-GP-SSL framework achieves superior AFDD performance compared to the existing GAN-based AHU AFDD method.
有监督学习方法在空气处理机组（AHU）自动故障检测和诊断（FDD）场景中，在训练数据集形状良好的情况下，显示出较高的分类准确性。然而，对于不平衡的训练数据集，即现实世界中的故障训练数据样本少于大量正常数据样本，基于监督学习的方法无法产生令人满意的故障检测与诊断结果。针对上述问题，本研究提出了一种带梯度惩罚的半监督条件瓦瑟斯坦生成对抗网络（CWGAN-GP），用于生成高质量的合成故障训练样本。基于半监督学习的 AHU AFDD 框架是通过识别高质量的合成故障样本并将其反复插入训练池来完成的。利用不同数量的真实故障样本，在 ASHRAE 项目 RP-1312 收集的夏季和冬季数据集上进行了对比实验。实验结果表明，在真实世界故障样本数量有限的情况下，所提出的 AFDD 方法与传统方法相比具有明显优势。此外，与现有的基于 GAN 的 AHU AFDD 方法相比，提出的 CWGAN-GP-SSL 框架实现了更优越的 AFDD 性能。
{"title":"Semi-supervised CWGAN-GP modeling for AHU AFDD with high-quality synthetic data filtering mechanism","authors":"Hua Wang , Jian Bi , Mei Hua , Ke Yan , Afshin Afshari","doi":"10.1016/j.buildenv.2024.112265","DOIUrl":"10.1016/j.buildenv.2024.112265","url":null,"abstract":"<div><div>Supervised learning methods demonstrated high classification accuracy for air handling unit (AHU) automated fault detection and diagnosis (FDD) scenarios with well-shaped training datasets. However, for imbalanced training datasets, i.e., much less real-world fault training data samples against an enormous amount of normal data samples, the supervised learning-based methods failed to produce satisfactory FDD results. To address the above-mentioned issue, this study proposes a semi-supervised conditional Wasserstein generative adversarial network with gradient penalty (CWGAN-GP) to generate high-quality synthetic fault training samples. The semi-supervised learning-based AHU AFDD framework is completed by identifying high-quality synthetic fault samples and inserting them into the training pool iteratively. With different numbers of real-world fault samples, comparative experiments are conducted on datasets collected by ASHRAE project RP-1312 in the summer and winter seasons. The experimental results show that the proposed AFDD method has obvious advantages over the traditional method with limited numbers of real-world fault samples. Moreover, the proposed CWGAN-GP-SSL framework achieves superior AFDD performance compared to the existing GAN-based AHU AFDD method.</div></div>","PeriodicalId":9273,"journal":{"name":"Building and Environment","volume":"267 ","pages":"Article 112265"},"PeriodicalIF":7.1,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-02DOI: 10.1016/j.buildenv.2024.112264
Florin Bode , Titus Joldos , Gabriel Mihai Sirbu , Paul Danca , Ilinca Nastase , Costin Coșoiu
In recent years, the accurate numerical simulation of airflow in vehicle cabins has become increasingly important for optimizing thermal comfort and energy efficiency. This study investigates the impact of realistic boundary conditions on Computational Fluid Dynamics (CFD) simulations for vehicle ventilation systems. The research integrates detailed HVAC duct data to provide a more accurate representation of airflow characteristics, diverging from conventional approaches that often assume uniform inlet conditions. Using a 3D CFD model, airflow patterns were simulated under two scenarios, comparing a case with simplified boundary conditions to one incorporating detailed duct geometries and realistic conditions. The numerical model was validated using experimental data, including Laser Doppler Velocimetry (LDV) and Particle Image Velocimetry (PIV) measurements. The findings reveal that using realistic boundary conditions significantly enhances the accuracy of airflow predictions, particularly regarding velocity distribution and thermal comfort. This work highlights the critical role of detailed boundary condition specification in improving the reliability of CFD simulations for vehicle ventilation and other personalized ventilation applications.
