View in EDS

Research on multi-parameter cooperative control of smart opening and closing windows based on feed-forward neural network.

Saved in:
Bibliographic Details
Title: Research on multi-parameter cooperative control of smart opening and closing windows based on feed-forward neural network.
Authors: Lai, Aihua, Liu, Aimei, Xuan, Wenjing, Ding, Yanyan
Source: Journal of Combinatorial Mathematics & Combinatorial Computing; Dec2025, Vol. 127b, p7731-7742, 12p
Subject Terms: ARTIFICIAL neural networks, ENERGY consumption, INDOOR air pollution, ELECTROCHROMIC windows, ENERGY management, FEEDBACK control systems, ADAPTIVE control systems
Abstract: Control techniques of Smart windows using Multi-parameter neural feedforward systems as a control strategy shows great potential in improving not only the energy efficiency geometrically but also the building’s indoor environmental quality. In this study, a new smart window control is developed that is based on neural networks which are able to implement multi control strategies in various conditions with regard to temperature, humidity, light and air quality. This allows for a further development of the system: firstly, it thoroughly presents the model, which facilitates the understanding of the mathematic modeling of windows' dynamic position and, at the same time, shows how the neural network works. The structure comprises a perception layer, which provides perception of the environment, processing layer for analysis and decision making on the input data, and the last action layer that performs windows' actuation and gives feedback on the action implemented. In terms of the system's control efficiency, timing, energy consumption and seeking users’ satisfaction, the performance of this control system outperforms other existing systems in empirical application. The control accuracy attained in the proposed system is 97.8%. What is more interesting about this approach is the energy efficiency which stands at 94.3%, this is only the bare minimum, estimation says it surpasses the rest by a great deal. The successful realization of this control system is an important step toward the development of smart buildings that can be relied on for excellent results. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Combinatorial Mathematics & Combinatorial Computing is the property of Combinatorial Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:Control techniques of Smart windows using Multi-parameter neural feedforward systems as a control strategy shows great potential in improving not only the energy efficiency geometrically but also the building’s indoor environmental quality. In this study, a new smart window control is developed that is based on neural networks which are able to implement multi control strategies in various conditions with regard to temperature, humidity, light and air quality. This allows for a further development of the system: firstly, it thoroughly presents the model, which facilitates the understanding of the mathematic modeling of windows' dynamic position and, at the same time, shows how the neural network works. The structure comprises a perception layer, which provides perception of the environment, processing layer for analysis and decision making on the input data, and the last action layer that performs windows' actuation and gives feedback on the action implemented. In terms of the system's control efficiency, timing, energy consumption and seeking users’ satisfaction, the performance of this control system outperforms other existing systems in empirical application. The control accuracy attained in the proposed system is 97.8%. What is more interesting about this approach is the energy efficiency which stands at 94.3%, this is only the bare minimum, estimation says it surpasses the rest by a great deal. The successful realization of this control system is an important step toward the development of smart buildings that can be relied on for excellent results. [ABSTRACT FROM AUTHOR]
ISSN:08353026
DOI:10.61091/jcmcc127b-423