Energy and Buildings最新文献_第9页

Interpreting environmental impacts of wooden windows based on existing EPDs: An application in Italy 根据现有 EPD 解释木窗对环境的影响：在意大利的应用

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2024-11-06 DOI: 10.1016/j.enbuild.2024.114987

Victor Marinello Jorba , Elisabetta Palumbo , Pamela del Rosario , Marzia Traverso

To meet climate targets, it is necessary to adopt robust and recognized methods, such as life cycle assessment (LCA), to evaluate emissions, particularly from building materials. As shown in the literature, embodied impacts have become as significant as operational impacts. The embodied impacts of a specific product are given in a transparent and quantitative manner in environmental product declarations (EPDs), based on LCA results. Windows play a crucial role in the energy performance of buildings. In fact, they typically account for 10–25 % of the exposed area of a building, resulting in more than 60 % of its total energy loss. In Italy, wooden windows make up 28 % of the window market and are the cheapest option for mild climates over a timeline of 60 years. However, an important element is still missing: a simplified interpretation of EPD results to enable straightforward, balanced comparisons of the environmental performance between alternatives. In this context, an analysis based EPDs of wooden windows is proposed, with a focus on production and use stages, for the six Italian climate zones. The three main steps of the study are: 1) evaluation of the influence of window properties on the embedded impacts; 2) assessment of maintenance scenarios; and 3) estimation of operational impacts regarding window properties and exposed climate. The results suggest that the influence of thermal transmittance, wood type and exposed climate is higher for cold climates due to better performing production materials and more frequent maintenance during service life.

为了实现气候目标，有必要采用可靠且公认的方法，如生命周期评估（LCA），来评估排放，尤其是建筑材料的排放。如文献所示，内含影响已变得与运行影响同等重要。根据生命周期评估的结果，在环境产品声明（EPD）中以透明和量化的方式给出了特定产品的内含影响。窗户在建筑节能方面发挥着至关重要的作用。事实上，窗户通常占建筑物外露面积的 10-25%，造成的能量损失占建筑物总能量损失的 60%以上。在意大利，木窗占窗户市场的 28%，在气候温和的地区，木窗是最便宜的选择，使用寿命长达 60 年。然而，目前仍缺少一个重要因素：简化 EPD 结果的解释，以便对不同替代品的环保性能进行直接、平衡的比较。在此背景下，我们提出了一项基于木窗 EPD 的分析，重点是意大利六个气候区的生产和使用阶段。研究的三个主要步骤是1) 评估窗户特性对嵌入式影响的影响；2) 评估维护方案；3) 估算窗户特性和暴露气候对运行的影响。研究结果表明，在寒冷气候条件下，由于生产材料性能更好以及在使用寿命期间维护更频繁，热透射率、木材类型和暴露气候的影响更大。

{"title":"Interpreting environmental impacts of wooden windows based on existing EPDs: An application in Italy","authors":"Victor Marinello Jorba , Elisabetta Palumbo , Pamela del Rosario , Marzia Traverso","doi":"10.1016/j.enbuild.2024.114987","DOIUrl":"10.1016/j.enbuild.2024.114987","url":null,"abstract":"<div><div>To meet climate targets, it is necessary to adopt robust and recognized methods, such as life cycle assessment (LCA), to evaluate emissions, particularly from building materials. As shown in the literature, embodied impacts have become as significant as operational impacts. The embodied impacts of a specific product are given in a transparent and quantitative manner in environmental product declarations (EPDs), based on LCA results. Windows play a crucial role in the energy performance of buildings. In fact, they typically account for 10–25 % of the exposed area of a building, resulting in more than 60 % of its total energy loss. In Italy, wooden windows make up 28 % of the window market and are the cheapest option for mild climates over a timeline of 60 years. However, an important element is still missing: a simplified interpretation of EPD results to enable straightforward, balanced comparisons of the environmental performance between alternatives. In this context, an analysis based EPDs of wooden windows is proposed, with a focus on production and use stages, for the six Italian climate zones. The three main steps of the study are: 1) evaluation of the influence of window properties on the embedded impacts; 2) assessment of maintenance scenarios; and 3) estimation of operational impacts regarding window properties and exposed climate. The results suggest that the influence of thermal transmittance, wood type and exposed climate is higher for cold climates due to better performing production materials and more frequent maintenance during service life.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"326 ","pages":"Article 114987"},"PeriodicalIF":6.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A hybrid forecasting model for general hospital electricity consumption based on mixed signal decomposition 基于混合信号分解的综合医院用电混合预测模型

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2024-11-06 DOI: 10.1016/j.enbuild.2024.115006

Anjun Zhao , Mengya Chen , Wei Quan , Sijia Zhang

Current research into electricity consumption forecasting for General Hospital still has considerable scope for further development, particularly in its failure to incorporate hospital-specific energy usage characteristics as input variables. This study explores the impact of the usage frequency of sizeable medical equipment on the electricity demand of general hospitals. It proposes a hybrid forecasting algorithm that integrates the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Variational Mode Decomposition (VMD) for signal decomposition with the Hyperband-LSTM deep learning algorithm to enhance prediction accuracy. ICEEMDAN is employed for preprocessing the power consumption series, while VMD is used for the secondary decomposition of high-frequency signals within the series. The Hyperband Pruner is utilized to efficiently adjust the hyperparameters of the LSTM, which is then used for electricity consumption forecasting. The predictive performance of the developed method is assessed by comparing it with 15 different forecasting models. The results indicate that the proposed method demonstrates superior forecasting performance. Applying the model to a real-case scenario, it has reduced the hospital’s electricity consumption by about 15%, providing a referable energy management solution for other medical institutions.

