[1]CHEN Meng,LI Ning,LI Shaoyuan.Interval type2 T-S fuzzy modeling of the PMV thermal comfort index[J].CAAI Transactions on Intelligent Systems,2011,6(3):219-244.
Copy

Interval type2 T-S fuzzy modeling of the PMV thermal comfort index

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 6 Number of periods: 2011 3 Page number: 219-244 Column: 学术论文—智能系统 Public date: 2011-06-25
Title:
Interval type2 T-S fuzzy modeling of the PMV thermal comfort index
Author(s):
CHEN Meng1; 2;  LI Ning1; 2;  LI Shaoyuan1; 2
1. Department of Automation, Shanghai JiaoTong University, Shanghai 200240, China;
2. Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai 200240, China
Keywords:
predicted mean vote;  computational fluid dynamics;  type2 fuzzy modeling;  interval T-S fuzzy systems
CLC:
TP273.4
DOI:
-
Abstract:
The predicted mean vote (PMV) index is widely used to evaluate the indoor thermal comfort with indoor environmental and human factors considered. However, PMV is difficult to control realtimely as its mathematical model is complicated and uncertain. Moreover, spatial distributions of environmental factors are neglected by using one PMV index in a room. In this paper, computational fluid dynamics (CFD) technology was applied for simulation of the environmental factors in order to accurately describe the PMV index. To deal with measurement noises or other system uncertainties, an interval type2 fuzzy model of PMV was developed and a new GKGAbased modeling method was proposed. The essential issue of type2 fuzzy modeling lies in the appropriate choice of secondary membership functions. In this study, the primary membership function was gained through a GustafsonKessel (GK) algorithm, and the secondary membership function was determined through a genetic algorithm (GA). The consequent parameter of the fuzzy rules was identified by a least squared algorithm. Simulation results show that the type2 fuzzy model is superior to type1 fuzzy model in minimizing the influence of uncertainties. The proposed method is effective and accurate. 
References:
［1］FANGER P O. Thermal comfort［M］. Copenhagen, Denmark: Danish Technical Press, 1970： 1244.
［2］ISO 7730. Moderate thermal environment—determination of PMV and PPD indices and specification of the condition for thermal comfort［S］. Geneva: International Organization for Standardization, 1994.
［3］WANG Shengwei, XU Xinhua. Optimal and robust control of outdoor ventilation airflow rate for improving energy efficiency and IAQ［J］. Building and Environment, 2004, 39(7): 763773.
［4］XU Xinhua, WANG Shengwei, SUN Zhongwei, et al. A modelbased optimal ventilation control strategy of multizone VAV airconditioning systems［J］. Applied Thermal Engineering, 2009, 29(1): 91104.
［5］MOSSOLLY M, GHALI K, GHADDAR N. Optimal control strategy for a multizone air conditioning system using a genetic algorithm［J］. Energy, 2009, 34(1): 5866.
［6］高立新,白桦.利用神经网络预测PMV指标［J］.哈尔滨建筑大学学报, 2002, 35(5): 7071.
GAO Lixin， BAI Hua. Prediction of PMV index using neural network［J］. Journal of Harbin University of Civil Engineering and Architecture, 2002, 35(5): 7071.
［7］刘靖,张子平,姜凡,等.最小二乘支持向量机在热舒适性PMV指标预测中的应用研究［J］.制冷空调与建筑机械, 2007, 28(6): 57.
?LIU Jing, ZHANG Ziping, JIANG Fan, et al. Research on the application of least square support vector machine in the prediction of PMV［J］. Refrigeration Air Conditioning & Electric Power Machinery, 2007, 28(6): 57.
［8］WANG Hanqing, HUANG Chunhua, LIU Zhiqiang, et al. Dynamic evaluation of thermal comfort environment of airconditioned buildings［J］. Building and Environment, 2006, 41(11): 15221529.
［9］HO S H, ROSARIO L, RAHMAN M M. Three dimensional analysis for hospital operating room thermal comfort and contaminant removal［J］. Applied Thermal Engineering, 2009, 29(10): 20802092.
［10］FAZEL ZARANDI M H, TURKSEN I B, TORBI KASBI O. Type2 fuzzy modeling for desulphurization of steel process［J］. Expert Systems with Applications, 2007, 32(1): 157171.
［11］廖倩芳,李柠,李少远.一种数据驱动的Ⅱ型TS模糊建模方法［J］.智能系统学报, 2009, 4(4): 303308.
LIAO Qianfang, LI Ning, LI Shaoyuan. A TypeⅡ TS fuzzy modeling method for datadriven approaches［J］. CAAI Transactions on Intelligent Systems, 2009, 4(4): 303308.
［12］王梦灵,李柠,李少远.带有测量噪声的Ⅱ型TS模糊建模［J］.系统工程与电子技术, 2009, 30(10): 19571961.
WANG Mengling, LI Ning, LI Shaoyuan. Type2 TS fuzzy modeling for the dynamic systems with measurement noise［J］. Systems Engineering and Electronics, 2009, 30(10): 19571961.
［13］MENDEZ G M, CASTILLO O. Interval type2 TSK fuzzy logic systems using hybrid learning algorithm［C］//The 14th IEEE International Conference on Fuzzy Systems. Reno, USA, 2005: 230235.
［14］MENDEZ G M, HERNANDEZ M A. Interval type1 nonsingleton type2 TSK fuzzy logic systems using the hybrid training method RLSBP［C］//Proceedings of the 2007 IEEE Symposium on Foundations of Computational Intelligence. Honolulu, USA, 2007: 370374.
［15］LIANG Qilian, MENDEL J M. An introduction to type2 TSK fuzzy logic systems［C］//IEEE International Fuzzy Systems Conference Proceedings. Seoul, Korea, 1999: 15341539.
［16］MENDEL J M. Interval type2 fuzzy logic systems made simple［J］. IEEE Transactions on Fuzzy Systems, 2006, 14(6): 808821.
［17］QUN Ren, BARON L, BALAZINSKI M. Type2 TakagiSugenoKang fuzzy logic modeling using subtractive clustering［C］//Annual Meeting of the North American Fuzzy Information Processing Society. Montreal, Canada, 2006: 120125.
［18］GUSTAFSON D E, KESSEL W C. Fuzzy clustering with a fuzzy covariance matrix［C］//IEEE Conference on Decision and Control Including the 17th Symposium on Adaptive Process. San Diego, USA, 1979: 761766.
［19］PAPADAKIS S E, THEOCHARIS J B. A GAbased fuzzy modeling approach for generating TSK models［J］. Fuzzy Sets and Systems, 2002, 131(2): 121152.
Similar References:

Memo

-

Last Update: 2011-07-23

Copyright © CAAI Transactions on Intelligent Systems