Energy and Buildings最新文献_第5页

Spatiotemporal evolution of the temperature field in cemented tailings backfill considering volume effects and its impact on the thermal environment 考虑体积效应的尾砂胶结充填体温度场时空演化及其对热环境的影响

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-04-01 Epub Date: 2026-02-05 DOI: 10.1016/j.enbuild.2026.117110

Menghui Xiao , Cuifeng Du , Weidong Song , Yuan Wang , Zimo Shi , Yao Lu

Hydration‐induced heating in cemented tailings backfill (CTB) can deteriorate the thermal environment of underground working areas. To support thermal management, the influence of placement volume on the spatiotemporal evolution of the CTB temperature field and its coupled multiphysics processes was investigated. An integrated micro–macro experimental program was conducted to analyze the spatiotemporal evolution of hydration parameters for CTB with different volumes, and to develop a temperature-field model incorporating volume effects. A coupled thermos-chemical-hydraulic-electrical (T-C-H-E) mechanism was then proposed. In-situ monitoring was undertaken to validate the model and assess environmental impact. The results indicate that volume effects significantly reshape the temperature field; both peak temperature and time-to-peak increase with volume. Specifically, the largest sample (CTB₄₀) exhibited a peak temperature 6.9 ℃ higher than the smallest sample (CTB₁₀). Peak temperature at different locations exhibits a power-law relationship with characteristic length (T = T_env + aL_c^b), and the spatial profile is approximately Gaussian. Microstructural tests indicate greater formation of hydration products with increasing volume, with enrichment in the center and lower region. The hydration product content in the central region is 1.73 times that of the surrounding areas. Temperature is strongly and positively correlated with hydration product yield, confirming spatial non-uniformity driven by volume effects. The proposed T-C-H-E mechanism captures this spatiotemporal coupling. In-situ validation reports that the error of the temperature field calculation model was less than 10 %, and the backfill increases the ambient temperature by approximately 4–5 ℃. These findings provide practical guidance for controlling backfill heat release and improving the mine thermal environment.

尾砂胶结充填体水化加热会使井下采空区热环境恶化。为了支持热管理，研究了放置体积对CTB温度场时空演变及其耦合多物理场过程的影响。采用微观-宏观一体化实验方案，分析了不同体积CTB水化参数的时空演化规律，建立了考虑体积效应的温度场模型。提出了热-化学-液-电耦合机理。进行了现场监测，以验证模型并评估环境影响。结果表明，体积效应显著地改变了温度场；峰值温度和到达峰值的时间随体积的增加而增加。其中，最大样品CTB40的峰值温度比最小样品CTB10的峰值温度高6.9℃。不同位置的峰值温度与特征长度呈幂律关系（T = Tenv + aLcb），空间分布近似为高斯分布。微观结构试验表明，随着体积的增大，水化产物的形成增多，在中心和下部富集。中部水化产物含量是周边水化产物含量的1.73倍。温度与水化产物产率呈正相关，证实了体积效应驱动的空间非均匀性。提出的T-C-H-E机制捕获了这种时空耦合。现场验证表明，温度场计算模型误差小于10%，充填体使环境温度升高约4 ~ 5℃。研究结果对控制回填体放热，改善矿山热环境具有实际指导意义。

{"title":"Spatiotemporal evolution of the temperature field in cemented tailings backfill considering volume effects and its impact on the thermal environment","authors":"Menghui Xiao , Cuifeng Du , Weidong Song , Yuan Wang , Zimo Shi , Yao Lu","doi":"10.1016/j.enbuild.2026.117110","DOIUrl":"10.1016/j.enbuild.2026.117110","url":null,"abstract":"<div><div>Hydration‐induced heating in cemented tailings backfill (CTB) can deteriorate the thermal environment of underground working areas. To support thermal management, the influence of placement volume on the spatiotemporal evolution of the CTB temperature field and its coupled multiphysics processes was investigated. An integrated micro–macro experimental program was conducted to analyze the spatiotemporal evolution of hydration parameters for CTB with different volumes, and to develop a temperature-field model incorporating volume effects. A coupled thermos-chemical-hydraulic-electrical (T-C-H-E) mechanism was then proposed. In-situ monitoring was undertaken to validate the model and assess environmental impact. The results indicate that volume effects significantly reshape the temperature field; both peak temperature and time-to-peak increase with volume. Specifically, the largest sample (CTB<sub>40</sub>) exhibited a peak temperature 6.9 ℃ higher than the smallest sample (CTB<sub>10</sub>). Peak temperature at different locations exhibits a power-law relationship with characteristic length (<em>T = T<sub>env</sub> + aL<sub>c</sub><sup>b</sup></em>), and the spatial profile is approximately Gaussian. Microstructural tests indicate greater formation of hydration products with increasing volume, with enrichment in the center and lower region. The hydration product content in the central region is 1.73 times that of the surrounding areas. Temperature is strongly and positively correlated with hydration product yield, confirming spatial non-uniformity driven by volume effects. The proposed T-C-H-E mechanism captures this spatiotemporal coupling. In-situ validation reports that the error of the temperature field calculation model was less than 10 %, and the backfill increases the ambient temperature by approximately 4–5 ℃. These findings provide practical guidance for controlling backfill heat release and improving the mine thermal environment.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"356 ","pages":"Article 117110"},"PeriodicalIF":7.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146185943","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}

引用次数: 0

A Non-Invasive stacked ensemble framework with shadow correction for Cost-Effective daylight illuminance prediction in buildings 一种具有阴影校正的非侵入式叠加集成框架，用于建筑物中具有成本效益的日光照度预测

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-04-01 Epub Date: 2026-02-04 DOI: 10.1016/j.enbuild.2026.117116

Shanshan Li, Xinyue Xu, Haoran Wang, Yuheng Cao, Hongda An, Ziyang Wang, Sina A, Changhao Wang