{"title":"Impact of realistic boundary conditions on CFD simulations: A case study of vehicle ventilation","authors":"Florin Bode , Titus Joldos , Gabriel Mihai Sirbu , Paul Danca , Ilinca Nastase , Costin Coșoiu","doi":"10.1016/j.buildenv.2024.112264","DOIUrl":"10.1016/j.buildenv.2024.112264","url":null,"abstract":"<div><div>In recent years, the accurate numerical simulation of airflow in vehicle cabins has become increasingly important for optimizing thermal comfort and energy efficiency. This study investigates the impact of realistic boundary conditions on Computational Fluid Dynamics (CFD) simulations for vehicle ventilation systems. The research integrates detailed HVAC duct data to provide a more accurate representation of airflow characteristics, diverging from conventional approaches that often assume uniform inlet conditions. Using a 3D CFD model, airflow patterns were simulated under two scenarios, comparing a case with simplified boundary conditions to one incorporating detailed duct geometries and realistic conditions. The numerical model was validated using experimental data, including Laser Doppler Velocimetry (LDV) and Particle Image Velocimetry (PIV) measurements. The findings reveal that using realistic boundary conditions significantly enhances the accuracy of airflow predictions, particularly regarding velocity distribution and thermal comfort. This work highlights the critical role of detailed boundary condition specification in improving the reliability of CFD simulations for vehicle ventilation and other personalized ventilation applications.</div></div>","PeriodicalId":9273,"journal":{"name":"Building and Environment","volume":"267 ","pages":"Article 112264"},"PeriodicalIF":7.1,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-02DOI: 10.1016/j.buildenv.2024.112262
Jenni Radun , Jukka Keränen , Reijo Alakoivu , Isabel S. Schiller , Sabine J. Schlittmeier , Valtteri Hongisto
Working during task-irrelevant speech influences workers. Adequate room acoustic design can reduce the negative effects in open-plan offices, but harmonized target values do not exist. Our purpose was to examine the effects of room acoustic design levels on a working person during the exposure to task-irrelevant speech. The Finnish room acoustic regulation was chosen as a reference, as it is one of the strictest worldwide. Three room acoustic conditions were examined: regulation violated (Reg-) (Speech Transmission Index, STI=0.71), regulation fulfilled (Reg0) (STI=0.37), and regulation surpassed (Reg+) (STI=0.16). To examine the generalizability of the results, a similar experiment was performed in two countries (two languages and laboratories): Finland and Germany (FinGer study, N = 98). Experience was measured with questionnaires, performance with visual and auditory serial recall tasks, and physiological stress with heart rate variability. Results did not depend on the country, suggesting that our findings could be similar also in other countries. Speech annoyance and perceived concentration difficulty differed in each condition. With other experience measures, only Reg+ improved experience compared to the two other conditions. Visual serial recall performance was more accurate and faster in Reg+ than in Reg-. Accuracy was also improved in Reg0 compared to Reg-. The physiological stress levels did not depend on the condition. Our study shows that Reg0 was better than Reg- with respect to experience and performance but experience was further improved from Reg0 to Reg+. Therefore, it is beneficial to design room acoustics better than the Finnish regulation to maximize work performance and experience.
{"title":"How speech in acoustically different offices influences a working person? – Experiments in two countries","authors":"Jenni Radun , Jukka Keränen , Reijo Alakoivu , Isabel S. Schiller , Sabine J. Schlittmeier , Valtteri Hongisto","doi":"10.1016/j.buildenv.2024.112262","DOIUrl":"10.1016/j.buildenv.2024.112262","url":null,"abstract":"<div><div>Working during task-irrelevant speech influences workers. Adequate room acoustic design can reduce the negative effects in open-plan offices, but harmonized target values do not exist. Our purpose was to examine the effects of room acoustic design levels on a working person during the exposure to task-irrelevant speech. The Finnish room acoustic regulation was chosen as a reference, as it is one of the strictest worldwide. Three room acoustic conditions were examined: regulation violated (Reg-) (Speech Transmission Index, STI=0.71), regulation fulfilled (Reg0) (STI=0.37), and regulation surpassed (Reg+) (STI=0.16). To examine the generalizability of the results, a similar experiment was performed in two countries (two languages and laboratories): Finland and Germany (FinGer study, <em>N</em> = 98). Experience was measured with questionnaires, performance with visual and auditory serial recall tasks, and physiological stress with heart rate variability. Results did not depend on the country, suggesting that our findings could be similar also in other countries. Speech annoyance and perceived concentration difficulty differed in each condition. With other experience measures, only Reg+ improved experience compared to the two other conditions. Visual serial recall performance was more accurate and faster in Reg+ than in Reg-. Accuracy was also improved in Reg0 compared to Reg-. The physiological stress levels did not depend on the condition. Our study shows that Reg0 was better than Reg- with respect to experience and performance but experience was further improved from Reg0 to Reg+. Therefore, it is beneficial to design room acoustics better than the Finnish regulation to maximize work performance and experience.