目前对综合医院用电预测的研究仍有很大的发展空间，特别是未能将医院的特定能源使用特征作为输入变量。本研究探讨了大型医疗设备的使用频率对综合医院用电需求的影响。它提出了一种混合预测算法，将用于信号分解的自适应噪声改进型完全集合经验模式分解（ICEEMDAN）和变异模式分解（VMD）与超宽带-LSTM 深度学习算法相结合，以提高预测精度。ICEEMDAN 用于预处理功耗序列，而 VMD 则用于对序列中的高频信号进行二次分解。利用超带剪枝器有效调整 LSTM 的超参数，然后将其用于用电量预测。通过与 15 种不同的预测模型进行比较，对所开发方法的预测性能进行了评估。结果表明，所提出的方法具有卓越的预测性能。将该模型应用到实际情况中，医院的用电量减少了约 15%，为其他医疗机构提供了可参考的能源管理解决方案。

{"title":"A hybrid forecasting model for general hospital electricity consumption based on mixed signal decomposition","authors":"Anjun Zhao , Mengya Chen , Wei Quan , Sijia Zhang","doi":"10.1016/j.enbuild.2024.115006","DOIUrl":"10.1016/j.enbuild.2024.115006","url":null,"abstract":"<div><div>Current research into electricity consumption forecasting for General Hospital still has considerable scope for further development, particularly in its failure to incorporate hospital-specific energy usage characteristics as input variables. This study explores the impact of the usage frequency of sizeable medical equipment on the electricity demand of general hospitals. It proposes a hybrid forecasting algorithm that integrates the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Variational Mode Decomposition (VMD) for signal decomposition with the Hyperband-LSTM deep learning algorithm to enhance prediction accuracy. ICEEMDAN is employed for preprocessing the power consumption series, while VMD is used for the secondary decomposition of high-frequency signals within the series. The Hyperband Pruner is utilized to efficiently adjust the hyperparameters of the LSTM, which is then used for electricity consumption forecasting. The predictive performance of the developed method is assessed by comparing it with 15 different forecasting models. The results indicate that the proposed method demonstrates superior forecasting performance. Applying the model to a real-case scenario, it has reduced the hospital’s electricity consumption by about 15%, providing a referable energy management solution for other medical institutions.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"325 ","pages":"Article 115006"},"PeriodicalIF":6.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661229","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

Building performance optimization through sensitivity Analysis, and economic insights using AI 通过灵敏度分析优化楼宇性能，利用人工智能洞察经济形势

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2024-11-06 DOI: 10.1016/j.enbuild.2024.114999

Haidar Hosamo , Guilherme B. A. Coelho , Christian Nordahl Rolfsen , Dimitrios Kraniotis

Optimizing building designs for energy efficiency and occupant comfort presents significant challenges due to the complex and often conflicting requirements of various stakeholders. Consequently, this study conducts a multifaceted sensitivity and economic impact analysis that aims to improve building performance in terms of energy efficiency and occupant comfort by implementing machine learning techniques. Using a broad dataset comprising of 12,000 energy simulation runs for Tvedestrand Upper Secondary School in Norway, several machine learning models were employed with Multi-Layer Perceptron outperforming the others. In addition, several sensitivity analysis methods were used to explore the influence of individual parameters on building performance. The analysis reveals that ventilation rate, room depth, U-value of the facade, and heat gains significantly affect energy consumption. Economic impact analysis was also carried out to compare the cost-effectiveness of traditional HVAC systems with Building Management System (BMS) HVAC solutions. The BMS HVAC system shows significantly lower operational costs over time, with investment costs averaging around 1200 Norwegian kroner (NOK)/m² and operational costs of approximately 150 NOK/m² per year. Sensitivity analysis under different economic scenarios highlights the economic viability of the BMS HVAC system. This study identifies optimal building parameters that balance energy efficiency and thermal comfort, achieving total energy consumption between 11.05 and 22.51 kWh/m² and zero discomfort hours (h > 26 °C). In sum, the findings offer valuable insights for stakeholders, enabling informed decisions about sustainable building design and energy efficiency improvements, ensuring both technical soundness and financial viability under a wide range of conditions, while using the tested tools.

