The impact of a reduced training subspace on the prediction accuracy of neural networks for hygrothermal predictions

Tijskens, Astrid; Janssen, Hans; Roels, Staf

doi:10.1080/19401493.2020.1832148

Cited by 11 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reduce simulation time, this study proposes the use of a metamodel, a mathematical model that replaces the original hygrothermal model. The authors showed previously that a convolutional neural network is able to accurately capture the non-linear hygrothermal response of a massive masonry wall [6]- [8] and thus is likely to be suitable for timber frame wall simulations as well. The neural network is trained on a limited dataset, obtained with the original hygrothermal model.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…The authors showed previously that a convolutional neural network for time series is highly adequate for such purpose [6]- [8] as it is able to capture the complex time-dependent patterns of the hygrothermal response and allows flexibility in the desired post-processing. Hence, a similar network architecture as in [6] is used in this study to replace the hygrothermal model used to evaluate the hygrothermal performance of timber frame walls.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hygrothermal assessment of timber frame walls using a convolutional neural network

Tijskens

Roels

Janssen

2021

Building and Environment

Self Cite

View full text Add to dashboard Cite

Section: Convolutional Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hygrothermal assessment of timber frame walls using a convolutional neural network

Tijskens

Roels

Janssen

2021

Building and Environment

Self Cite

View full text Add to dashboard Cite

“…Various hygrothermal simulation programs emerged alongside the maturation of theoretical frameworks [11][12][13]. Hygrothermal simulation programs were frequently combined with a stochastic approach [14,15] or machine learning [16][17][18][19] to simulate and predict the envelope's long-term condition and function. The hygrothermal simulation software, especially Wärme Und Feuchte Instationär (WUFI), was used to evaluate the suitability and hygrothermal properties of new materials.…”

Section: Introductionmentioning

confidence: 99%

Hygrothermal Properties Analysis of Bamboo Building Envelope with Different Insulation Systems in Five Climate Zones

Yang

Zha

et al. 2023

Buildings

View full text Add to dashboard Cite

Laminated bamboo lumber (BLL) and bamboo scrimber (BS) are potential environmentally friendly building materials, considering that they are hygroscopic materials and that their hygrothermal performance is closely related to the occupants’ comfort, their building durability, and building energy consumption. This study carried out material property tests on bamboo-based materials (BLL and BS) and analyzed hygrothermal performance simulations on bamboo exterior wall constructions in five major climatic zones using WUFI. Results show that BS has a greater heat storage capacity than BLL. However, BLL shows a relatively higher moisture sorption capacity, and BLL is more easily permeated by vapor than BS. The water content (WC) of 12 walls of BLL and BS was below 20%; therefore, BLL and BS met the requirements of the envelope, and the WC of BS was lower than that of BLL. Based on the results, the walls designed in this study are suitable for the corresponding climate zones; in the cold and severe climate zones especially, the external insulation system walls performed better than the internal insulation system; therefore, the external insulation system is recommended for these two climate zones. The design and simulation results of walls made of two types of bamboo-based materials provide a scientific basis for the application of the material.

show abstract

“…The hygrothermal response of building components is transient and highly nonlinear. Astrid et al [28][29][30] developed a meta-model to replace the hygrothermal model, and hygrothermal time series such as temperature, humidity, and moisture content can be directly predicted. The network reliably evaluated the future damage risks of walls and calculated the hygrothermal performance of 96 types of wood-frame walls.…”

Section: Introductionmentioning

confidence: 99%

Using Machine Learning Method to Discover Hygrothermal Transfer Patterns from the Outside of the Wall to Interior Bamboo and Wood Composite Sheathing

Wang

Zhu

et al. 2022

Buildings

View full text Add to dashboard Cite

To identify hygrothermal transfer patterns of exterior walls is a crucial issue in the design, assessment, and construction of buildings. Temperature and relative humidity, as sensor monitoring data, were collected from the outside of the wall to interior bamboo and wood composite sheathing over the year in Huangshan Mountain District, Anhui Province, China. Combining the machine learning method of reservoir computing (RC) with agglomerative hierarchical clustering (AHC), a novel clustering framework was built for better extraction of the characteristics of hygrothermal transfer on the time series data. The experimental results confirmed the hypothesis that the change in the temperature and relative humidity of the outside of the wall (RHT12) dominated the change of the interior sheathing (RHT11). The delay time between two adjacent peaks in temperature was 1 to 2 h, while that in relative humidity was 1 to 4 h from the outside of the wall to interior bamboo and wood composite sheathing. There was no significant difference in temperature peak delay time between April and July. Temperature peak delay time was 50 to 120 min. However, relative humidity peak delay time was 100 to 240 min in April, whereas it was 20 to 120 min in July. The impact formed a relatively linear relationship between outdoor temperature and relative humidity peak delay time. The hygrothermal transfer patterns were characterized effectively by the peak delays. The discovery of the hygrothermal transfer patterns for the bamboo and wood composite walls using the machine learning method will facilitate the development of energy-efficient and durable bamboo and wood composite wall materials and structures.

show abstract

The impact of a reduced training subspace on the prediction accuracy of neural networks for hygrothermal predictions

Cited by 11 publications

References 24 publications

Hygrothermal assessment of timber frame walls using a convolutional neural network

Hygrothermal assessment of timber frame walls using a convolutional neural network

Hygrothermal Properties Analysis of Bamboo Building Envelope with Different Insulation Systems in Five Climate Zones

Using Machine Learning Method to Discover Hygrothermal Transfer Patterns from the Outside of the Wall to Interior Bamboo and Wood Composite Sheathing

Contact Info

Product

Resources

About