Energy and Buildings最新文献

{"title":"A physics-informed autoencoder method with automatic weighted loss for chiller water system sensor fault detection","authors":"Chengliang Xu ,&nbsp;Chen Xu ,&nbsp;Yongjun Sun ,&nbsp;Shiao Chen ,&nbsp;Guannan Li","doi":"10.1016/j.enbuild.2025.116448","DOIUrl":"10.1016/j.enbuild.2025.116448","url":null,"abstract":"<div><div>Machine learning (ML) methods have been increasingly applied in sensor fault detection and diagnosis (FDD) of heating, ventilation and air-conditioning (HVAC) systems. However, most current ML based sensor FDD methods overly focus on extracting features from sensor data and using combined ML methods to improve detection efficiency, which often neglects the inner physical correlation information among HVAC sensors. To address this issue, this study proposes a physics-informed autoencoder (PIAE) method that fully utilizes the physical correlation information between sensors. PIAE can efficiently extract complex relationships among input variables by integrating the physical correlation information into the autoencoder structure through the combination of the decoder’s output and the loss function. This integration approach effectively avoids results from a single autoencoder output that may deviate from the physical correlation information, thus improving the accuracy and reliability of sensor fault detection. The ASHRAE RP-1043 data was used for validation. The results show that, compared with a single autoencoder, PIAE significantly improves the fault detection accuracy. The average Youden’s index increases from 0.28 to 0.69 and the detection accuracy of the temperature sensor increases from ±3.25 °F to ±1.75 °F. Furthermore, the analysis indicates that an increase in training data amount can effectively enhance the accuracy of the proposed model. The proposed method contributes to providing a concise and reliable approach for sensor fault detection in HVAC systems.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"348 ","pages":"Article 116448"},"PeriodicalIF":7.1,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145061643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hybrid SMOTE and Trans-CWGAN for data imbalance in real operational AHU AFDD: A case study of an auditorium building","authors":"Seunghyeon Wang","doi":"10.1016/j.enbuild.2025.116447","DOIUrl":"10.1016/j.enbuild.2025.116447","url":null,"abstract":"<div><div>Class imbalance remains a significant challenge in Automated Fault Detection and Diagnosis (AFDD) for Air Handling Units (AHUs), as normal operating conditions significantly outnumber rare fault events. Prior studies mainly relied on simulated or laboratory-generated datasets, limiting their applicability to real-world scenarios due to insufficient operational complexity. This study introduces a novel hybrid data augmentation method combining the Synthetic Minority Over-sampling Technique (SMOTE) with Transfer Conditional Wasserstein Generative Adversarial Network (Trans-CWGAN), applied to real operational data collected over one year from an auditorium building equipped with 13 AHUs. Through hyperparameter optimization, a total of 1212 distinct datasets were generated across augmentation strategies. Among these strategies, the SMOTE-based Trans-CWGAN approach consistently delivered superior results. Specifically, TabNet achieved the highest performance, with a mean F1 score of 98.68 % and accuracy of 98.98 %, followed by RNN-LSTM (F1: 96.56 %, accuracy: 95.84 %). Even the DT model significantly improved from its initial baseline F1 score of 73.53 %. These findings underscore the effectiveness of integrating SMOTE and Trans-CWGAN to mitigate class imbalance, highlighting its strong potential for practical deployment in real-world HVAC monitoring systems.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"348 ","pages":"Article 116447"},"PeriodicalIF":7.1,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145094133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Strategies for implementing sunshades and street trees for pedestrian heat avoidance in street canyons","authors":"Hideki Takebayashi,&nbsp;Ami Takasaki","doi":"10.1016/j.enbuild.2025.116414","DOIUrl":"10.1016/j.enbuild.2025.116414","url":null,"abstract":"<div><div>One of the most effective adaptation strategies for mitigating heat in urban spaces, particularly in hot climates, is shielding the human body from direct solar radiation. This study evaluates the thermal environment mitigation effects of sunshades and street trees through field measurements. Additionally, the results of the sun shading effects are discussed to develop more effective strategies for pedestrian heat control in urban areas. The measurement results indicate that the shading provided by sunshades and street trees lowered the new Standard Effective Temperature (SET*) by approximately 5 °C. A particularly noteworthy finding is that the same large effect was observed in both the morning and afternoon, as well as during the daytime. In the morning and afternoon, while the amount of direct solar radiation on horizontal surfaces, such as the ground, is relatively small, the radiation incident on vertical surfaces is significantly higher. Long horizontal sunshades, extended in the east–west direction, provide 8 to 10 h of solar shading, covering almost the entire day. In contrast, shorter horizontal sunshades in the east–west direction provide only 3 to 5 h of shading, meaning that people would need to move to different spots depending on the time of day. Street trees are particularly suitable for installation at intersections, as they offer shading effects in both the east–west and north–south directions due to their vertical height. This study highlights the significant role of sunshades and street trees in improving the thermal environment for pedestrians, particularly during peak commuting hours. By strategically positioning sunshades and trees, urban planners can enhance pedestrian comfort and reduce heat exposure, contributing to a more sustainable and livable urban environment.