由于各利益相关方的要求错综复杂，往往相互冲突，因此优化建筑设计以提高能效和居住舒适度面临着巨大挑战。因此，本研究进行了多方面的敏感性和经济影响分析，旨在通过采用机器学习技术，提高建筑在能效和居住舒适度方面的性能。通过对挪威 Tvedestrand 高级中学 12,000 次能源模拟运行的广泛数据集进行分析，采用了多种机器学习模型，其中多层感知器模型的性能优于其他模型。此外，还采用了几种敏感性分析方法，以探索各个参数对建筑性能的影响。分析结果表明，通风率、房间深度、外墙 U 值和热增益对能耗有显著影响。此外，还进行了经济影响分析，以比较传统暖通空调系统与楼宇管理系统（BMS）暖通空调解决方案的成本效益。随着时间的推移，BMS 暖通空调系统的运营成本明显降低，投资成本平均约为 1200 挪威克朗（NOK）/平方米，每年的运营成本约为 150 挪威克朗/平方米。在不同的经济情况下进行的敏感性分析凸显了 BMS 暖通空调系统的经济可行性。这项研究确定了平衡能源效率和热舒适度的最佳建筑参数，实现了 11.05 至 22.51 kWh/m2 的总能耗和零不适时间（26 °C）。总之，研究结果为利益相关者提供了宝贵的见解，使他们能够就可持续建筑设计和能效改进做出明智的决策，在使用测试工具的同时，确保在各种条件下的技术合理性和财务可行性。

{"title":"Building performance optimization through sensitivity Analysis, and economic insights using AI","authors":"Haidar Hosamo , Guilherme B. A. Coelho , Christian Nordahl Rolfsen , Dimitrios Kraniotis","doi":"10.1016/j.enbuild.2024.114999","DOIUrl":"10.1016/j.enbuild.2024.114999","url":null,"abstract":"<div><div>Optimizing building designs for energy efficiency and occupant comfort presents significant challenges due to the complex and often conflicting requirements of various stakeholders. Consequently, this study conducts a multifaceted sensitivity and economic impact analysis that aims to improve building performance in terms of energy efficiency and occupant comfort by implementing machine learning techniques. Using a broad dataset comprising of 12,000 energy simulation runs for Tvedestrand Upper Secondary School in Norway, several machine learning models were employed with Multi-Layer Perceptron outperforming the others. In addition, several sensitivity analysis methods were used to explore the influence of individual parameters on building performance. The analysis reveals that ventilation rate, room depth, U-value of the facade, and heat gains significantly affect energy consumption. Economic impact analysis was also carried out to compare the cost-effectiveness of traditional HVAC systems with Building Management System (BMS) HVAC solutions. The BMS HVAC system shows significantly lower operational costs over time, with investment costs averaging around 1200 Norwegian kroner (NOK)/m<sup>2</sup> and operational costs of approximately 150 NOK/m<sup>2</sup> per year. Sensitivity analysis under different economic scenarios highlights the economic viability of the BMS HVAC system. This study identifies optimal building parameters that balance energy efficiency and thermal comfort, achieving total energy consumption between 11.05 and 22.51 kWh/m<sup>2</sup> and zero discomfort hours (h > 26 °C). In sum, the findings offer valuable insights for stakeholders, enabling informed decisions about sustainable building design and energy efficiency improvements, ensuring both technical soundness and financial viability under a wide range of conditions, while using the tested tools.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"325 ","pages":"Article 114999"},"PeriodicalIF":6.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A recommendation model for optimizing transfer learning hyper-parameter settings in building heat load prediction with limited data samples 在数据样本有限的建筑物热负荷预测中优化迁移学习超参数设置的推荐模型

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2024-11-06 DOI: 10.1016/j.enbuild.2024.115021

Di Bai , Shuo Ma , Xiaochen Yang , Dandan Ma , Xiaoyu Ma , Hongting Ma

The transfer learning method has gained increasing attention in the domain of building load prediction, particularly in scenarios with limited data samples. Its core principle involves leveraging knowledge obtained from abundant data in source buildings to aid the learning process of models for the target buildings. Existing research has predominantly concentrated on optimizing the selection of source building data to improve transfer learning effectiveness, while the optimization of transfer learning hyper-parameter settings is often neglected. This study proposes a recommendation model tailored for transfer learning hyper-parameter settings in the context of small sample prediction for building heat loads. The objective is to automatically suggest suitable transfer learning hyper-parameter combination based on the specific features of the building heat load data samples. In this study, 200 real building profiles were utilized to generate the input–output dataset required for the recommendation model. By employing data mining techniques such as clustering and classification, the correlation between the features of source building data and the most effective transfer learning hyper-parameter combination is investigated. The developed recommendation model for optimal transfer learning hyper-parameter settings achieves a classification accuracy of 90.5%，and the performance evaluation was conducted using an additional dataset of 30 source buildings. The results show that by employing this recommendation model, the prediction error of the target buildings can be reduced by 0.12% to 6.64% compared to the conventional method of empirically determining transfer learning hyper-parameter settings.