</div></div>","PeriodicalId":9273,"journal":{"name":"Building and Environment","volume":"267 ","pages":"Article 112262"},"PeriodicalIF":7.1,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-02DOI: 10.1016/j.buildenv.2024.112263
Peijun Wen , Liya He , Jie Li , Xiaodong Hu
Several major international sports events in the next five years require new sports venues, with lighting environments being a crucial factor. Typically, the lighting systems in sports venues are primarily for illumination. However, since light has been indicated to affect human psychology and physiology, we investigated whether the light environments in sports buildings impact athletic performance. Additionally, swimming is the indoor sport with the most gold medals in the Olympics. Therefore, we conducted a within-subject, randomized crossover study in an aquatics center with fourteen elite swimmers, including the Olympic champions and Asian champions (6 female and 8 male; 19.3 ± 3.4 years of age). During the experiment, the elite swimmers were exposed to either a common correlated color temperature (CCT) light environment (controlled condition: 5780 K) or an experimental light environment (8512 K) in the aquatics center, with both having the same illuminance (1020 lx). The neurobehavioral and swimming test results showed that the Olympic champions and other elite swimmers had significantly faster responses, fewer lapses, greater arousal, less visual fatigue, quicker reactions at start, and higher swimming speeds in the experimental condition compared to the controlled condition (p < 0.05). Our findings suggest that the light environment in the aquatics center affects swimmers' non-visual performance and enhancing the CCT of the light environment could improve swimmers' performance. We propose the concepts of Sports Lighting Beyond Illumination and Sports Human-Centric Lighting to enhance athletes’ health and performance, and to improve the sports environment for a better experience for all participants.
{"title":"Optimizing light environments in aquatics center to enhance the performance of Olympic champions and other elite swimmers: An experimental study","authors":"Peijun Wen , Liya He , Jie Li , Xiaodong Hu","doi":"10.1016/j.buildenv.2024.112263","DOIUrl":"10.1016/j.buildenv.2024.112263","url":null,"abstract":"<div><div>Several major international sports events in the next five years require new sports venues, with lighting environments being a crucial factor. Typically, the lighting systems in sports venues are primarily for illumination. However, since light has been indicated to affect human psychology and physiology, we investigated whether the light environments in sports buildings impact athletic performance. Additionally, swimming is the indoor sport with the most gold medals in the Olympics. Therefore, we conducted a within-subject, randomized crossover study in an aquatics center with fourteen elite swimmers, including the Olympic champions and Asian champions (6 female and 8 male; 19.3 ± 3.4 years of age). During the experiment, the elite swimmers were exposed to either a common correlated color temperature (CCT) light environment (controlled condition: 5780 K) or an experimental light environment (8512 K) in the aquatics center, with both having the same illuminance (1020 lx). The neurobehavioral and swimming test results showed that the Olympic champions and other elite swimmers had significantly faster responses, fewer lapses, greater arousal, less visual fatigue, quicker reactions at start, and higher swimming speeds in the experimental condition compared to the controlled condition (p < 0.05). Our findings suggest that the light environment in the aquatics center affects swimmers' non-visual performance and enhancing the CCT of the light environment could improve swimmers' performance. We propose the concepts of Sports Lighting Beyond Illumination and Sports Human-Centric Lighting to enhance athletes’ health and performance, and to improve the sports environment for a better experience for all participants.</div></div>","PeriodicalId":9273,"journal":{"name":"Building and Environment","volume":"267 ","pages":"Article 112263"},"PeriodicalIF":7.1,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-02DOI: 10.1016/j.buildenv.2024.112258
Wei Wang , Haoran Di , Rui Tang , Wenzhe Wei , Yuying Sun , Chuanmin Dai