Rapid and accurate prediction of indoor daylight illuminance is pivotal for dynamically optimizing artificial lighting operation under insufficient daylight conditions, a key strategy for reducing building energy consumption. To address the limitations of existing methodologies, including the computational latency of physical simulations, the insufficient adaptability to dynamic shading, and the data complexity challenges in machine learning algorithms, this study introduces a novel non-intrusive methodological framework for rapid daylight prediction, achieved through the synergistic integration of stacked ensemble learning and shadow correction strategies. A large-scale dataset of 46,656 scenarios, encompassing diverse environmental, spatial, and building-related variables, was generated using DIALux evo software. At its core, a Bayesian-optimized stacked ensemble model, combining XGBoost and Random Forest, was developed, achieving a Mean Absolute Percentage Error (MAPE) of 1.89% and a Mean Absolute Error (MAE) of 21.95 lx under complex lighting conditions, markedly surpassing single-algorithm models. To circumvent the geometric explosion in data volume associated with incorporating occlusion parameters, a partitioned shading coverage method guided by the Bayesian Information Criterion (BIC) was further proposed. This efficient post-hoc correction strategy enhances the framework’s theoretical capability to characterize dynamic shading effects from different scenarios, thereby significantly expanding its methodological applicability. Furthermore, SHapley Additive exPlanations (SHAP) analysis was employed to identify XGBoost as the primary contributor of the model and verify the model’s consistency with established daylighting principles. While validated on a simulation-based dataset, the proposed framework presents a low-cost, high-precision solution for rapid indoor daylight prediction and exhibits theoretical adaptability to complex shading scenarios, thereby offering a valuable data basis for subsequent lighting control strategies.

快速准确地预测室内日光照度对于在日光不足条件下动态优化人工照明运行至关重要，这是降低建筑能耗的关键策略。为了解决现有方法的局限性，包括物理模拟的计算延迟、对动态阴影的适应性不足以及机器学习算法中的数据复杂性挑战，本研究引入了一种新的非侵入式方法框架，通过堆叠集成学习和阴影校正策略的协同集成来实现快速日光预测。使用DIALux evo软件生成了包含46,656个场景的大型数据集，包括各种环境，空间和建筑相关变量。该模型的核心是bayesian优化的叠加集成模型，结合XGBoost和Random Forest，在复杂光照条件下的平均绝对百分比误差（MAPE）为1.89%，平均绝对误差（MAE）为21.95 lx，明显优于单一算法模型。为了避免遮挡参数合并带来的数据量几何爆炸，进一步提出了一种基于贝叶斯信息准则（BIC）的分区遮阳覆盖方法。这种有效的事后校正策略增强了框架表征不同场景下动态阴影效果的理论能力，从而大大扩展了其方法的适用性。此外，采用SHapley加性解释（SHAP）分析确定XGBoost是模型的主要贡献者，并验证模型与既定采光原则的一致性。在基于模拟的数据集上验证，该框架为快速室内日光预测提供了一种低成本、高精度的解决方案，并表现出对复杂遮阳场景的理论适应性，从而为后续照明控制策略提供了有价值的数据基础。

{"title":"A Non-Invasive stacked ensemble framework with shadow correction for Cost-Effective daylight illuminance prediction in buildings","authors":"Shanshan Li, Xinyue Xu, Haoran Wang, Yuheng Cao, Hongda An, Ziyang Wang, Sina A, Changhao Wang","doi":"10.1016/j.enbuild.2026.117116","DOIUrl":"10.1016/j.enbuild.2026.117116","url":null,"abstract":"<div><div>Rapid and accurate prediction of indoor daylight illuminance is pivotal for dynamically optimizing artificial lighting operation under insufficient daylight conditions, a key strategy for reducing building energy consumption. To address the limitations of existing methodologies, including the computational latency of physical simulations, the insufficient adaptability to dynamic shading, and the data complexity challenges in machine learning algorithms, this study introduces a novel non-intrusive methodological framework for rapid daylight prediction, achieved through the synergistic integration of stacked ensemble learning and shadow correction strategies. A large-scale dataset of 46,656 scenarios, encompassing diverse environmental, spatial, and building-related variables, was generated using DIALux evo software. At its core, a Bayesian-optimized stacked ensemble model, combining XGBoost and Random Forest, was developed, achieving a Mean Absolute Percentage Error (MAPE) of 1.89% and a Mean Absolute Error (MAE) of 21.95 lx under complex lighting conditions, markedly surpassing single-algorithm models. To circumvent the geometric explosion in data volume associated with incorporating occlusion parameters, a partitioned shading coverage method guided by the Bayesian Information Criterion (BIC) was further proposed. This efficient post-hoc correction strategy enhances the framework’s theoretical capability to characterize dynamic shading effects from different scenarios, thereby significantly expanding its methodological applicability. Furthermore, SHapley Additive exPlanations (SHAP) analysis was employed to identify XGBoost as the primary contributor of the model and verify the model’s consistency with established daylighting principles. While validated on a simulation-based dataset, the proposed framework presents a low-cost, high-precision solution for rapid indoor daylight prediction and exhibits theoretical adaptability to complex shading scenarios, thereby offering a valuable data basis for subsequent lighting control strategies.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"356 ","pages":"Article 117116"},"PeriodicalIF":7.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146185968","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}

引用次数: 0

Hybrid machine learning–physics-based modeling and model predictive control of variable refrigerant flow systems in buildings 基于混合机器学习-物理的建筑物变制冷剂流量系统建模与模型预测控制

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-04-01 Epub Date: 2026-01-30 DOI: 10.1016/j.enbuild.2026.117086

Po-Ching Hsu, Yunho Hwang

Model predictive control (MPC) of variable refrigerant flow (VRF) in buildings requires accurate modeling of both overall power consumption and the capacity distribution among individual indoor units (IDUs). Conventional physics-based models, such as VRF-SysCurve, often struggle to capture the system dynamics or represent detailed control inputs, while purely data-driven models, though accurate, typically lack physical consistency. This study proposes a hybrid modeling framework that integrates a modified VRF-SysCurve model with a machine learning (ML) model to enhance control flexibility, predictive accuracy, and physical consistency. Control-oriented inputs selected through domain expertise enable the ML model to predict IDU capacities, which are then used by the modified VRF-SysCurve model to estimate total system power. The models are trained and validated using real-world field test data from both cooling and heating seasons, with hyperparameters optimized through Bayesian optimization. A new evaluation framework combining conventional accuracy metrics and Spearman correlation is introduced to jointly assess predictive accuracy and physical consistency. Results show that the ANN-Sub model achieves high accuracy in predicting per-IDU cooling capacity (R² ≥ 0.95). The modified VRF-SysCurve with Lasso Regression provides the best balance of accuracy, physical consistency, and simplicity for power prediction. The developed hybrid model is integrated into an MPC framework to demonstrate demand-side flexibility through multi-objective optimization of energy consumption and thermal comfort in both cooling and heating modes.