迁移学习法在建筑负荷预测领域受到越来越多的关注，尤其是在数据样本有限的情况下。其核心原理是利用从源建筑的丰富数据中获取的知识来帮助目标建筑的模型学习过程。现有研究主要集中在优化源建筑数据的选择，以提高迁移学习的效果，而迁移学习超参数设置的优化往往被忽视。本研究针对建筑物热负荷的小样本预测，提出了一个专门针对迁移学习超参数设置的推荐模型。其目的是根据建筑物热负荷数据样本的具体特征，自动推荐合适的迁移学习超参数组合。在这项研究中，利用 200 个真实建筑剖面来生成推荐模型所需的输入输出数据集。通过采用聚类和分类等数据挖掘技术，研究了源建筑数据特征与最有效的转移学习超参数组合之间的相关性。所开发的最优迁移学习超参数设置推荐模型的分类准确率达到了 90.5%，并使用额外的 30 个源建筑数据集进行了性能评估。结果表明，与通过经验确定迁移学习超参数设置的传统方法相比，采用该推荐模型可将目标建筑物的预测误差降低 0.12% 至 6.64%。

{"title":"A recommendation model for optimizing transfer learning hyper-parameter settings in building heat load prediction with limited data samples","authors":"Di Bai , Shuo Ma , Xiaochen Yang , Dandan Ma , Xiaoyu Ma , Hongting Ma","doi":"10.1016/j.enbuild.2024.115021","DOIUrl":"10.1016/j.enbuild.2024.115021","url":null,"abstract":"<div><div>The transfer learning method has gained increasing attention in the domain of building load prediction, particularly in scenarios with limited data samples. Its core principle involves leveraging knowledge obtained from abundant data in source buildings to aid the learning process of models for the target buildings. Existing research has predominantly concentrated on optimizing the selection of source building data to improve transfer learning effectiveness, while the optimization of transfer learning hyper-parameter settings is often neglected. This study proposes a recommendation model tailored for transfer learning hyper-parameter settings in the context of small sample prediction for building heat loads. The objective is to automatically suggest suitable transfer learning hyper-parameter combination based on the specific features of the building heat load data samples. In this study, 200 real building profiles were utilized to generate the input–output dataset required for the recommendation model. By employing data mining techniques such as clustering and classification, the correlation between the features of source building data and the most effective transfer learning hyper-parameter combination is investigated. The developed recommendation model for optimal transfer learning hyper-parameter settings achieves a classification accuracy of 90.5%，and the performance evaluation was conducted using an additional dataset of 30 source buildings. The results show that by employing this recommendation model, the prediction error of the target buildings can be reduced by 0.12% to 6.64% compared to the conventional method of empirically determining transfer learning hyper-parameter settings.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"325 ","pages":"Article 115021"},"PeriodicalIF":6.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661221","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

Subjective information in thermal comfort evaluation methods: A critical review 热舒适度评估方法中的主观信息：批判性评论

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2024-11-06 DOI: 10.1016/j.enbuild.2024.115019

Yuxin Yang , Junmeng Lyu , Zhiwei Lian , Yongxin Xie , Ying Jiang , Junwei Lin , Jianlei Niu

Thermal environments hold significant importance in human living environments, affecting quality of life, work efficiency, and building energy consumption. Accurate evaluation of thermal comfort involves the quantification of subjective information and the establishment of indices and models. Although various thermal comfort evaluation methods currently exist, the complexity of subjective emotions has often been overlooked. This review provides a comprehensive analysis of the underlying purposes and logic behind different thermal comfort evaluation methods, focusing on the intricacies of subjective information. It emphasizes that while substantial studies have already demonstrated that thermal sensation alone is insufficient for evaluating thermal environments in different contexts, there is still an overreliance on thermal sensation by various indices and models. By critically reviewing the role of subjective information in these methods, this review aims to promote the healthy development of thermal comfort evaluation.

热环境在人类生活环境中具有重要意义，影响着生活质量、工作效率和建筑能耗。要对热舒适度进行准确评估，就必须对主观信息进行量化，并建立相关指数和模型。尽管目前存在各种热舒适度评估方法，但主观情绪的复杂性往往被忽视。本综述全面分析了不同热舒适度评价方法背后的基本目的和逻辑，重点关注主观信息的复杂性。它强调，虽然大量研究已经证明，仅凭热感觉不足以评估不同环境下的热环境，但各种指数和模型仍然过度依赖热感觉。通过对主观信息在这些方法中的作用进行严格审查，本综述旨在促进热舒适度评估的健康发展。

引用次数: 0

Cross-condition fault diagnosis of chillers based on an ensemble approach with adaptive weight allocation 基于自适应权重分配的集合方法的冷却器跨工况故障诊断

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2024-11-05 DOI: 10.1016/j.enbuild.2024.115007

Zhen Chen , Wei Zhang , Wanqing Zhao , Xuebin Yang , Xingxing Zhang , Yu Li

The Heating, Ventilation and Air Conditioning (HVAC) systems are complex and prone to failures during operation, often leading to significant energy waste. Timely and accurate Fault Detection and Diagnosis (FDD) can enhance energy efficiency. The HVAC system operates under diverse conditions, data-driven models trained under existing conditions may experience performance degradation when faced with new conditions. Transfer learning offers an effective solution to this issue. This study proposes a novel transfer learning ensemble model based on adaptive weights, leveraging different transfer learning strategies to improve diagnosis performance under new conditions. Multiple cross-condition transfer learning tasks were implemented to test the proposed method, and its effectiveness was validated through multiple experiments to minimize the impact of randomness. Results showed that, compared to fine-tuning (FT), domain-adversarial neural network (DANN), and baseline models, the proposed method outperforms the other models. The average accuracy of multiple experiments improved by 0.21 % to 2.34 % compared to FT. Additionally, modifying DANN to utilize a small amount of labeled information from the target domain has led to greater overlap between the feature distributions of the source and target domains, resulting in improved performance that is close to that of FT. Finally, we analyzed the impact of target domain data volume on the performance of the four methods. The performance of the baseline model improved significantly with the increase in data volume, while the other models showed less improvement. Meanwhile, the diagnostic results of the baseline model were significantly influenced by experimental randomness when there is less training data, whereas the FT diagnostic results were relatively more stable.

