Artificial neural network-based smart aerogel glazing in low-energy buildings: A state-of-the-art review

Aerogel materials with super-insulating, visual-penetrable, and sound-proof properties are promising in buildings, whereas the coupling effect of various parameters in complex porous aerogels proposes challenges for thermal/visual performance prediction. Traditional physics-based models face challenges such as modeling complexity, heavy computational load, and inadaptability for long-term validation (owing to boundary condition change, degradation of thermophysical properties, and so on). In this study, a holistic review is conducted on aerogel production, components prefabrication, modeling development, single-, and multi-objective optimizations. Methodologies to quantify parameter uncertainties are reviewed, including interface energy balance, Rosseland approximation and Monte Carlo method. Novel aerogel integrated glazing systems with synergistic functions are demonstrated. Originalities include an innovative modeling approach, enhanced computational efficiency, and user-friendly interface for non-professionals or multidisciplinary research. In addition, human knowledge-based machine learning can reduce abundant data requirement, increase performance prediction reliability, and improve model interpretability, so as to promote advanced aerogel materials in smart and energy-efficient buildings.

Automated summary

This study provides a comprehensive review of aerogel production, modeling, and optimization methods, as well as proposing solutions to potential challenges such as quantifying parameter uncertainties through interface energy balance and Monte Carlo methods. It also demonstrates the innovation of novel aerogel integrated glazing systems with synergistic functions. Human knowledge-based machine learning is shown to increase performance prediction reliability, aiding in the development of advanced aerogel materials in smart and energy-efficient buildings.