建筑物中变制冷剂流量（VRF）的模型预测控制（MPC）需要对总功耗和各个室内单元（idu）之间的容量分布进行精确建模。传统的基于物理的模型，如VRF-SysCurve，通常难以捕捉系统动态或表示详细的控制输入，而纯数据驱动的模型虽然准确，但通常缺乏物理一致性。本研究提出了一种混合建模框架，该框架将改进的VRF-SysCurve模型与机器学习（ML）模型集成在一起，以增强控制灵活性、预测准确性和物理一致性。通过领域专业知识选择的面向控制的输入使ML模型能够预测IDU容量，然后由修改后的VRF-SysCurve模型使用这些容量来估计系统的总功率。模型使用来自制冷和供暖季节的实际现场测试数据进行训练和验证，并通过贝叶斯优化对超参数进行优化。提出了一种结合传统精度指标和Spearman相关的评价框架，对预测精度和物理一致性进行联合评价。结果表明，ANN-Sub模型对每idu制冷量的预测精度较高（R2≥0.95）。使用Lasso Regression的改进VRF-SysCurve为功率预测提供了准确性、物理一致性和简单性的最佳平衡。开发的混合动力模型集成到MPC框架中，通过在制冷和供暖模式下对能耗和热舒适性进行多目标优化，展示需求侧灵活性。

{"title":"Hybrid machine learning–physics-based modeling and model predictive control of variable refrigerant flow systems in buildings","authors":"Po-Ching Hsu, Yunho Hwang","doi":"10.1016/j.enbuild.2026.117086","DOIUrl":"10.1016/j.enbuild.2026.117086","url":null,"abstract":"<div><div>Model predictive control (MPC) of variable refrigerant flow (VRF) in buildings requires accurate modeling of both overall power consumption and the capacity distribution among individual indoor units (IDUs). Conventional physics-based models, such as VRF-SysCurve, often struggle to capture the system dynamics or represent detailed control inputs, while purely data-driven models, though accurate, typically lack physical consistency. This study proposes a hybrid modeling framework that integrates a modified VRF-SysCurve model with a machine learning (ML) model to enhance control flexibility, predictive accuracy, and physical consistency. Control-oriented inputs selected through domain expertise enable the ML model to predict IDU capacities, which are then used by the modified VRF-SysCurve model to estimate total system power. The models are trained and validated using real-world field test data from both cooling and heating seasons, with hyperparameters optimized through Bayesian optimization. A new evaluation framework combining conventional accuracy metrics and Spearman correlation is introduced to jointly assess predictive accuracy and physical consistency. Results show that the ANN-Sub model achieves high accuracy in predicting per-IDU cooling capacity (R<sup>2</sup> ≥ 0.95). The modified VRF-SysCurve with Lasso Regression provides the best balance of accuracy, physical consistency, and simplicity for power prediction. The developed hybrid model is integrated into an MPC framework to demonstrate demand-side flexibility through multi-objective optimization of energy consumption and thermal comfort in both cooling and heating modes.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"356 ","pages":"Article 117086"},"PeriodicalIF":7.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146089294","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}

引用次数: 0

Multiscale performance of embedded current collector cement-based double-layer capacitor for building-energy storage integration: microstructure, mechanical and electrochemical properties 建筑-储能一体化嵌入式集流水泥双层电容器的多尺度性能：微观结构、力学和电化学性能

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-04-01 Epub Date: 2026-02-07 DOI: 10.1016/j.enbuild.2026.117125

Jun Tian , Wenchao Zhu , Xiaowei Wu , Yu Zheng , Weiwei Zhang , Jinyun Yuan , Wen-Wei Wang , Hao Fu , Mingyuan Liu

Embedded current collector cement-based double-layer capacitors (EDLCs) can simultaneously achieve the dual functions of load-bearing and energy storage, providing a potential feasible technical path for integration of building structures and energy storage. Therefore, this study investigated the feasibility of integrating building structure and energy storage functions using EDLCs. It concentrated on exploring the effects of fiber content and fiber types (i.e., carbon fiber and steel fiber), and current collector types (i.e., steel wire mesh and carbon fiber mesh) on the microstructure, working performance, mechanical properties, and electrochemical properties of EDLCs. The results showed that carbon fibers exhibited superior electrical conductivity, mechanical performance, and electrochemical properties compared with steel fibers. Specifically, compared with the electrode with steel fibers (GP-3), the electrode with carbon fibers (TP-3) has a 94.88% reduction in resistivity and an 8.80% increase in compressive strength; correspondingly, the area capacitance of capacitor T-TP-3 was 645.81% higher than that of T-GP-3. The “point-line” conductive network constructed by carbon black and carbon fibers markedly boosted the conductivity of cement-based electrodes and the energy storage performance of EDLCs. Although the increase in content of steel fibers enhanced area capacitance of EDLCs, steel fibers were prone to corrosion in cement-based environments containing chloride ions, which ultimately limited their overall electrochemical performance. The type of current collector significantly affected the capacitance performance under different current densities, and carbon fiber mesh current collector was superior to steel wire mesh current collector. The electrochemical results indicate that the EDLCs exhibit typical electric double-layer capacitive behavior, as reflected by cyclic voltammetry curves, galvanostatic charge–discharge characteristics and impedance response. This study can provide a credible foundation and technical aid for the design and practical application of embedded current collector cement-based double-layer capacitors in integrating building structure with energy storage functions.

嵌入式集流水泥基双层电容器（edlc）可同时实现承重和储能双重功能，为建筑结构与储能一体化提供了一条潜在可行的技术路径。因此，本研究探讨了利用edlc将建筑结构与储能功能相结合的可行性。重点探讨了纤维含量、纤维类型（碳纤维和钢纤维）、集流类型（钢丝网和碳纤维网）对edlc的微观结构、工作性能、力学性能和电化学性能的影响。结果表明，碳纤维具有优于钢纤维的导电性、力学性能和电化学性能。其中，与钢纤维电极（GP-3）相比，碳纤维电极（TP-3）的电阻率降低了94.88%，抗压强度提高了8.80%；相应的，T-TP-3电容器的面积电容比T-GP-3高645.81%。炭黑和碳纤维构建的“点线”导电网络显著提高了水泥基电极的导电性和edlc的储能性能。虽然钢纤维含量的增加增强了edlc的面积电容，但在含氯离子的水泥基环境中，钢纤维容易腐蚀，最终限制了edlc的整体电化学性能。不同电流密度下，集流器类型对电容性能有显著影响，碳纤维网状集流器优于钢丝网状集流器。电化学结果表明，edlc具有典型的双电层电容性，反映在循环伏安曲线、恒流充放电特性和阻抗响应上。本研究可为嵌入式集流水泥基双层电容器在建筑结构与储能功能集成中的设计和实际应用提供可靠的基础和技术支持。