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"348 ","pages":"Article 116414"},"PeriodicalIF":7.1,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145061637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Numerical coupling of energy efficiency and thermal performance for cold plate cooling optimization in high-density compute AI data centers","authors":"Jinkyun Cho,&nbsp;Joo Hyun Moon","doi":"10.1016/j.enbuild.2025.116441","DOIUrl":"10.1016/j.enbuild.2025.116441","url":null,"abstract":"<div><div>The rapid growth of AI-driven, high-density data centers has pushed conventional air cooling to its operational limits, creating an urgent need for more efficient thermal management solutions. This study develops a coupled numerical framework that integrates CFD-based thermal analysis at the component level with system- and building-level energy performance evaluation to optimize cold plate cooling systems for a 30 MW-class data center. A total of 49 matrix cases were simulated using a k–ε turbulence model, varying coolant supply temperature (S-Class) and flow rate to assess the thermal stability of high-power chips and the associated pressure drop. These CFD results were then translated into the sizing of key cooling system components, including the Technology Cooling System (TCS), Facility Water System (FWS), and Condenser Water System (CWS), from which PUE_cooling was calculated. The findings show that higher flow rates enhance chip temperature stability but increase coolant pump power due to greater pressure drop, requiring a balance between thermal safety and energy efficiency. At the system level, all liquid cooling cases outperformed the conventional air-cooled baseline (PUE = 1.60). Optimized operating conditions achieved PUE_cooling values below 1.1, representing significant efficiency gains. This work demonstrates the novelty of numerically coupling component-level thermal performance with system-level energy analysis for large-scale AI data centers. The methodology provides practical design insights for identifying operating ranges that ensure both thermal safety of high-power chips and energy-efficient cooling, offering a scalable and sustainable solution for next-generation data center operations.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"348 ","pages":"Article 116441"},"PeriodicalIF":7.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145109751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lifecycle cost analysis of residential buildings considering thermal performance and financial uncertainties","authors":"Mikael Gilbert,&nbsp;Khalegh Barati,&nbsp;Xuesong Shen","doi":"10.1016/j.enbuild.2025.116442","DOIUrl":"10.1016/j.enbuild.2025.116442","url":null,"abstract":"<div><div>Building energy-efficient houses has been a major focus in the construction industry to lower its carbon footprint. Prior research has indicated that there is a cost trade-off between energy efficiency and capital cost. However, most cost-benefit analysis, projections use current energy prices and insulation performance, undermining the impact of future uncertainties on the project’s financial projection. This research aims to present a holistic framework where optimal insulation material and renewable pricing scenarios are considered throughout a building’s Lifecycle Cost (LCC) analysis. Firstly, two Australian residential case buildings were selected to showcase the capability of the framework. Next, the optimal insulation material is selected using multi-criteria decision analysis which considers local climatic and economic conditions. Adjustments to the LCC parameters by considering the impacts of building quality on thermal performance are also performed. Results have shown that Building Quality Index (BQI)-adjusted building insulation specifications can provide a performance buffer (11.6%) in residential settings without significant additional costs. Thirdly, a financial model was also constructed considering the uptake in renewable energy and its macroscopic impact on the overall energy price. These changes were then used to modify the inputs of the LCC analysis to determine the best energy-saving solutions. Unexpectedly, the LCC analysis also found that an aggressive uptake in renewable energy production, which would drive down energy prices, may disincentivise stakeholders from opting for more capital-intensive additional energy saving measures (ESMs). By utilising this framework, designers can produce localised and future-proof solutions, addressing the current limitations of LCC analysis.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"348 ","pages":"Article 116442"},"PeriodicalIF":7.