During the space heating in winter, the air source heat pump (ASHP) often encounters frosting problem. In former studies, it was found that the frosting performance of ASHP and indoor thermal environment vary significantly when the supply water temperature changes. However, the influence mechanism of supply water temperature is still unknown. To solve this problem, the frosting performance variations of ASHP and its effect on indoor thermal environment variations at the supply water temperature of 41–50 ℃ were investigated in the psychrometric chamber and artificial environmental chamber, respectively. Results showed that increasing supply water temperature can effectively suppress the frosting speed and reduce the impact of frosting-defrosting on indoor thermal environment. When the supply water temperature raises from 30 ℃ to 50 ℃, the frosting duration prolongs from 50 min to 101 min. Meanwhile, the indoor temperature drop caused by frosting-defrosting decreased by about 45 % when supply water temperature rises from 41 ℃ to 50 ℃. Besides, with the increase of supply water temperature, the impact of frosting on the heating performance of the ASHP decreases. When it rises from 30 ℃ to 50 ℃, the attenuation degree of the average coefficient of performance during frosting-defrosting cycle drops from 9.85 % to 7.25 %, compared to those at non-frosting condition. However, although the frosting performance of ASHP and its effect on indoor thermal environment both get better with the increase of supply water temperature, the overall heating performance of the ASHP still declines.
{"title":"Effect of supply water temperature on frosting performance of air source heat pump and indoor thermal environment in space heating","authors":"Wei Wang , Haoran Di , Rui Tang , Wenzhe Wei , Yuying Sun , Chuanmin Dai","doi":"10.1016/j.buildenv.2024.112258","DOIUrl":"10.1016/j.buildenv.2024.112258","url":null,"abstract":"<div><div>During the space heating in winter, the air source heat pump (ASHP) often encounters frosting problem. In former studies, it was found that the frosting performance of ASHP and indoor thermal environment vary significantly when the supply water temperature changes. However, the influence mechanism of supply water temperature is still unknown. To solve this problem, the frosting performance variations of ASHP and its effect on indoor thermal environment variations at the supply water temperature of 41–50 ℃ were investigated in the psychrometric chamber and artificial environmental chamber, respectively. Results showed that increasing supply water temperature can effectively suppress the frosting speed and reduce the impact of frosting-defrosting on indoor thermal environment. When the supply water temperature raises from 30 ℃ to 50 ℃, the frosting duration prolongs from 50 min to 101 min. Meanwhile, the indoor temperature drop caused by frosting-defrosting decreased by about 45 % when supply water temperature rises from 41 ℃ to 50 ℃. Besides, with the increase of supply water temperature, the impact of frosting on the heating performance of the ASHP decreases. When it rises from 30 ℃ to 50 ℃, the attenuation degree of the average coefficient of performance during frosting-defrosting cycle drops from 9.85 % to 7.25 %, compared to those at non-frosting condition. However, although the frosting performance of ASHP and its effect on indoor thermal environment both get better with the increase of supply water temperature, the overall heating performance of the ASHP still declines.</div></div>","PeriodicalId":9273,"journal":{"name":"Building and Environment","volume":"267 ","pages":"Article 112258"},"PeriodicalIF":7.1,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-01DOI: 10.1016/j.buildenv.2024.112109
Fernando Gomes, Mariana Giannotti
The Sky View Factor (SVF) has been used as an index of dimensionality and complexity reduction in several areas of knowledge to model and qualify the urban environment and the landscape. This article proposes a new method to calculate the Digital Continuous Model of SVF (SVF-CDM) from LiDAR 3D ALS surveys for large cities. The method is described from the perspective of single-point computing and then adapted to a more efficient heuristic computational process called here SVFPy . The SVF-CDM processing was carried out for the entire length of the São Paulo and New York cities, with a spatial resolution of 50 cm and 1.25 ft (38.1 cm), respectively. Method validation was based on comparing a sample of random points, and the median errors were -0.53 (São Paulo) and 1.37 (New York) percentage points. The results indicate that the SVF-CDM has advantages over other digital models and features for urban morphology analysis. Whether visually or through its dimensional and statistical expression, the presented model manages to express the nuances and morphological aspects of the studied areas. In this way, we conclude that we are facing a significant advance for the models of urban studies, not only because it considers the perspective of the pedestrian but also because it is a powerful resource for studies and disciplines related to the urban form without disregarding all its complexity.