{"title":"Multiscale performance of embedded current collector cement-based double-layer capacitor for building-energy storage integration: microstructure, mechanical and electrochemical properties","authors":"Jun Tian , Wenchao Zhu , Xiaowei Wu , Yu Zheng , Weiwei Zhang , Jinyun Yuan , Wen-Wei Wang , Hao Fu , Mingyuan Liu","doi":"10.1016/j.enbuild.2026.117125","DOIUrl":"10.1016/j.enbuild.2026.117125","url":null,"abstract":"<div><div>Embedded current collector cement-based double-layer capacitors (EDLCs) can simultaneously achieve the dual functions of load-bearing and energy storage, providing a potential feasible technical path for integration of building structures and energy storage. Therefore, this study investigated the feasibility of integrating building structure and energy storage functions using EDLCs. It concentrated on exploring the effects of fiber content and fiber types (i.e., carbon fiber and steel fiber), and current collector types (i.e., steel wire mesh and carbon fiber mesh) on the microstructure, working performance, mechanical properties, and electrochemical properties of EDLCs. The results showed that carbon fibers exhibited superior electrical conductivity, mechanical performance, and electrochemical properties compared with steel fibers. Specifically, compared with the electrode with steel fibers (GP-3), the electrode with carbon fibers (TP-3) has a 94.88% reduction in resistivity and an 8.80% increase in compressive strength; correspondingly, the area capacitance of capacitor T-TP-3 was 645.81% higher than that of T-GP-3. The “point-line” conductive network constructed by carbon black and carbon fibers markedly boosted the conductivity of cement-based electrodes and the energy storage performance of EDLCs. Although the increase in content of steel fibers enhanced area capacitance of EDLCs, steel fibers were prone to corrosion in cement-based environments containing chloride ions, which ultimately limited their overall electrochemical performance. The type of current collector significantly affected the capacitance performance under different current densities, and carbon fiber mesh current collector was superior to steel wire mesh current collector. The electrochemical results indicate that the EDLCs exhibit typical electric double-layer capacitive behavior, as reflected by cyclic voltammetry curves, galvanostatic charge–discharge characteristics and impedance response. This study can provide a credible foundation and technical aid for the design and practical application of embedded current collector cement-based double-layer capacitors in integrating building structure with energy storage functions.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"356 ","pages":"Article 117125"},"PeriodicalIF":7.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146134673","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}

引用次数: 0

Synergistic deployment of electric heat pumps and pit thermal energy storage for renewable energy integration and heating decarbonization 电热泵与地穴蓄热协同部署，实现可再生能源整合与供热脱碳

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-04-01 Epub Date: 2026-01-29 DOI: 10.1016/j.enbuild.2026.117079

Luyao Li , Jichao Zhao , Zhiyong Tian , Xinyu Chen , Dilshod Jalilov , Tukhtamurod Juraev , Akbar Halimov , Michael T.F. Owen

With the rapid expansion of renewable energy (RE) sources such as photovoltaic (PV) and wind power (WP), managing surplus energy and mitigating renewable energy curtailment have become critical challenges. This study investigates the synergistic integration of electric heat pumps (EHPs) and pit thermal energy storage (PTES) as a power-to-heat pathway to enhance renewable energy utilization and district heating (DH) performance.. A theoretical framework and a PTES heat transfer model are developed to evaluate the impacts of EHP–PTES integration on curtailment mitigation, auxiliary heating demand, and system investment costs. Integrating EHPs with PTES increases storage temperatures, reduces reliance on backup heating, and decreases solar collector investment by up to 56%. In high-penetration RE systems, a 94,985 m³ PTES can lower curtailment rates by 32.43%, saving approximately CNY 433.61 million in curtailed energy costs, CNY 30.27 million in collector investment, and reducing auxiliary heating electricity consumption by 94.5%. Compared with electrochemical storage, power-to-gas technologies, and conventional solar district heating systems, the EHP–PTES pathway enables large-capacity, low-cost, and long-duration utilization of curtailed electricity while directly interfacing with existing district heating networks. These findings highlight the significant potential of EHP-PTES integration for optimizing RE utilization, promoting heating decarbonization, and reducing overall system costs.

随着光伏（PV）和风电（WP）等可再生能源（RE）的迅速发展，管理剩余能源和减少可再生能源弃风已成为严峻的挑战。本研究探讨了电热泵（EHPs）和坑式储热（PTES）的协同集成作为一种电力到热量的途径，以提高可再生能源的利用和区域供热（DH）的性能。建立了一个理论框架和PTES传热模型，以评估EHP-PTES集成对减少弃风、辅助供热需求和系统投资成本的影响。将EHPs与PTES集成可以提高存储温度，减少对备用加热的依赖，并减少高达56%的太阳能集热器投资。在高渗透可再生能源系统中，94,985 m3的PTES可降低弃风率32.43%，节约约4.3361亿元的弃风能源成本，节约集热器投资3027万元，减少94.5%的辅助供热用电量。与电化学存储、电转气技术和传统太阳能区域供热系统相比，EHP-PTES路径能够大容量、低成本、长时间地利用减少的电力，同时直接与现有的区域供热网络连接。这些发现突出了EHP-PTES集成在优化可再生能源利用、促进加热脱碳和降低整体系统成本方面的巨大潜力。

{"title":"Synergistic deployment of electric heat pumps and pit thermal energy storage for renewable energy integration and heating decarbonization","authors":"Luyao Li , Jichao Zhao , Zhiyong Tian , Xinyu Chen , Dilshod Jalilov , Tukhtamurod Juraev , Akbar Halimov , Michael T.F. Owen","doi":"10.1016/j.enbuild.2026.117079","DOIUrl":"10.1016/j.enbuild.2026.117079","url":null,"abstract":"<div><div>With the rapid expansion of renewable energy (RE) sources such as photovoltaic (PV) and wind power (WP), managing surplus energy and mitigating renewable energy curtailment have become critical challenges. This study investigates the synergistic integration of electric heat pumps (EHPs) and pit thermal energy storage (PTES) as a power-to-heat pathway to enhance renewable energy utilization and district heating (DH) performance.. A theoretical framework and a PTES heat transfer model are developed to evaluate the impacts of EHP–PTES integration on curtailment mitigation, auxiliary heating demand, and system investment costs. Integrating EHPs with PTES increases storage temperatures, reduces reliance on backup heating, and decreases solar collector investment by up to 56%. In high-penetration RE systems, a 94,985 m<sup>3</sup> PTES can lower curtailment rates by 32.43%, saving approximately CNY 433.61 million in curtailed energy costs, CNY 30.27 million in collector investment, and reducing auxiliary heating electricity consumption by 94.5%. Compared with electrochemical storage, power-to-gas technologies, and conventional solar district heating systems, the EHP–PTES pathway enables large-capacity, low-cost, and long-duration utilization of curtailed electricity while directly interfacing with existing district heating networks. These findings highlight the significant potential of EHP-PTES integration for optimizing RE utilization, promoting heating decarbonization, and reducing overall system costs.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"356 ","pages":"Article 117079"},"PeriodicalIF":7.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146071621","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}