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145097830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing hybrid insulation systems for diverse climates: A comparative analysis of composite material combinations in residential buildings","authors":"Salim Khoso ,&nbsp;Ezzeddin Bakhtavar ,&nbsp;Ahmed Abouyoussef ,&nbsp;Muhammad Zahid ,&nbsp;Kasun Hewage ,&nbsp;Rehan Sadiq","doi":"10.1016/j.enbuild.2025.116433","DOIUrl":"10.1016/j.enbuild.2025.116433","url":null,"abstract":"<div><div>With increasing concerns over global warming and climate change, achieving environmental sustainability in residential construction has become a priority. Traditional insulation materials often struggle to maintain optimal thermal and energy efficiency across varying climatic conditions, highlighting the need for innovative hybrid systems. This study systematically evaluates hybrid insulation systems through simulation-based analysis and a multi-objective mathematical model to optimize energy performance in residential buildings. Simulations were conducted to analyze different material configurations in two distinct Canadian climates: the mild conditions of Vancouver and the cold environment of Winnipeg. The assessment considered thermal resistance, energy consumption, and operational emissions. A multi-objective binary integer programming model was developed to prioritize material combinations based on five key criteria: accessibility to materials, total energy consumption, operational cost, operational environmental impacts, and societal aesthetics. The model incorporated priority weights to align with diverse stakeholder preferences, enabling decision-makers to tailor the optimization process based on specific goals. The results demonstrate that Combination 4, comprising limestone, oriented strand board (OSB), and clay tiles, consistently outperformed other configurations in both climates. In Vancouver, this combination reduced energy consumption by 47.7% compared to a conventional 6-inch concrete wall, while in Winnipeg, it achieved a 49.8% reduction. Furthermore, Combination 4 exhibited the lowest operational emissions and costs, making it the most cost-effective and sustainable choice. These findings provide valuable insights for architects, policymakers, and construction professionals seeking resilient, energy-efficient, and environmentally sustainable insulation solutions adaptable to diverse climatic conditions.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"348 ","pages":"Article 116433"},"PeriodicalIF":7.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145097884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Topology optimization of phase-change energy walls considering boundary conditions and thermal interference effects","authors":"Huiyuan Wang ,&nbsp;Xiaozhao Li ,&nbsp;Xue Wang ,&nbsp;Zhaofei Dong ,&nbsp;Lei Zhang ,&nbsp;Peng Zhao","doi":"10.1016/j.enbuild.2025.116438","DOIUrl":"10.1016/j.enbuild.2025.116438","url":null,"abstract":"<div><div>This study proposes a topology-optimized phase-change energy wall (TPEW) enhanced with PCM-enhanced concrete (PEC) and develops a coupled three-dimensional thermo-hydro-mechanical finite element model to systematically analyze the heat exchange performance and thermo-mechanical coupling characteristics of TPEWs under various optimization strategies and boundary conditions. Results show that TP-G and TP-T distinctly affect PEC zones depending on pipe configurations: for DW 1U-pipe, TP-G shifts PEC toward the soil, while TP-T shifts it toward the pipe; for DW 2U-pipe, TP-G forms X-shaped PEC, while TP-T forms droplet-shaped PEC near the pipes; for PW 1U-pipe, TP-G distributes PEC horizontally, while TP-T distributes it vertically; for PW 3U-pipe, TP-G forms I-shaped PEC, while TP-T creates six isolated zones. Under seepage, TP-T shifts PEC downstream as seepage velocity <em>v_w</em> increases, whereas under airflow, TP-T shifts PEC toward the soil-side as airflow velocity <em>v_a</em> increases. Temperature-dominated topology (TP-T) enhances heat exchange power, gradient-dominated topology (TP-G) reduces thermal stress and thermal interference TP-T further improves power. Compared with conventional center-backfilled (CB), the maximum power increases of TP-T under pure soil, seepage, and air boundary conditions are 25.7%, 6.2% and 20.5%, respectively. Under pure soil, seepage, and air boundary conditions, TP-TI further enhances power for larger pipe configurations, achieving increases over TP-T of 12.6%, 19.5%, and 5.4%, and reduces heated zones by up to 22%. In summary, the topology-optimized PEC zones effectively enhance power, reduce thermal stress and long-term stability, providing practical guidance for the design and optimization of phase-change energy walls under various pipe configurations and boundary conditions.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"348 ","pages":"Article 116438"},"PeriodicalIF":7.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145109687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A shot in the dark: The current state of PCM hysteresis modelling in building energy simulation software","authors":"Dmitry Zhilyaev ,&nbsp;Alejandro E. Albanesi ,&nbsp;M. Cecilia Demarchi ,&nbsp;Víctor D. Fachinotti ,&nbsp;Hans L.M. Bakker ,&nbsp;Henk M. Jonkers","doi":"10.1016/j.enbuild.2025.116418","DOIUrl":"10.1016/j.enbuild.2025.116418","url":null,"abstract":"<div><div>Phase change materials (PCM) are receiving ever-growing attention as a promising construction material for improving building energy performance through thermal storage and peak load shifting. The analysis of PCM performance and decision-making related to PCM implementation in building envelopes often relies on building energy simulation software such as EnergyPlus – a de facto standard in the academic world and the industry. For a precise modelling of the dynamic PCM behaviour, it is essential to correctly account for PCM hysteresis. This work introduces two new implementations of PCM hysteresis models in EnergyPlus. Further, it provides an in-depth analysis of four publicly available EnergyPlus-based hysteresis