{"title":"SVF-CDM: Sky View Factor, a Continuous Digital Model for large cities using SVFPy","authors":"Fernando Gomes, Mariana Giannotti","doi":"10.1016/j.buildenv.2024.112109","DOIUrl":"10.1016/j.buildenv.2024.112109","url":null,"abstract":"<div><div>The Sky View Factor (SVF) has been used as an index of dimensionality and complexity reduction in several areas of knowledge to model and qualify the urban environment and the landscape. This article proposes a new method to calculate the Digital Continuous Model of SVF (SVF-CDM) from LiDAR 3D ALS surveys for large cities. The method is described from the perspective of single-point computing and then adapted to a more efficient heuristic computational process called here SVFPy . The SVF-CDM processing was carried out for the entire length of the São Paulo and New York cities, with a spatial resolution of 50 cm and 1.25 ft (38.1 cm), respectively. Method validation was based on comparing a sample of random points, and the median errors were -0.53 (São Paulo) and 1.37 (New York) percentage points. The results indicate that the SVF-CDM has advantages over other digital models and features for urban morphology analysis. Whether visually or through its dimensional and statistical expression, the presented model manages to express the nuances and morphological aspects of the studied areas. In this way, we conclude that we are facing a significant advance for the models of urban studies, not only because it considers the perspective of the pedestrian but also because it is a powerful resource for studies and disciplines related to the urban form without disregarding all its complexity.</div></div>","PeriodicalId":9273,"journal":{"name":"Building and Environment","volume":"267 ","pages":"Article 112109"},"PeriodicalIF":7.1,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-01DOI: 10.1016/j.buildenv.2024.112253
Gang Liu , Junxi Gao , Zhen Han , Ye Yuan
Efforts to reduce energy demand in the building sector have prompted a focus on the operational control of HVAC systems. Despite extensive research on HVAC control based on temperature prediction models, existing approaches often rely on node-based or average temperature predictions, which lack the detailed temperature distribution data necessary for accurate control, especially in transient situations with both spatial and temporal variations. This study introduces a precise HVAC control method based on a fast temperature field prediction model. By combining the single-step prediction response coefficient (SPRC) method with Convolutional Neural Network (CNN) architecture, sub-temperature field prediction models for multiple independent heat sources were constructed and integrated to achieve fast temperature field predictions. Subsequently, utilizing the predicted temperature field, air conditioning operation parameters were optimized and controlled to minimize energy consumption. Application of the proposed method in real building scenarios demonstrated the temperature field predictions closely aligned with computational fluid dynamics (CFD) simulations, achieving a mean absolute error (MAE) of 0.27 °C and a root mean square error (RMSE) of 0.24 °C. Furthermore, this model achieved a notable 57.8 % improvement in prediction accuracy compared to models relying solely on single-step prediction responses. Additionally, the model predictive control based on the hybrid model's temperature field predictions significantly reduced the runtime of the HVAC system by 18.18 % while maintaining temperatures within the comfort range throughout the operation period. The method presents a promising avenue for optimizing HVAC operations and minimizing energy consumption in building environments, thereby contributing to sustainable building management practices.