引用次数: 0

Artificial intelligence for improving thermal comfort through envelope design in residential buildings: Recent developments and future directions 通过住宅建筑围护结构设计改善热舒适的人工智能：最新发展和未来方向

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-04-01 Epub Date: 2026-01-13 DOI: 10.1016/j.enbuild.2026.117007

Arda Bayraktar, Berk Ekici

Envelopes are vital components for improving thermal comfort in almost all building typologies. Yet, the design and analysis of envelopes are complex, as they involve multiple aspects and various parameters, ensuring comfort standards. Improving thermal comfort in residential buildings is within the scope of researchers to suggest sustainable design alternatives that consider multiple performance aspects and design parameters. Previous review articles have focused on improving thermal performance in residential buildings from the perspective of envelope technology, materials, and design strategies. However, none of them investigated current developments using artificial intelligence (AI), which inevitably supports decision-making in complex circumstances for a sustainable built environment. This review examines the contribution of AI methods, which consist of metaheuristic optimization and machine learning algorithms as sub-branches, to envelope parameters. The paper systematically reviews 95 relevant works on AI, including early approaches, to provide a comprehensive overview of current developments, following PRISMA guidelines. The results showed that early applications considered conventional approaches to improve thermal comfort and energy performance, which mostly limit the results to specified cases. On the other hand, studies utilizing AI methods dealt with numerous parameters, allowing them to cope with complex envelope systems in a reasonable amount of time. The study addresses relevant research questions related to the trends, research methods, system types, AI methods, data types, and their relation to performance and envelope parameters. The study also provides actionable insight, underlining gaps and future works for utilizing machine learning methods in the reviewed research domain.

在几乎所有类型的建筑中，围护结构都是提高热舒适性的重要组成部分。然而，围护结构的设计和分析是复杂的，因为它涉及多个方面和各种参数，以确保舒适性标准。改善住宅建筑的热舒适是研究人员提出的可持续设计方案的范围，考虑多个性能方面和设计参数。以前的评论文章主要是从围护结构技术、材料和设计策略的角度来改善住宅建筑的热性能。然而，他们都没有研究使用人工智能（AI）的当前发展，这不可避免地支持在复杂情况下为可持续建筑环境做出决策。本文审查了人工智能方法的贡献，其中包括作为子分支的元启发式优化和机器学习算法，以包络参数。本文系统地回顾了95项有关人工智能的相关工作，包括早期方法，以提供当前发展的全面概述，遵循PRISMA指南。结果表明，早期的应用考虑了传统的方法来改善热舒适和能源性能，这些方法大多限制了特定情况下的结果。另一方面，利用人工智能方法的研究处理了许多参数，使他们能够在合理的时间内处理复杂的包络系统。该研究解决了与趋势、研究方法、系统类型、人工智能方法、数据类型及其与性能和信封参数的关系有关的相关研究问题。该研究还提供了可操作的见解，强调了在所审查的研究领域中利用机器学习方法的差距和未来的工作。

{"title":"Artificial intelligence for improving thermal comfort through envelope design in residential buildings: Recent developments and future directions","authors":"Arda Bayraktar, Berk Ekici","doi":"10.1016/j.enbuild.2026.117007","DOIUrl":"10.1016/j.enbuild.2026.117007","url":null,"abstract":"<div><div>Envelopes are vital components for improving thermal comfort in almost all building typologies. Yet, the design and analysis of envelopes are complex, as they involve multiple aspects and various parameters, ensuring comfort standards. Improving thermal comfort in residential buildings is within the scope of researchers to suggest sustainable design alternatives that consider multiple performance aspects and design parameters. Previous review articles have focused on improving thermal performance in residential buildings from the perspective of envelope technology, materials, and design strategies. However, none of them investigated current developments using artificial intelligence (AI), which inevitably supports decision-making in complex circumstances for a sustainable built environment. This review examines the contribution of AI methods, which consist of metaheuristic optimization and machine learning algorithms as sub-branches, to envelope parameters. The paper systematically reviews 95 relevant works on AI, including early approaches, to provide a comprehensive overview of current developments, following PRISMA guidelines. The results showed that early applications considered conventional approaches to improve thermal comfort and energy performance, which mostly limit the results to specified cases. On the other hand, studies utilizing AI methods dealt with numerous parameters, allowing them to cope with complex envelope systems in a reasonable amount of time. The study addresses relevant research questions related to the trends, research methods, system types, AI methods, data types, and their relation to performance and envelope parameters. The study also provides actionable insight, underlining gaps and future works for utilizing machine learning methods in the reviewed research domain.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"356 ","pages":"Article 117007"},"PeriodicalIF":7.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145962618","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}

引用次数: 0

Exploration of key design questions in rule-based shading control for building energy load reduction 探索基于规则的建筑节能遮阳控制的关键设计问题

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-04-01 Epub Date: 2026-01-21 DOI: 10.1016/j.enbuild.2026.117038

Jihyeon Cho , Suyeon Bang , Hoseong Lee , Yeonsook Heo

Automated shading can curb building energy use; however, its performance depends on the control strategy design. This study quantified how state variable, dynamicity level, and adaptation horizon shape end-use savings and visual comfort. and formulated static and dynamic rule-based strategies for exterior slat-type blinds that track the solar horizontal profile angle (SHPA). Both schemes were tuned monthly or annually. The candidate state variables include direct solar irradiance, outdoor temperature, and indoor temperature. We simulated the total energy loads (cooling, heating, and lighting) and operational behavior (mode duration and switching frequency) for the perimeter zones across the orientations. Monthly optimized static control achieved 39–41% total-load savings vs. a no-control baseline and outperformed a fixed 90° reference with dimming (∼29%). Dynamic SHPA tracking offers marginal energy gains (<≈1 percentage point) but incurs orders-of-magnitude higher switching frequency. Hourly analysis showed that neither the slat modulation level nor state variable choice produced load savings because the shaded areas controlled by the strategies were not significantly different. Monthly tuning outperformed annual optimized cases by ∼ 12 percentage points, reflecting seasonal non-stationarity in sun geometry and weather. This indicates that the adaptation time interval is critical in rule-based shading control. Finally, visual comfort of static controls remained acceptable; hours with visual discomfort (daylight glare index > 22) were < 3% in every zone. Overall, these findings provide a practical guideline: use optimized static rules as the default approach and select the adaptation timescale according to local climate variability, while aligning shading system design with the proposed control framework.

