Coupling a neural network temperature predictor and a fuzzy logic controller to perform thermal comfort regulation in an office building

被引:85
|
作者
Marvuglia, Antonino [1 ]
Messineo, Antonio [2 ]
Nicolosi, Giuseppina [2 ]
机构
[1] Resource Ctr Environm Technol CRTE, Publ Res Ctr Henri Tudor CRPHT, L-4362 Luxembourg, Luxembourg
[2] Univ Enna Kore, Fac Engn & Architecture, I-94100 Enna, Italy
关键词
Indoor thermal comfort; Artificial neural networks; NNARX; Fuzzy logic; Controller; Temperature forecast; INDOOR AIR-QUALITY; ENERGY; OPTIMIZATION; DESIGN; SYSTEM; CONSUMPTION; IMPACT; SPACE; MODEL;
D O I
10.1016/j.buildenv.2013.10.020
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The paper describes the application of a combined neuro-fuzzy model for indoor temperature dynamic and automatic regulation. The neural module of the model, an auto-regressive neural network with external inputs (NNARX), produces indoor temperature forecasts that are used to feed a fuzzy logic control unit that simulates switching the heating, ventilation and air conditioning (HVAC) system on and off and regulating the inlet air speed. To generate an indoor temperature forecast, the NNARX module uses weather parameters (e.g., outdoor temperature, air relative humidity and wind speed) and the indoor temperature recorded in previous time steps as regressors. In its current state, the fuzzy controller is only driven by the indoor temperature forecasted by the NNARX module; no variations in indoor heat gains or occupants' clothing and behavior were considered for driving the controller. The main goal of this paper is to demonstrate the effectiveness of the hybrid neuro-fuzzy approach and the importance of efficiently designing the temperature forecast model, especially with respect to the selection of the order of the regressor for each of the external and internal parameters used. Therefore, a differential entropy-based method was applied in this study, which provided good forecasting performances for the NNARX model. (C) 2013 Elsevier Ltd. All rights reserved.
引用
收藏
页码:287 / 299
页数:13
相关论文
共 50 条
  • [1] Blood glucose regulation using a neural network predictor with a fuzzy logic controller
    Allam, Fayrouz
    Nossair, Zaki
    Gomma, Hesham
    Ibrahim, Ibrahim
    Abdelsalam, Mona
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2013, 25 (02) : 403 - 413
  • [2] Thermal comfort based fuzzy logic controller
    Gouda, M.M.
    Danaher, S.
    Underwood, C.P.
    Building Services Engineering Research and Technology, 2001, 22 (04) : 237 - 253
  • [3] A fuzzy logic based neural network controller
    Rao, M.V.C.
    Mahesh, J.
    Elektron, 2000, 17 (01):
  • [4] Design and Modeling of Intelligent Building Office and Thermal Comfort Based on Probabilistic Neural Network
    Kciuk M.
    Bijok T.
    Lo Sciuto G.
    SN Computer Science, 3 (6)
  • [5] Study on the combination of the fuzzy controller and neural network predictor
    Gao, Hai-yan
    Bo, Ya-ming
    Liu, Guo-dong
    Chuan Bo Li Xue/Journal of Ship Mechanics, 2000, 4 (02): : 61 - 64
  • [6] Tuning of fuzzy logic controller using neural network
    Van Cleave, D
    Rattan, KS
    PROCEEDINGS OF THE IEEE 2000 NATIONAL AEROSPACE AND ELECTRONICS CONFERENCE: ENGINEERING TOMORROW, 2000, : 305 - 312
  • [7] A sliding mode controller with neural network and fuzzy logic
    Lee, M
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 2414 - 2417
  • [8] A Dynamic Fuzzy Controller to Meet Thermal Comfort by Using Neural Network Forecasted Parameters as the Input
    Collotta, Mario
    Messineo, Antonio
    Nicolosi, Giuseppina
    Pau, Giovanni
    ENERGIES, 2014, 7 (08): : 4727 - 4756
  • [9] A Fuzzy Controller for Thermal Comfort and Indoor Air Quality in a Bioclimatic Building
    Bretones, Maria D.
    Alvarez, Jose D.
    del Mar Castilla, Maria
    Berenguel, Manuel
    2020 EUROPEAN CONTROL CONFERENCE (ECC 2020), 2020, : 1029 - 1036
  • [10] Industrial robotic systems with fuzzy logic controller & neural network
    Lee, SB
    FIRST INTERNATIONAL CONFERENCE ON KNOWLEDGE-BASED INTELLIGENT ELECTRONIC SYSTEMS, PROCEEDINGS 1997 - KES '97, VOLS 1 AND 2, 1997, : 599 - 606