models, including the two newly introduced ones, and identifies the existing limitations for each of them. Finally, it explores the effects of PCM model selection on decision-making using the example of novel PCM-embedded material development. The results of this study show that the current built-in hysteresis model in EnergyPlus is not implemented correctly, and none of the other analysed models is completely free of limitations. Moreover, this work draws attention to the existing contradictions between different PCM modelling approaches, highlighting the critical impact the selection of a PCM model has on PCM-related decision-making. We conclude that while the existing hysteresis models in EnergyPlus are operable – albeit with great caution – they are not yet at the stage where they could be used as a reliable decision-making support tool. Practical real-world integration of PCM in building envelopes is hardly possible without having dependable modelling tools to back it up, and the development of such tools requires far more attention than it is given at the moment.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"348 ","pages":"Article 116418"},"PeriodicalIF":7.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145097882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing thermal insulation through geometric design: Comparative analysis of normal and lightweight 3D printed concrete wall patterns","authors":"Ruiqing Liu,&nbsp;Hongjian Du","doi":"10.1016/j.enbuild.2025.116437","DOIUrl":"10.1016/j.enbuild.2025.116437","url":null,"abstract":"<div><div>Thermal performance plays a crucial role in the energy efficiency of 3D-printed concrete (3DPC) buildings, yet it remains underexplored compared to structural considerations. Unlike traditional cast-in-place walls, 3DPC walls enable complex internal geometries that can enhance insulation while reducing material consumption. This study investigates the thermal insulation performance of 3DPC walls with different patterns using both normal mortar and lightweight mortar mixtures. Ten walls were analyzed in total, including five normal 3DPC walls and five lightweight 3DPC walls. Thermal transmittance (U-value) assessed resistive insulation, while time lag and decremental factor evaluated capacitive insulation. All 3DPC hollow walls exhibited lower U-values compared to the solid wall, with reductions ranging from 45.3 % to 73.6 %. Among them, the double-row triangular wall demonstrated the best overall thermal insulation. When combined with a lightweight mixture, it achieved the lowest U-value of 1.90 W/(m²·K), representing a 73.6 % reduction relative to the solid configuration. With normal mixture, it had the lowest decremental factor (0.741) and a time lag of 105 min. These findings confirm that air layer configurations in 3DPC walls can greatly improve thermal insulation. Lightweight mixture performs better for resistive insulation, while normal mixture is more efficient in capacitive insulation. This study provides valuable insights for enhancing energy efficiency in additive construction. The findings contribute to the development of sustainable building practices, supporting the integration of 3D printing technology into energy-efficient architectural design and future construction standards.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"348 ","pages":"Article 116437"},"PeriodicalIF":7.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145097886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An adaptable framework for resilient subtropical low-income housing under future climate and predicted lifestyles: a Hong Kong case study","authors":"Yilin Lee ,&nbsp;Edward Ng","doi":"10.1016/j.enbuild.2025.116412","DOIUrl":"10.1016/j.enbuild.2025.116412","url":null,"abstract":"<div><div>This study presents an integrated design framework combining passive cooling strategies with occupant behaviour modelling to improve the thermal resilience of low-income housing in subtropical, high density cities. Driven by the urgent need for resilient, occupant-focused housing in high-density urban areas, the framework addresses the declining effectiveness of traditional passive cooling. These measures predominantly rely on the indoor-outdoor temperature gradient, which is diminishing due to rising extreme heat events. The proposed framework layers occupant-driven spatial adaptations including thermal zoning, dynamic occupancy schedules, functional allocation, interior partitioning, and semi-outdoor areas to create local microclimates that more effectively mitigate heat stress.</div><div>Using Hong Kong as a case study, EnergyPlus simulations evaluate current conditions and projected heat scenarios for 2040 and 2090. In parallel, façade measures such as optimized window-to-wall ratios, operable and strategically spaced windows, fixed shading devices, advanced glazing, and high-performance wall insulationfurther control solar heat gain. Linear regression and Sobol global sensitivity analyses quantify each strategy’s impact on cooling loads and annual comfort hours. The combined spatial and façade interventions reduce cooling loads by up to 73% under present conditions and increase comfort hours by up to 89% under future climates.</div><div>This approach links technical performance with occupant adaptability. It offers scalable design guidance for subtropical, high-density urban housing amid escalating heat.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"348 ","pages":"Article 116412"},"PeriodicalIF":7.1,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145097832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}