自动遮阳可以减少建筑能源的使用；然而，其性能取决于控制策略的设计。本研究量化了状态变量、动态水平和适应水平如何影响最终用途节约和视觉舒适度。并为跟踪太阳水平轮廓角（SHPA）的外部板条式百叶窗制定了基于静态和动态规则的策略。这两种方案都是按月或按年调整的。候选状态变量包括太阳直射度、室外温度和室内温度。我们模拟了各个方向周边区域的总能量负荷（冷却、加热和照明）和运行行为（模式持续时间和切换频率）。与无控制基线相比，每月优化的静态控制实现了39-41%的总负载节省，并且优于带调光的固定90°参考（约29%）。动态SHPA跟踪提供边际能量增益（<；≈1个百分点），但会导致更高的开关频率。每小时的分析表明，无论是调制水平还是状态变量选择都不会产生负载节省，因为由策略控制的阴影区域没有显着差异。月度调整比年度优化案例的表现高出约12个百分点，反映了太阳几何形状和天气的季节性非平稳性。这表明适应时间间隔在基于规则的着色控制中是至关重要的。最后，静态控制的视觉舒适度仍然可以接受；每个区域的视觉不适时间（日光眩光指数>； 22）为<； 3%。总的来说，这些发现提供了一个实用的指导方针：使用优化的静态规则作为默认方法，并根据当地气候变化选择适应时间尺度，同时将遮阳系统设计与提出的控制框架保持一致。

{"title":"Exploration of key design questions in rule-based shading control for building energy load reduction","authors":"Jihyeon Cho , Suyeon Bang , Hoseong Lee , Yeonsook Heo","doi":"10.1016/j.enbuild.2026.117038","DOIUrl":"10.1016/j.enbuild.2026.117038","url":null,"abstract":"<div><div>Automated shading can curb building energy use; however, its performance depends on the control strategy design. This study quantified how state variable, dynamicity level, and adaptation horizon shape end-use savings and visual comfort. and formulated static and dynamic rule-based strategies for exterior slat-type blinds that track the solar horizontal profile angle (SHPA). Both schemes were tuned monthly or annually. The candidate state variables include direct solar irradiance, outdoor temperature, and indoor temperature. We simulated the total energy loads (cooling, heating, and lighting) and operational behavior (mode duration and switching frequency) for the perimeter zones across the orientations. Monthly optimized static control achieved 39–41% total-load savings vs. a no-control baseline and outperformed a fixed 90° reference with dimming (∼29%). Dynamic SHPA tracking offers marginal energy gains (<≈1 percentage point) but incurs orders-of-magnitude higher switching frequency. Hourly analysis showed that neither the slat modulation level nor state variable choice produced load savings because the shaded areas controlled by the strategies were not significantly different. Monthly tuning outperformed annual optimized cases by ∼ 12 percentage points, reflecting seasonal non-stationarity in sun geometry and weather. This indicates that the adaptation time interval is critical in rule-based shading control. Finally, visual comfort of static controls remained acceptable; hours with visual discomfort (daylight glare index > 22) were < 3% in every zone. Overall, these findings provide a practical guideline: use optimized static rules as the default approach and select the adaptation timescale according to local climate variability, while aligning shading system design with the proposed control framework.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"356 ","pages":"Article 117038"},"PeriodicalIF":7.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146033360","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}

引用次数: 0

Linear temperature model for rapid prediction of multi-scale urban thermal environments toward climate-resilient city design 面向气候适应型城市设计的多尺度城市热环境快速预测线性温度模型

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-04-01 Epub Date: 2026-02-04 DOI: 10.1016/j.enbuild.2026.117117

Chen Ren , Hao-Cheng Zhu , Shi-Jie Cao

Urban heat island (UHI) effects, intensified by global climate change and rapid urbanization, significantly elevate urban air temperatures. This phenomenon leads to substantial increases in building energy consumption, aggravated urban carbon emission, and raised public health risks under extreme heat. Facing these multifaceted challenges, there is a pressing need to develop accurate and efficient tools for predicting non-uniform urban thermal environment to support the UHI mitigation towards climate-resilient city design. High-resolution computational fluid dynamics (CFD) required large expenses for practical application, prompting the exploration of alternative approach such as machine learning. Nevertheless, these data-driven methods still encounter challenge in extensive training data requirement and limited physical interpretability. To address these gaps, this study develops a linear temperature model (LTM) to rapidly predict urban temperature distributions by linear superposition of pre-computed thermal contributions from heat sources. The prediction model is systematically validated across three representative test cases at different urban scales, i.e., an isolated building, a neighborhood, and a real street block. Results showed that by largely improving computational efficiency, the LTM maintained high prediction accuracy in terms of mean absolute error (MAE), root mean square error (RMSE), and mean relative error (MRE). Compared to CFD simulations, the LTM achieved good prediction precision at the building scale (MAE = 0.11°C, RMSE = 0.22°C, MRE = 0.28%), the neighborhood scale (MAE = 0.12°C, RMSE = 0.17°C, MRE = 0.31%), and the street block scale (MAE = 0.29°C, RMSE = 0.41°C, MRE = 0.84%). This model can provide urban planners, designers as well as policymakers with a practical tool for rapid thermal impact assessment, thereby guiding the development of UHI mitigation and climate-resilient design strategies.

