检索结果-南通市图书馆

Unsupervised learning of load signatures to estimate energy-related building features using surrogate modelling techniques

引用

Building Simulation 2023年第7期16卷 1273-1286页

作者： Shane Ferreira Burak Gunay Araz Ashouri Scott Shillinglaw Carleton University OttawaK1S 5B6Canada National Research Council Canada OttawaK1A 0R6Canada

Characterization of an existing building’s energy-related features is critical to inform maintenance and retrofit ***,existing field-scale characterization methods tend to be labour intensive,invasive,and require high fidelity longitudinal data gathered through tightly regulated *** highlights the need for a low cost,scalable,and efficient screening *** paper puts forward a surrogate model-based approach to rapidly estimate energy-related building *** this end,EnergyPlus models for 12 midrise office archetypes,all with a rectangular footprint,are *** thousand variants of each archetype are generated by altering envelope,causal heat gain,and heating,ventilation,and air conditioning operation features.A unique load signature is derived for each variant’s heating and cooling energy *** parameters of the load signatures are clustered,then each cluster is associated with a set of plausible energy-related *** accuracy of the results was evaluated using five test buildings not seen by the *** method could effectively identify building features with reasonable accuracy and no significant degradation in performance across all 12 archetypes.

关键词： remote characterization energy-related building features surrogate modelling cluster analysis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Using Bayesian deep learning approaches for uncertainty-aware building energy surrogate models

引用

Energy and AI 2021年第1期3卷 91-103页

作者： Paul Westermann Ralph Evins Energy and Cities Group Department of Civil Engineering University of VictoriaCanada

Fast machine learning-based surrogate models are trained to emulate slow,high-fidelity engineering simulation models to accelerate engineering design *** introduces uncertainty as the surrogate is only an approxi-mation of the original *** methods can quantify that uncertainty,and deep learning models exist that follow the Bayesian *** models,namely Bayesian neural networks and Gaussian process models,enable us to give predic-tions together with an estimate of the model’s *** a result we can derive uncertainty-aware surrogate models that can automatically identify unseen design samples that may cause large emulation *** these samples the high-fidelity model can be queried *** paper outlines how the Bayesian paradigm allows us to hybridize fast but approximate and slow but accurate *** this paper,we train two types of Bayesian models,dropout neural networks and stochastic variational Gaussian Process models,to emulate a complex high dimensional building energy performance simulation *** surrogate model processes 35 building design parameters(inputs)to estimate 12 annual building energy perfor-mance metrics(outputs).We benchmark both approaches,prove their accuracy to be competitive,and show that errors can be reduced by up to 30%when the 10%of samples with the highest uncertainty are transferred to the high-fidelity model.

关键词： surrogate modelling Metamodel Building performance simulation Uncertainty Bayesian deep learning Gaussian Process Bayesian neural network

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Synergistic optimization framework for the process synthesis and design of biorefineries

引用

Frontiers of Chemical Science and Engineering 2022年第2期16卷 251-273页

作者： Nikolaus IVollmer Resul Al Krist V.Gernaey Gürkan Sin Process and Systems Engineering(PROSYS)Research Center Department of Chemical and Biochemical EngineeringTechnical University of Denmark2800 Kgs.LyngbyDenmark Novo Nordisk A/S 2880 BagsværdDenmark

The conceptual process design of novel bioprocesses in biorefinery setups is an important task,which remains yet challenging due to several *** propose a novel framework incorporating superstructure optimization and simulation-based optimization *** this context,several approaches for superstructure optimization based on different surrogate models can be *** means of a case study,the framework is introduced and validated,and the different superstructure optimization approaches are *** results indicate that even though surrogate-based optimization approaches alleviate the underlying computational issues,there remains a potential issue regarding their *** development of appropriate surrogate models,comprising the selection of surrogate type,sampling type,and size for training and cross-validation sets,are essential *** this aspect,satisfactory validation metrics do not ensure a successful outcome from its embedded use in an optimization ***,the framework’s synergistic effects by sequentially performing superstructure optimization to determine candidate process topologies and simulationbased optimization to consolidate the process design under uncertainty offer an alternative and promising *** findings invite for a critical assessment of surrogatebased optimization approaches and point out the necessity of benchmarking to ensure consistency and quality of optimized solutions.

关键词： biotechnology surrogate modelling superstructure optimization simulation-based optimization process design

来源：

维普期刊数据库

同方期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：