Climate adaptive optimal design of an aerogel glazing system with the integration of a heuristic teaching-learning-based algorithm in machine learning-based optimization

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

7 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)375-391
Journal / PublicationRenewable Energy
Volume153
Online published31 Jan 2020
Publication statusPublished - Jun 2020

Abstract

Integrating advanced materials in building glazing systems is critical for promoting net-zero energy buildings. In this research, both experimental and numerical studies were conducted on an aerogel glazing system. In order to provide climate adaptive designs on the aerogel glazing system with optimal geometric and operating parameters, a generic optimization methodology was developed by flexibly integrating supervised machine learning and advanced teaching-learning-based optimization algorithm. The proposed optimization methodology was thereafter used for optimal system designs in different climate regions. Results indicate that the proposed surrogate model can intelligently and accurately learn and update the optimization function with straightforward mathematical associations between multivariables and objectives. In addition, within optimal cases, total heat gain and heat flux are dominated by the extinction coefficient in southern cities, whereas the total heat gain is dominated by the thermal conductivity in the northern city, LanZhou. By adopting the proposed technique in this study, compared to optimal results following the Taguchi standard orthogonal array, the total heat gain can be reduced by 62.5% to 36.27 kWh/m2 in LanZhou, and by 5.9% to 267.18 kWh/m2 in GuangZhou, respectively. This study formulates a general methodology for climate adaptive optimal designs on aerogel glazing systems in different climatic regions.

Research Area(s)

  • Aerogel glazing system, Climatic regions, Machine learning, Optimization function, Teaching-learning-based optimization

Citation Format(s)