{"title":"Hybrid model-based predictive HVAC control through fast prediction of transient indoor temperature fields","authors":"Gang Liu , Junxi Gao , Zhen Han , Ye Yuan","doi":"10.1016/j.buildenv.2024.112253","DOIUrl":"10.1016/j.buildenv.2024.112253","url":null,"abstract":"<div><div>Efforts to reduce energy demand in the building sector have prompted a focus on the operational control of HVAC systems. Despite extensive research on HVAC control based on temperature prediction models, existing approaches often rely on node-based or average temperature predictions, which lack the detailed temperature distribution data necessary for accurate control, especially in transient situations with both spatial and temporal variations. This study introduces a precise HVAC control method based on a fast temperature field prediction model. By combining the single-step prediction response coefficient (SPRC) method with Convolutional Neural Network (CNN) architecture, sub-temperature field prediction models for multiple independent heat sources were constructed and integrated to achieve fast temperature field predictions. Subsequently, utilizing the predicted temperature field, air conditioning operation parameters were optimized and controlled to minimize energy consumption. Application of the proposed method in real building scenarios demonstrated the temperature field predictions closely aligned with computational fluid dynamics (CFD) simulations, achieving a mean absolute error (MAE) of 0.27 °C and a root mean square error (RMSE) of 0.24 °C. Furthermore, this model achieved a notable 57.8 % improvement in prediction accuracy compared to models relying solely on single-step prediction responses. Additionally, the model predictive control based on the hybrid model's temperature field predictions significantly reduced the runtime of the HVAC system by 18.18 % while maintaining temperatures within the comfort range throughout the operation period. The method presents a promising avenue for optimizing HVAC operations and minimizing energy consumption in building environments, thereby contributing to sustainable building management practices.</div></div>","PeriodicalId":9273,"journal":{"name":"Building and Environment","volume":"267 ","pages":"Article 112253"},"PeriodicalIF":7.1,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-01DOI: 10.1016/j.buildenv.2024.112257
Jingqi Chen , Na Dong , Zhen Liu , Yimin Chen , Ming Luo , Huabing Huang
Urbanization has led to significant alterations in surface properties, contributing to surging urban heatwave events. The detrimental impact of urban heatwaves on public health highlights the urgency for proactive evaluations of diverse heat mitigation strategies. This study assesses the impacts of cool roof (CR), green roof (GR) and rooftop photovoltaic panel (PV) strategies on urban air temperatures within Guangzhou and Foshan agglomeration, utilizing the Weather Research and Forecasting with Urban Canopy Model (WRF-UCM). A comparative analysis of heat exchanges is conducted between two types of urban morphology datasets: local climate zone maps with categorized urban canopy parameters (LCZ-UCPs) and gridded urban canopy parameters from real building databases (gridded-UCPs). The results indicate that the discrepancies in the average temperature between LCZ-UCP and gridded-UCP is almost negligible, whereas increase to 0.39 °C and 0.54 °C for the daily maximum and minimum temperature, respectively. CR provides the most substantial cooling at an average of 0.44 °C, followed by GR and PV. Scenarios with the two types of morphology datasets reveal varying mitigation efficiencies. CRs with LCZ-UCPs show more pronounced temperature reductions, whereas GRs and PVs with gridded-UCPs in central urban regions demonstrate stronger cooling effects. CRs and PVs cool temperature by decreasing sensible heat flux, whereas GR is largely influenced by enhanced evapotranspiration especially with grass plantation. These findings elucidate the differing efficiencies of the three mitigation strategies and highlight the representation discrepancies in climatic simulations brought by the two urban canopy datasets. This emphasizes the importance of accurate urban morphological datasets in evaluating mitigation strategies in WRF-UCM, thus providing practicable insights for urban planning and climate policy-making.
{"title":"Local temperature impact of urban heat mitigation strategy based on WRF integrating urban canopy parameters and local climate zones","authors":"Jingqi Chen , Na Dong , Zhen Liu , Yimin Chen , Ming Luo , Huabing Huang","doi":"10.1016/j.buildenv.2024.112257","DOIUrl":"10.1016/j.buildenv.2024.112257","url":null,"abstract":"<div><div>Urbanization has led to significant alterations in surface properties, contributing to surging urban heatwave events. The detrimental impact of urban heatwaves on public health highlights the urgency for proactive evaluations of diverse heat mitigation strategies. This study assesses the impacts of cool roof (CR), green roof (GR) and rooftop photovoltaic panel (PV) strategies on urban air temperatures within Guangzhou and Foshan agglomeration, utilizing the Weather Research and Forecasting