全球气候变化和快速城市化加剧了城市热岛效应，显著提高了城市气温。这一现象导致建筑能耗大幅增加，加剧了城市碳排放，增加了极端高温下的公共健康风险。面对这些多方面的挑战，迫切需要开发准确和有效的工具来预测不均匀的城市热环境，以支持缓解城市热岛影响，实现气候适应型城市设计。高分辨率计算流体动力学（CFD）在实际应用中需要大量的费用，这促使人们探索机器学习等替代方法。然而，这些数据驱动的方法仍然面临着大量训练数据需求和有限的物理可解释性的挑战。为了解决这些差距，本研究开发了一个线性温度模型（LTM），通过预先计算的热源热贡献的线性叠加来快速预测城市温度分布。该预测模型在三个不同城市尺度的代表性测试案例中进行了系统验证，即一个孤立的建筑，一个社区和一个真实的街道街区。结果表明，通过大幅提高计算效率，LTM在平均绝对误差（MAE）、均方根误差（RMSE）和平均相对误差（MRE）方面保持了较高的预测精度。与CFD模拟相比，LTM在建筑尺度（MAE = 0.11°C, RMSE = 0.22°C, MRE = 0.28%）、邻域尺度（MAE = 0.12°C, RMSE = 0.17°C, MRE = 0.31%）和街区尺度（MAE = 0.29°C, RMSE = 0.41°C, MRE = 0.84%）均取得了较好的预测精度。该模型可为城市规划者、设计师和决策者提供快速热影响评估的实用工具，从而指导城市热岛缓解和气候适应型设计战略的制定。

{"title":"Linear temperature model for rapid prediction of multi-scale urban thermal environments toward climate-resilient city design","authors":"Chen Ren , Hao-Cheng Zhu , Shi-Jie Cao","doi":"10.1016/j.enbuild.2026.117117","DOIUrl":"10.1016/j.enbuild.2026.117117","url":null,"abstract":"<div><div>Urban heat island (UHI) effects, intensified by global climate change and rapid urbanization, significantly elevate urban air temperatures. This phenomenon leads to substantial increases in building energy consumption, aggravated urban carbon emission, and raised public health risks under extreme heat. Facing these multifaceted challenges, there is a pressing need to develop accurate and efficient tools for predicting non-uniform urban thermal environment to support the UHI mitigation towards climate-resilient city design. High-resolution computational fluid dynamics (CFD) required large expenses for practical application, prompting the exploration of alternative approach such as machine learning. Nevertheless, these data-driven methods still encounter challenge in extensive training data requirement and limited physical interpretability. To address these gaps, this study develops a linear temperature model (LTM) to rapidly predict urban temperature distributions by linear superposition of pre-computed thermal contributions from heat sources. The prediction model is systematically validated across three representative test cases at different urban scales, i.e., an isolated building, a neighborhood, and a real street block. Results showed that by largely improving computational efficiency, the LTM maintained high prediction accuracy in terms of mean absolute error (MAE), root mean square error (RMSE), and mean relative error (MRE). Compared to CFD simulations, the LTM achieved good prediction precision at the building scale (MAE = 0.11°C, RMSE = 0.22°C, MRE = 0.28%), the neighborhood scale (MAE = 0.12°C, RMSE = 0.17°C, MRE = 0.31%), and the street block scale (MAE = 0.29°C, RMSE = 0.41°C, MRE = 0.84%). This model can provide urban planners, designers as well as policymakers with a practical tool for rapid thermal impact assessment, thereby guiding the development of UHI mitigation and climate-resilient design strategies.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"356 ","pages":"Article 117117"},"PeriodicalIF":7.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146186341","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}

引用次数: 0

Intelligence-based prediction of coefficient of performance for a novel high-temperature industrial heat pump: Comparative performance of ANN and ANFIS models 基于智能的新型高温工业热泵性能系数预测：人工神经网络模型与ANFIS模型的性能比较

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-04-01 Epub Date: 2026-01-30 DOI: 10.1016/j.enbuild.2026.117078

Iman Golpour , José Daniel Marcos , Rubén Barbero , Antonio Rovira , Alex Butean , Arne Høeg

This study presents a comparative evaluation of the artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) approaches for predicting the coefficient of performance (COP) of the HoegTemp, a high-temperature heat pump (HTHP) based on a Stirling cycle (SC) with a design heat capacity of 400 kW. Experimental tests were conducted at the IVAR biogas facility in Stavanger, Norway. This study employed a feedforward backpropagation neural network (FFBPNN) model with one and two hidden layers, with various numbers of neurons and three activation functions, as well as the ANFIS approach, to estimate the COP of the SC-HTHP. The FFBPNN model used the Levenberg-Marquardt (LM) and Bayesian regularization (BR) training algorithms, while the ANFIS model utilized a hybrid optimization method and grid partitioning. The ANN and ANFIS models were evaluated using the following input variables: temperature ratio (1.4–1.6 K/K), average source temperature (21–22 °C), average sink temperature (139–199 °C) and hot water inlet temperature (137–197 °C), with COP as the output variable. The results demonstrated that the FFBP-ANN model exhibited superior predictive accuracy compared to the ANFIS model, achieving R² = 0.9999, MSE = 0.00010, MAE = 0.00804, and RMSE = 0.01000, whereas the ANFIS approach resulted in R² = 0.9863, MSE = 0.00019, MAE = 0.01114, and RMSE = 0.01392. The optimal ANN topology was 4–23-16–1 with tansig–logsig–purelin activation functions. In contrast, the best membership functions selected for ANFIS were Gaussian for the input layer and constant for the output layer.

本研究比较了人工神经网络（ANN）和自适应神经模糊推理系统（ANFIS）两种方法对设计热容量为400 kW的高温热泵HoegTemp的性能系数（COP）的预测。在挪威斯塔万格的IVAR沼气设施进行了实验测试。本研究采用一层和两层隐层、不同数量神经元和三种激活函数的前馈反向传播神经网络（FFBPNN）模型，以及ANFIS方法来估计SC-HTHP的COP。FFBPNN模型采用Levenberg-Marquardt （LM）和Bayesian正则化（BR）训练算法，而ANFIS模型采用混合优化方法和网格划分。ANN和ANFIS模型使用以下输入变量进行评估：温度比（1.4-1.6 K/K）、平均源温度（21-22℃）、平均汇温度（139-199℃）和热水进口温度（137-197℃），COP为输出变量。结果表明，与ANFIS模型相比，FFBP-ANN模型的预测精度更高，R2 = 0.9999, MSE = 0.00010, MAE = 0.00804, RMSE = 0.01000，而ANFIS方法的预测精度为R2 = 0.9863, MSE = 0.00019, MAE = 0.01114, RMSE = 0.01392。最优ANN拓扑为4-23-16-1，具有tansg - log - purelin激活函数。相比之下，ANFIS选择的最佳隶属函数为输入层的高斯函数和输出层的常数函数。