供暖、通风和空调（HVAC）系统十分复杂，在运行过程中很容易出现故障，往往会造成大量能源浪费。及时准确的故障检测和诊断（FDD）可以提高能源效率。暖通空调系统的运行条件多种多样，在现有条件下训练的数据驱动模型在面对新条件时可能会出现性能下降。迁移学习为这一问题提供了有效的解决方案。本研究提出了一种基于自适应权重的新型迁移学习集合模型，利用不同的迁移学习策略来提高新条件下的诊断性能。为了测试所提出的方法，我们执行了多个跨条件迁移学习任务，并通过多次实验验证了该方法的有效性，以尽量减少随机性的影响。结果表明，与微调（FT）、域对抗神经网络（DANN）和基线模型相比，所提出的方法优于其他模型。与 FT 相比，多次实验的平均准确率提高了 0.21 % 至 2.34 %。此外，修改 DANN 以利用来自目标域的少量标记信息，使得源域和目标域的特征分布有了更大的重叠，从而提高了性能，接近 FT 的性能。最后，我们分析了目标域数据量对四种方法性能的影响。随着数据量的增加，基线模型的性能显著提高，而其他模型的性能提高幅度较小。同时，当训练数据较少时，基线模型的诊断结果受实验随机性的影响较大，而 FT 诊断结果相对更稳定。

{"title":"Cross-condition fault diagnosis of chillers based on an ensemble approach with adaptive weight allocation","authors":"Zhen Chen , Wei Zhang , Wanqing Zhao , Xuebin Yang , Xingxing Zhang , Yu Li","doi":"10.1016/j.enbuild.2024.115007","DOIUrl":"10.1016/j.enbuild.2024.115007","url":null,"abstract":"<div><div>The Heating, Ventilation and Air Conditioning (HVAC) systems are complex and prone to failures during operation, often leading to significant energy waste. Timely and accurate Fault Detection and Diagnosis (FDD) can enhance energy efficiency. The HVAC system operates under diverse conditions, data-driven models trained under existing conditions may experience performance degradation when faced with new conditions. Transfer learning offers an effective solution to this issue. This study proposes a novel transfer learning ensemble model based on adaptive weights, leveraging different transfer learning strategies to improve diagnosis performance under new conditions. Multiple cross-condition transfer learning tasks were implemented to test the proposed method, and its effectiveness was validated through multiple experiments to minimize the impact of randomness. Results showed that, compared to fine-tuning (FT), domain-adversarial neural network (DANN), and baseline models, the proposed method outperforms the other models. The average accuracy of multiple experiments improved by 0.21 % to 2.34 % compared to FT. Additionally, modifying DANN to utilize a small amount of labeled information from the target domain has led to greater overlap between the feature distributions of the source and target domains, resulting in improved performance that is close to that of FT. Finally, we analyzed the impact of target domain data volume on the performance of the four methods. The performance of the baseline model improved significantly with the increase in data volume, while the other models showed less improvement. Meanwhile, the diagnostic results of the baseline model were significantly influenced by experimental randomness when there is less training data, whereas the FT diagnostic results were relatively more stable.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"325 ","pages":"Article 115007"},"PeriodicalIF":6.6,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661227","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

Enhancing indoor light and thermal performance with micro-prismatic materials for complex fenestration systems: A review 使用微棱镜材料提高复杂幕墙系统的室内光热性能：综述

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2024-11-05 DOI: 10.1016/j.enbuild.2024.115002

Xuran Guo , Zhen Tian , Yongqing Zhao , David Geisler-Moroder , Martin Hauer

Creating high performance buildings is crucial not only for energy conservation but also for enhancing indoor comfort and well-being of occupants. Complex Fenestration Systems (CFS) can modulate daylight and/or solar radiation, thereby improving the quality of indoor light and thermal environments. This paper provided a comprehensive review of the application of micro-prismatic materials (MiPMs) in CFS, analyzing and summarizing the design, manufacturing, evaluation methods, case studies, and implementation framework of MiPMs. The effectiveness of MiPMs in enhancing indoor light and thermal performance was analyzed and the limitations and future research directions of these materials were discussed. The review suggested that using mathematical models and algorithms to design the prismatic structure parameters could be an efficient approach. Integrating other materials or technologies and incorporating dynamic control could significantly further enhance the optimized performance of MiPMs. Ultra-precision machining is the core manufacturing technology for MiPMs, and the use of recycled materials may offer a more sustainable approach for material production. Through characterization via bidirectional scattering distribution functions (BSDF) and the ability to generate the data using goniophotometers or simulation tools, computer simulation can act as a time-efficient, and accurate method for performance evaluation of MiPMs. A summarized roadmap may help building owners and architects more effectively apply MiPMs in their projects. Future work might focus on enhancing product quality and weather resistance, standardizing test and simulation work, developing accurate and integrated analysis methods, and exploring integration of MiPMs with building integrated photovoltaic (BIPV) systems.