with Urban Canopy Model (WRF-UCM). A comparative analysis of heat exchanges is conducted between two types of urban morphology datasets: local climate zone maps with categorized urban canopy parameters (LCZ-UCPs) and gridded urban canopy parameters from real building databases (gridded-UCPs). The results indicate that the discrepancies in the average temperature between LCZ-UCP and gridded-UCP is almost negligible, whereas increase to 0.39 °C and 0.54 °C for the daily maximum and minimum temperature, respectively. CR provides the most substantial cooling at an average of 0.44 °C, followed by GR and PV. Scenarios with the two types of morphology datasets reveal varying mitigation efficiencies. CRs with LCZ-UCPs show more pronounced temperature reductions, whereas GRs and PVs with gridded-UCPs in central urban regions demonstrate stronger cooling effects. CRs and PVs cool temperature by decreasing sensible heat flux, whereas GR is largely influenced by enhanced evapotranspiration especially with grass plantation. These findings elucidate the differing efficiencies of the three mitigation strategies and highlight the representation discrepancies in climatic simulations brought by the two urban canopy datasets. This emphasizes the importance of accurate urban morphological datasets in evaluating mitigation strategies in WRF-UCM, thus providing practicable insights for urban planning and climate policy-making.</div></div>","PeriodicalId":9273,"journal":{"name":"Building and Environment","volume":"267 ","pages":"Article 112257"},"PeriodicalIF":7.1,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-31DOI: 10.1016/j.buildenv.2024.112238
S. Manavvi , Dragan Milosevic
Urban environments in humid subtropical climates, like Roorkee, India, often experience high summer temperatures and uncomfortable outdoor thermal conditions. However, the impact of green-blue landscape configurations on cooling intensity (ΔTa) and outdoor thermal comfort (OTC) is insufficiently understood. This study, conducted in Roorkee during summer 2022, assessed the effect of green-blue landscape configurations on OTC using Physiological Equivalent Temperature (PET) and mean radiant temperature (Tmrt). PET values ranged from slight to extreme heat stress, with statistically significant differences in cooling intensity across varied landscape configurations. Tree shaded canal front locations registered lower Ta (1.6 °C) and Tmrt (9.3 °C). Similarly, shaded canal front locations registered 4.7 °C lower PET than sun-exposed locations
Different tree species showed significant variation in ΔTa, with the highest cooling effect (maximum average ΔTa of 3 °C) occurring during the morning hours. Notably Morus alba and Mangifera indica yielded the highest cooling effect, outperforming artificial and mixed shade. Eucalyptus alba, on the other hand, registered adverse comfort conditions. Denser tree canopies and attributes - canopy diameter, leaf area index, and height were strongly correlated to improved cooling performance.
Additionally, increasing pervious surfaces and tree cover within 100 m of intervention areas enhanced cooling, with significant effects noted within a 25–50 m radius. This study highlights the role of green-blue infrastructure, particularly the combination of low sky-view factor (SVF), dense canopy trees, and proximity to water, in reducing heat stress. These findings offer crucial insights for climate-responsive open space design, particularly in Indian cities facing rampant urbanization and global warming.
{"title":"Chasing cool: Unveiling the influence of green-blue features on outdoor thermal environment in Roorkee (India)","authors":"S. Manavvi , Dragan Milosevic","doi":"10.1016/j.buildenv.2024.112238","DOIUrl":"10.1016/j.buildenv.2024.112238","url":null,"abstract":"<div><div>Urban environments in humid subtropical climates, like Roorkee, India, often experience high summer temperatures and uncomfortable outdoor thermal conditions. However, the impact of green-blue landscape configurations on cooling intensity (ΔT<sub>a</sub>) and outdoor thermal comfort (OTC) is insufficiently understood. This study, conducted in Roorkee during summer 2022, assessed the effect of green-blue landscape configurations on OTC using Physiological Equivalent Temperature (PET) and mean radiant temperature (T<sub>mrt</sub>). PET values ranged from slight to extreme heat stress, with statistically significant differences in cooling intensity across varied landscape configurations. Tree shaded canal front locations registered lower T<sub>a</sub> (1.6 °C) and T<sub>mrt</sub> (9.3 °C). Similarly, shaded canal front locations registered 4.7 °C lower PET than sun-exposed locations</div><div>Different tree species showed significant variation in ΔT<sub>a</sub>, with the highest cooling effect (maximum average <em>ΔT<sub>a</sub></em> of 3 °C) occurring during the morning hours. Notably <em>Morus alba</em> and <em>Mangifera indica</em> yielded the highest cooling effect, outperforming artificial and mixed shade. <em>Eucalyptus alba</em>, on the other hand, registered adverse comfort conditions. Denser tree canopies and attributes - canopy diameter, leaf area index, and height were strongly correlated to improved cooling performance.