{"title":"Intelligence-based prediction of coefficient of performance for a novel high-temperature industrial heat pump: Comparative performance of ANN and ANFIS models","authors":"Iman Golpour , José Daniel Marcos , Rubén Barbero , Antonio Rovira , Alex Butean , Arne Høeg","doi":"10.1016/j.enbuild.2026.117078","DOIUrl":"10.1016/j.enbuild.2026.117078","url":null,"abstract":"<div><div>This study presents a comparative evaluation of the artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) approaches for predicting the coefficient of performance (COP) of the HoegTemp, a high-temperature heat pump (HTHP) based on a Stirling cycle (SC) with a design heat capacity of 400 kW. Experimental tests were conducted at the IVAR biogas facility in Stavanger, Norway. This study employed a feedforward backpropagation neural network (FFBPNN) model with one and two hidden layers, with various numbers of neurons and three activation functions, as well as the ANFIS approach, to estimate the COP of the SC-HTHP. The FFBPNN model used the Levenberg-Marquardt (LM) and Bayesian regularization (BR) training algorithms, while the ANFIS model utilized a hybrid optimization method and grid partitioning. The ANN and ANFIS models were evaluated using the following input variables: temperature ratio (1.4–1.6 K/K), average source temperature (21–22 °C), average sink temperature (139–199 °C) and hot water inlet temperature (137–197 °C), with COP as the output variable. The results demonstrated that the FFBP-ANN model exhibited superior predictive accuracy compared to the ANFIS model, achieving R<sup>2</sup> = 0.9999, MSE = 0.00010, MAE = 0.00804, and RMSE = 0.01000, whereas the ANFIS approach resulted in R<sup>2</sup> = 0.9863, MSE = 0.00019, MAE = 0.01114, and RMSE = 0.01392. The optimal ANN topology was 4–23-16–1 with tansig–logsig–purelin activation functions. In contrast, the best membership functions selected for ANFIS were Gaussian for the input layer and constant for the output layer.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"356 ","pages":"Article 117078"},"PeriodicalIF":7.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146089314","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}

引用次数: 0

Optimized lime-based renders with Phase Changing Materials (PCMs) for energy-efficient and climate resilient traditional and contemporary structures 优化石灰基渲染与相变材料（PCMs）的节能和气候弹性的传统和现代结构

IF 7.1 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2026-04-01 Epub Date: 2026-01-30 DOI: 10.1016/j.enbuild.2026.117069

Magdalini Theodoridou , Loucas Kyriakou , Ioannis Ioannou

Improving building energy efficiency is a top priority for the European Union. Member States take measures to encourage property owners to enhance thermal performance and reduce heating and cooling demands. Conventional thermal insulating materials, such as expanded or extruded polystyrene, remain widely used but present drawbacks, such as thermal bridging, imposition of additional loads on the structures and increased building envelope thickness. Hence, alternative solutions are continuously being sought. This experimental study focuses on developing innovative, smart, cementless renders, enhanced with Phase Changing Materials (PCMs), tailored for traditional and contemporary structures in southern Europe. Following a parametric analysis, a series of PCM-enhanced lime composites were designed and assessed for their thermal and physico-mechanical properties. Accelerated weathering tests were also carried out to investigate the durability of the new end-products against salt crystallization, which is critical for restoration and renovation projects. The addition of PCMs at 5% w/w of the binder and aggregates resulted in the optimum performance, considering the experimentally determined thermal, physico-mechanical and durability properties of the end-products. The results confirm that PCMs indeed have the potential to enhance the thermal efficiency of lime-based composites, while careful mix design may allow for tailored selection of end-products based on specific needs. Future market adoption of PCM-enhanced renders is expected to contribute to lower energy consumption, supporting the EU’s strategic goals for energy-efficient and climate-resilient structures.

提高建筑能源效率是欧盟的首要任务。会员国采取措施，鼓励业主提高热力性能，减少供热和制冷需求。传统的隔热材料，如膨胀或挤压聚苯乙烯，仍然被广泛使用，但存在缺点，如热桥接，对结构施加额外载荷和增加建筑围护结构厚度。因此，人们不断寻求其他解决办法。这项实验研究的重点是开发创新的、智能的、无水泥的渲染，用相变材料（PCMs）增强，为南欧的传统和当代建筑量身定制。通过参数分析，设计了一系列pcm增强石灰复合材料，并对其热性能和物理力学性能进行了评估。还进行了加速风化试验，以调查新的最终产品抗盐结晶的耐久性，这对修复和翻新项目至关重要。考虑到实验确定的最终产品的热、物理机械和耐久性性能，以5% w/w的粘结剂和骨料添加PCMs可获得最佳性能。结果证实，pcm确实有潜力提高石灰基复合材料的热效率，而仔细的混合设计可能允许根据特定需求定制最终产品。未来市场对pcm增强型渲染的采用预计将有助于降低能耗，支持欧盟节能和气候适应性结构的战略目标。

{"title":"Optimized lime-based renders with Phase Changing Materials (PCMs) for energy-efficient and climate resilient traditional and contemporary structures","authors":"Magdalini Theodoridou , Loucas Kyriakou , Ioannis Ioannou","doi":"10.1016/j.enbuild.2026.117069","DOIUrl":"10.1016/j.enbuild.2026.117069","url":null,"abstract":"<div><div>Improving building energy efficiency is a top priority for the European Union. Member States take measures to encourage property owners to enhance thermal performance and reduce heating and cooling demands. Conventional thermal insulating materials, such as expanded or extruded polystyrene, remain widely used but present drawbacks, such as thermal bridging, imposition of additional loads on the structures and increased building envelope thickness. Hence, alternative solutions are continuously being sought. This experimental study focuses on developing innovative, smart, cementless renders, enhanced with Phase Changing Materials (PCMs), tailored for traditional and contemporary structures in southern Europe. Following a parametric analysis, a series of PCM-enhanced lime composites were designed and assessed for their thermal and physico-mechanical properties. Accelerated weathering tests were also carried out to investigate the durability of the new end-products against salt crystallization, which is critical for restoration and renovation projects. The addition of PCMs at 5% w/w of the binder and aggregates resulted in the optimum performance, considering the experimentally determined thermal, physico-mechanical and durability properties of the end-products. The results confirm that PCMs indeed have the potential to enhance the thermal efficiency of lime-based composites, while careful mix design may allow for tailored selection of end-products based on specific needs. Future market adoption of PCM-enhanced renders is expected to contribute to lower energy consumption, supporting the EU’s strategic goals for energy-efficient and climate-resilient structures.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"356 ","pages":"Article 117069"},"PeriodicalIF":7.1,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146089313","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}

引用次数: 0