创建高性能建筑不仅对节约能源至关重要，而且对提高室内舒适度和居住者的幸福感也至关重要。复合幕墙系统（CFS）可以调节日光和/或太阳辐射，从而改善室内光和热环境质量。本文全面综述了微棱镜材料（MiPM）在复合幕墙系统中的应用，分析并总结了微棱镜材料的设计、制造、评估方法、案例研究和实施框架。分析了微棱镜材料在提高室内光和热性能方面的有效性，并讨论了这些材料的局限性和未来研究方向。综述表明，使用数学模型和算法设计棱柱结构参数可能是一种有效的方法。整合其他材料或技术并结合动态控制可进一步显著提高 MiPM 的优化性能。超精密加工是 MiPMs 的核心制造技术，而使用回收材料可能会为材料生产提供一种更具可持续性的方法。通过双向散射分布函数 (BSDF) 进行表征，并使用测角光度计或模拟工具生成数据，计算机模拟可以作为一种省时、准确的 MiPM 性能评估方法。总结出的路线图可以帮助建筑业主和建筑师更有效地在项目中应用 MiPM。未来的工作重点可能是提高产品质量和耐候性，规范测试和模拟工作，开发精确的综合分析方法，以及探索 MiPM 与光伏建筑一体化 (BIPV) 系统的整合。

{"title":"Enhancing indoor light and thermal performance with micro-prismatic materials for complex fenestration systems: A review","authors":"Xuran Guo , Zhen Tian , Yongqing Zhao , David Geisler-Moroder , Martin Hauer","doi":"10.1016/j.enbuild.2024.115002","DOIUrl":"10.1016/j.enbuild.2024.115002","url":null,"abstract":"<div><div>Creating high performance buildings is crucial not only for energy conservation but also for enhancing indoor comfort and well-being of occupants. Complex Fenestration Systems (CFS) can modulate daylight and/or solar radiation, thereby improving the quality of indoor light and thermal environments. This paper provided a comprehensive review of the application of micro-prismatic materials (MiPMs) in CFS, analyzing and summarizing the design, manufacturing, evaluation methods, case studies, and implementation framework of MiPMs. The effectiveness of MiPMs in enhancing indoor light and thermal performance was analyzed and the limitations and future research directions of these materials were discussed. The review suggested that using mathematical models and algorithms to design the prismatic structure parameters could be an efficient approach. Integrating other materials or technologies and incorporating dynamic control could significantly further enhance the optimized performance of MiPMs. Ultra-precision machining is the core manufacturing technology for MiPMs, and the use of recycled materials may offer a more sustainable approach for material production. Through characterization via bidirectional scattering distribution functions (BSDF) and the ability to generate the data using goniophotometers or simulation tools, computer simulation can act as a time-efficient, and accurate method for performance evaluation of MiPMs. A summarized roadmap may help building owners and architects more effectively apply MiPMs in their projects. Future work might focus on enhancing product quality and weather resistance, standardizing test and simulation work, developing accurate and integrated analysis methods, and exploring integration of MiPMs with building integrated photovoltaic (BIPV) systems.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"325 ","pages":"Article 115002"},"PeriodicalIF":6.6,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661285","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

Individual differences in acceptance of direct load control 接受直接负载控制的个体差异

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2024-11-05 DOI: 10.1016/j.enbuild.2024.115009

Stepan Vesely , Christian A. Klöckner

Consumer acceptance of direct load control is becoming increasingly important as energy systems transition towards greater reliance on intermittent renewable energy sources. The objective of this paper is to better understand the attitudinal and socio-economic determinants of direct load control acceptance. To do so, we collect survey data from participants in 31 European countries (N = 5,970). Regression analyses testing a comprehensive model of attitudinal and socio-economic determinants of direct load control acceptance reveal that attitudes and beliefs specific to direct load control acceptance (social and personal norms, anticipated emotions, and outcome efficacy beliefs) predict acceptance, whereas more general attitudinal variables and socio-economic characteristics play no or only a secondary role. These findings substantially improve our understanding of direct load control acceptance. While European policy documents recognize the importance of individual attitudes for the success of demand response programs, reference to specific factors or processes is often missing due to lack of evidence. The present research helps fill this gap, and can inform the design of novel soft policy measures – highlighting the usefulness of facilitating positive peer influence, of reinforcing perceptions that engaging in demand response is effective, is the responsible thing to do, and also something to be proud of.