</div><div>Additionally, increasing pervious surfaces and tree cover within 100 m of intervention areas enhanced cooling, with significant effects noted within a 25–50 m radius. This study highlights the role of green-blue infrastructure, particularly the combination of low sky-view factor (SVF), dense canopy trees, and proximity to water, in reducing heat stress. These findings offer crucial insights for climate-responsive open space design, particularly in Indian cities facing rampant urbanization and global warming.</div></div>","PeriodicalId":9273,"journal":{"name":"Building and Environment","volume":"267 ","pages":"Article 112238"},"PeriodicalIF":7.1,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-31DOI: 10.1016/j.buildenv.2024.112256
Pan Cheng , Wei Jia , Li Liu , Hui-Ling Yen , Yuguo Li
Minimising airborne infection with respiratory viruses, such as SARS-CoV-2, requires knowledge of the infectious quanta generation rate for determining the minimum dilution requirement. The two existing methods for estimating quanta generation rates are the viral load method and outbreak method. The former method is challenged by significant uncertainty in input data, including dose-response parameters and infectious viral loads. The latter method, based on the Wells–Riley equation, is challenged by significant individual heterogeneity in quanta generation rates and lack of outbreak data. In this study, the two methods are integrated for studying the quanta generation profile of all individuals infected with an ancestral SARS-CoV-2 strain, based on four reported outbreaks of infection. The airborne transmission droplet size ranges in the four outbreaks, which were determined in previous studies, are used to estimate the hourly volume of expired droplets for the viral load method. Various viral load datasets and conversion factors from RNA copies to infectious quanta are tested. Two criteria are used to identify the probable quanta generation profile, i.e. 70% of infected individuals do not infect others, and the estimated quanta generation rates estimated using the outbreak method should be within the top 80%–99% of infected individuals. The predicted quanta generation profile of all individuals infected with SARS-CoV-2 follows a log-normal distribution, whereas that of the top 30% of infected individuals approximately follows a power-law distribution.
Practical significance: A major obstacle in defining dilution requirements for minimising airborne infection is the lack of infectious quanta generation rates for the general population. Our approach integrates two existing quanta estimation methods and paves the way to obtaining reliable quanta generation rate profiles at the population level.
{"title":"A power-law distribution of infectious quanta for the top 30% of SARS-CoV-2-infected individuals","authors":"Pan Cheng , Wei Jia , Li Liu , Hui-Ling Yen , Yuguo Li","doi":"10.1016/j.buildenv.2024.112256","DOIUrl":"10.1016/j.buildenv.2024.112256","url":null,"abstract":"<div><div>Minimising airborne infection with respiratory viruses, such as SARS-CoV-2, requires knowledge of the infectious quanta generation rate for determining the minimum dilution requirement. The two existing methods for estimating quanta generation rates are the viral load method and outbreak method. The former method is challenged by significant uncertainty in input data, including dose-response parameters and infectious viral loads. The latter method, based on the Wells–Riley equation, is challenged by significant individual heterogeneity in quanta generation rates and lack of outbreak data. In this study, the two methods are integrated for studying the quanta generation profile of all individuals infected with an ancestral SARS-CoV-2 strain, based on four reported outbreaks of infection. The airborne transmission droplet size ranges in the four outbreaks, which were determined in previous studies, are used to estimate the hourly volume of expired droplets for the viral load method. Various viral load datasets and conversion factors from RNA copies to infectious quanta are tested. Two criteria are used to identify the probable quanta generation profile, i.e. 70% of infected individuals do not infect others, and the estimated quanta generation rates estimated using the outbreak method should be within the top 80%–99% of infected individuals. The predicted quanta generation profile of all individuals infected with SARS-CoV-2 follows a log-normal distribution, whereas that of the top 30% of infected individuals approximately follows a power-law distribution.</div><div><strong>Practical significance:</strong> A major obstacle in defining dilution requirements for minimising airborne infection is the lack of infectious quanta generation rates for the general population. Our approach integrates two existing quanta estimation methods and paves the way to obtaining reliable quanta generation rate profiles at the population level.</div></div>","PeriodicalId":9273,"journal":{"name":"Building and Environment","volume":"267 ","pages":"Article 112256"},"PeriodicalIF":7.1,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号