Thermal conductivity improvement in a green building with Nano insulations using machine learning methods

Ghalandari, Mohammad; Mukhtar, Azfarizal; Yasir, Ahmad Shah Hizam Md; Alkhabbaz, Ali; Meza, Aníbal; Cárdenas-Escrocia, Yulineth; Le, Binh Nguyen

doi:10.1016/j.egyr.2023.03.123

Cited by 18 publications

(8 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The solids content was calculated using Equation (1): Solids content (wt. %) = ∑ weight (HMDI +PEG+DMPA+TEA+ EDA) ∑ weight (HMDI +PEG+DMPA+TEA+EDA+ water) •100 (1) As can be observed in Figure 3, there is a clear relationship between the solids content and the density of the aerogel samples. Samples with a higher solids content exhibit higher density values than those with a lower solids content.…”

Section: Influence Of Solids Contentmentioning

confidence: 86%

“…The current energy situation has promoted the development of different insulating materials for the building sector as one of the main focal points to achieve even greater energy savings. This helps to reduce energy consumption in situations with extreme temperatures and greenhouse gas emissions [ 1 , 2 ]. In this sense, aerogels are presented as an improved alternative to conventional insulating materials used in the construction industry, presenting much lower thermal conductivity values when compared to classic materials such as polyurethane foams.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring the Impact of the Synthesis Variables Involved in the Polyurethane Aerogels-like Materials Design

Pinilla-Peñalver,

Cantero,

Romero

et al. 2024

Gels

View full text Add to dashboard Cite

This research presents a novel approach to synthesising polyurethane (PUR)-based aerogels at the pilot scale, optimizing synthesis variables such as the gelation solvent, solids content, chain extender/isocyanate ratio, and dispersion mode. The solids content (2–11 wt.%) is the parameter with the most influence on the density of the aerogels, with a clear decrease in this property as the solids content decreases. On the other hand, it was demonstrated that minimizing the excess of ethylenediamine (used as chain extender) in relation to the isocyanate is a valuable consideration to improve the thermal conductivity of the aerogel. Related to the chain extender/isocyanate ratio, a compromise situation where the initial isocyanate reacts almost completely is crucial. Fourier-transform infrared spectroscopy was used to conduct such monitoring during the reaction. Once the conditions were optimised, the aerogel showing improved properties was synthesised using ethyl acetate as the gelling solvent, a 3.7 wt.% solids content, an ethylenediamine/isocyanate ratio of 0.20, and sonication as the dispersion mode, attaining a thermal conductivity of 0.030 W m−1 K−1 and a density of 0.046 g cm−3. Therefore, the synthesized aerogel emerges as a promising candidate for use in the construction and automotive industries.

show abstract

Section: Influence Of Solids Contentmentioning

confidence: 86%

Section: Introductionmentioning

confidence: 99%

Exploring the Impact of the Synthesis Variables Involved in the Polyurethane Aerogels-like Materials Design

Pinilla-Peñalver,

Cantero,

Romero

et al. 2024

Gels

View full text Add to dashboard Cite

show abstract

“…Random Forest is an ensemble learning method that builds a multitude of decision trees at training time and generates the class that is the fashion of the individual tree classes (Ghalandari et al, 2023). For regression, the Random Forest output is usually the average (mean) of the predictions of all the individual trees, as expressed by Equation 4.…”

Section: Second Step -Models Trainingmentioning

confidence: 99%

Tracing Andean Origins: A Machine Learning Framework for Lead Isotopes

Alviz-Meza

2024

Preprint

View full text Add to dashboard Cite

This study uses machine learning techniques to facilitate the geolocation of Andean lead isotopes, a novel approach in this geographical context. Two predictive models for latitude and longitude were developed based on the compilation of a database of the lead isotope ratios 206Pb/204Pb, 207Pb/204Pb, and 208Pb/204Pb from multiple Andean provinces. These models were cross-validated using GridsearchCV to assess their performance, identifying Random Forest as the best-performing model. Also, clustering analysis with the K-means model and Euclidean distance was used to correlate artifact isotope compositions with known sources. The limitations and scope of the models were listed for their appropriate usability and interpretability. This work extends basic geochronological studies, integrates a comprehensive database, and applies state-of-the-art algorithms to generate predictive models, contributing to a deeper understanding of the historical Andean mineral resources' distribution and use.

show abstract

“…In addition to using surrogate models, researchers have explored the combination of machine learning (ML) [ 23 , [38] , [39] , [40] , [41] , [42] , [43] ] genetic algorithms (GA) [ 23 , 38 , [43] , [44] , [45] , [46] , [47] ] design of experiments (DoE) [ 13 , 48 ] and computational fluid dynamics (CFD) [ 4 , 5 , 8 , 12 , 27 , 28 , 49 ] in engineering optimisation. Moiz et al [ 43 ] presented an integrated ML and GA approach to optimising internal combustion engines, achieving comparable results to traditional CFD-GA approaches with significant time and cost savings.…”

Section: Related Workmentioning

confidence: 99%

“…The study focuses primarily on comparing the performance of PR and Kriging-based models as surrogate modelling approaches, rather than considering other popular methods such as Support Vector Regression (SVR) [ 23 ], Process Regression (GPR) [ 23 ], Radial Basis Function ( ) [ 24 ] and Artificial Neural Networks ( ) [ 25 , 26 ]. The decision to exclude these alternative methods can be attributed to several factors.…”

Section: Introductionmentioning

confidence: 99%

A machine learning-based comparative analysis of surrogate models for design optimisation in computational fluid dynamics

Mukhtar¹,

Yasir²,

Nasir³

2023

Heliyon

Self Cite

View full text Add to dashboard Cite

Thermal conductivity improvement in a green building with Nano insulations using machine learning methods

Cited by 18 publications

References 55 publications

Exploring the Impact of the Synthesis Variables Involved in the Polyurethane Aerogels-like Materials Design

Exploring the Impact of the Synthesis Variables Involved in the Polyurethane Aerogels-like Materials Design

Tracing Andean Origins: A Machine Learning Framework for Lead Isotopes

A machine learning-based comparative analysis of surrogate models for design optimisation in computational fluid dynamics

Contact Info

Product

Resources

About