随着能源系统向更加依赖间歇性可再生能源过渡，消费者对直接负荷控制的接受程度变得越来越重要。本文旨在更好地了解消费者接受直接负荷控制的态度和社会经济决定因素。为此，我们收集了 31 个欧洲国家参与者的调查数据（N = 5970）。回归分析测试了直接负载控制接受度的态度和社会经济决定因素的综合模型，结果显示，与直接负载控制接受度相关的态度和信念（社会和个人规范、预期情绪和结果效能信念）可以预测接受度，而更一般的态度变量和社会经济特征则不起作用或仅起次要作用。这些发现大大提高了我们对直接负荷控制接受度的理解。虽然欧洲的政策文件承认个人态度对需求响应计划成功的重要性，但由于缺乏证据，往往没有提及具体的因素或过程。本研究有助于填补这一空白，并为设计新颖的软性政策措施提供信息--强调促进积极的同伴影响、强化参与需求响应是有效的、是负责任的行为、也是值得骄傲的行为等观念的有用性。

{"title":"Individual differences in acceptance of direct load control","authors":"Stepan Vesely , Christian A. Klöckner","doi":"10.1016/j.enbuild.2024.115009","DOIUrl":"10.1016/j.enbuild.2024.115009","url":null,"abstract":"<div><div>Consumer acceptance of direct load control is becoming increasingly important as energy systems transition towards greater reliance on intermittent renewable energy sources. The objective of this paper is to better understand the attitudinal and socio-economic determinants of direct load control acceptance. To do so, we collect survey data from participants in 31 European countries (<em>N</em> = 5,970). Regression analyses testing a comprehensive model of attitudinal and socio-economic determinants of direct load control acceptance reveal that attitudes and beliefs specific to direct load control acceptance (social and personal norms, anticipated emotions, and outcome efficacy beliefs) predict acceptance, whereas more general attitudinal variables and socio-economic characteristics play no or only a secondary role. These findings substantially improve our understanding of direct load control acceptance. While European policy documents recognize the importance of individual attitudes for the success of demand response programs, reference to specific factors or processes is often missing due to lack of evidence. The present research helps fill this gap, and can inform the design of novel soft policy measures – highlighting the usefulness of facilitating positive peer influence, of reinforcing perceptions that engaging in demand response is effective, is the responsible thing to do, and also something to be proud of.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"325 ","pages":"Article 115009"},"PeriodicalIF":6.6,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ten differences of seasonal borehole thermal energy storage system from ground-source heat pump system 季节性钻孔蓄热系统与地源热泵系统的十大区别

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2024-11-03 DOI: 10.1016/j.enbuild.2024.114994

Xingwang Zhao , Yanwei Li , Xin Chen , Yonggao Yin

Since both the cross-seasonal borehole thermal energy storage (BTES) system and the ground source heat pump (GSHP) system use buried tubes for heat exchange, GSHP is often mistaken for a BTES system. However, there are essential differences between the GSHP system and the BTES system, and the purpose of this study is to elucidate in detail the differences between these two systems. This study first summarizes the practical application cases of seasonal BTES globally, and then deeply compares and analyzes the differences between the seasonal BTES system and GSHP system from ten different perspectives, including system definition, technology timeline, purpose of buried tube heat exchanger, heat sources, soil temperature changes, buried tube heat exchanger volume, design of the buried tube heat exchanger, energy storage modes, biggest drawback, system performance evaluation. Finally, the future development prospects and research directions of the seasonal BTES system are further discussed. In summary, although the GSHP system may be confused with the seasonal BTES system in some aspects, they are indeed two different systems. Compared to the GSHP system, the seasonal BTES system can solve the contradiction between energy supply and demand in time and space, and effectively improve energy utilization efficiency.

由于跨季节钻孔热能储存（BTES）系统和地源热泵（GSHP）系统都使用埋管进行热交换，GSHP 经常被误认为是 BTES 系统。然而，GSHP 系统与 BTES 系统之间存在本质区别，本研究的目的就是要详细阐明这两种系统之间的区别。本研究首先总结了全球范围内季节性 BTES 的实际应用案例，然后从系统定义、技术年限、地埋管换热器的用途、热源、土壤温度变化、地埋管换热器体积、地埋管换热器设计、储能模式、最大缺点、系统性能评估等十个方面深入对比分析了季节性 BTES 系统与 GSHP 系统的差异。最后，进一步讨论了季节性 BTES 系统的未来发展前景和研究方向。总之，尽管在某些方面，GSHP 系统与季节性 BTES 系统可能会被混淆，但它们确实是两种不同的系统。与 GSHP 系统相比，季节性 BTES 系统可以解决能源供需在时间和空间上的矛盾，有效提高能源利用效率。

{"title":"Ten differences of seasonal borehole thermal energy storage system from ground-source heat pump system","authors":"Xingwang Zhao , Yanwei Li , Xin Chen , Yonggao Yin","doi":"10.1016/j.enbuild.2024.114994","DOIUrl":"10.1016/j.enbuild.2024.114994","url":null,"abstract":"<div><div>Since both the cross-seasonal borehole thermal energy storage (BTES) system and the ground source heat pump (GSHP) system use buried tubes for heat exchange, GSHP is often mistaken for a BTES system. However, there are essential differences between the GSHP system and the BTES system, and the purpose of this study is to elucidate in detail the differences between these two systems. This study first summarizes the practical application cases of seasonal BTES globally, and then deeply compares and analyzes the differences between the seasonal BTES system and GSHP system from ten different perspectives, including system definition, technology timeline, purpose of buried tube heat exchanger, heat sources, soil temperature changes, buried tube heat exchanger volume, design of the buried tube heat exchanger, energy storage modes, biggest drawback, system performance evaluation. Finally, the future development prospects and research directions of the seasonal BTES system are further discussed. In summary, although the GSHP system may be confused with the seasonal BTES system in some aspects, they are indeed two different systems. Compared to the GSHP system, the seasonal BTES system can solve the contradiction between energy supply and demand in time and space, and effectively improve energy utilization efficiency.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"325 ","pages":"Article 114994"},"PeriodicalIF":6.6,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593481","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

Investigating envelope retrofitting potential and resilience of Australian residential buildings − A stock modelling approach 调查澳大利亚住宅建筑的围护结构改造潜力和抗灾能力--一种存量建模方法

IF 6.6 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Energy and Buildings

Pub Date : 2024-11-03 DOI: 10.1016/j.enbuild.2024.114990

Priyadarsini Rajagopalan , Dong Chen , Michael Ambrose

Residential buildings consume around 24 percent of overall electricity use in Australia. Though the energy efficiency of new buildings is progressively increasing, there are around 10 million existing homes most with poor thermal and energy performance. Improving these existing homes are imperative for Australia to reach its target of net zero by 2050. This paper adopts a stock modelling approach using real designs of more than two hundred thousand detached dwellings and apartments submitted for certification in eight states and territories across Australia to investigate envelope retrofitting potential of the housing stock. The performance of the existing housing stock was assessed and the effect of various levels of envelope improvements on energy efficiency and overheating were analysed for current and future climatic conditions. With improvements in 10% of the entire building stock, 3.14 Mt, 3.52 Mt and 7.2 Mt CO₂ emission reductions per year respectively were estimated with Rehab, Refurb and Renov improvements. Both detached dwellings and apartments experienced overheating across all the states and territories for the current and future climatic conditions. Though envelope improvement caused some reduction in the overheating, it was not significant. The high average overheating hours in Queensland come from nighttime overheating in the bedrooms, whereas in most other states daytime overheating constitute the majority. Various improvements in the building envelope were effective in reducing daytime overheating reductions rather than nighttime overheating, though the impact was marginal. The results from this study provided guidance on policy and regulatory mechanisms that can be introduced for developing decarbonization pathways for buildings at a national level.

在澳大利亚，住宅建筑的用电量约占总用电量的 24%。虽然新建建筑的能效在逐步提高，但仍有约 1000 万户现有住宅的热能和能源性能最差。澳大利亚要在 2050 年前实现净零能耗的目标，就必须改善这些现有住宅。本文采用存量建模的方法，利用澳大利亚八个州和地区提交认证的二十多万套独立式住宅和公寓的实际设计，调查住房存量的围护结构改造潜力。对现有住房的性能进行了评估，并分析了在当前和未来气候条件下不同程度的围护结构改造对能效和过热的影响。在对整个建筑群的 10%进行改进的情况下，通过改造、翻新和翻新，估计每年可分别减少 314 万吨、352 万吨和 720 万吨二氧化碳排放量。在当前和未来的气候条件下，所有州和地区的独立式住宅和公寓都会出现过热现象。虽然围护结构的改善在一定程度上减少了过热现象，但效果并不显著。昆士兰的平均过热时间较长，主要是卧室夜间过热，而在其他大多数州，白天过热占绝大多数。建筑围护结构的各种改进措施都能有效减少白天的过热时间，而不是夜间的过热时间，尽管影响不大。这项研究的结果为政策和监管机制提供了指导，这些政策和监管机制可用于在国家层面制定建筑脱碳路径。

{"title":"Investigating envelope retrofitting potential and resilience of Australian residential buildings − A stock modelling approach","authors":"Priyadarsini Rajagopalan , Dong Chen , Michael Ambrose","doi":"10.1016/j.enbuild.2024.114990","DOIUrl":"10.1016/j.enbuild.2024.114990","url":null,"abstract":"<div><div>Residential buildings consume around 24 percent of overall electricity use in Australia. Though the energy efficiency of new buildings is progressively increasing, there are around 10 million existing homes most with poor thermal and energy performance. Improving these existing homes are imperative for Australia to reach its target of net zero by 2050. This paper adopts a stock modelling approach using real designs of more than two hundred thousand detached dwellings and apartments submitted for certification in eight states and territories across Australia to investigate envelope retrofitting potential of the housing stock. The performance of the existing housing stock was assessed and the effect of various levels of envelope improvements on energy efficiency and overheating were analysed for current and future climatic conditions. With improvements in 10% of the entire building stock, 3.14 Mt, 3.52 Mt and 7.2 Mt CO<sub>2</sub> emission reductions per year respectively were estimated with Rehab, Refurb and Renov improvements. Both detached dwellings and apartments experienced overheating across all the states and territories for the current and future climatic conditions. Though envelope improvement caused some reduction in the overheating, it was not significant. The high average overheating hours in Queensland come from nighttime overheating in the bedrooms, whereas in most other states daytime overheating constitute the majority. Various improvements in the building envelope were effective in reducing daytime overheating reductions rather than nighttime overheating, though the impact was marginal. The results from this study provided guidance on policy and regulatory mechanisms that can be introduced for developing decarbonization pathways for buildings at a national level.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"325 ","pages":"Article 114990"},"PeriodicalIF":6.6,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0