A pattern recognition approach for modeling the air change rates in naturally ventilated buildings from limited steady-state CFD simulations

Abstract Calculating the air change rates inside naturally ventilated buildings is essential for many applications including indoor temperature calculation. The air change per hour (ACH) at a particular time step and ambient conditions (wind speed, direction, temperature, etc.) is usually calculated via sophisticated simulators, e.g., CFD. However, having a mathematical model describing the relationship between ACH (output variable) and other ambient conditions (input variables), rather than mere simulated numbers, is very important for several reasons: understanding the nature of this relationship and its dominating variables; calculating the indoor temperature at arbitrary time steps; and saving the enormous simulation time when simulating long spans. In this article, a novel approach from pattern recognition literature is introduced to model ACH. A Classification and Regression Tree (CART) was designed from 180 CFD simulated values of ACH, along with their experimentally measured ambient conditions. The RMS error between the ACH values predicted by CART and those simulated by CFD is calculated using cross validation and found to be very acceptable (0.78 and 1.48) h−1 for two different rooms. The model revealed that the ambient temperature is not predictive and hence was dropped from the final model. Designed CART was then fed to TRNSYS 17 as an equation where variables defined as algebraic functions to produce an hourly output for ACH and calculate the indoor temperature along the summer season. The absolute deviance error between the indoor temperatures simulated by TRNSYS and those measured experimentally is as low as (0.3 and 0.4) °C for the two rooms respectively.

[1]  Donal Finn,et al.  Sensitivity of air change rates in a naturally ventilated atrium space subject to variations in external wind speed and direction , 2008 .

[2]  V. I. Hanby,et al.  CFD modelling of natural displacement ventilation in an enclosure connected to an atrium , 2007 .

[3]  Ben Richard Hughes,et al.  A numerical investigation into the effect of Windvent louvre external angle on passive stack ventilation performance , 2010 .

[4]  Yuehong Su,et al.  A review on wind driven ventilation techniques , 2008 .

[5]  John Kaiser Calautit,et al.  A numerical investigation into the feasibility of integrating green building technologies into row houses in the Middle East , 2013 .

[6]  Andreas K. Athienitis,et al.  Wind-induced natural ventilation analysis , 2007 .

[7]  Samir S. Ayad,et al.  Computational study of natural ventilation , 1999 .

[8]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[9]  Dominique Marchio,et al.  Numerical simulation of wind-driven natural ventilation: Effects of loggia and facade porosity on air change rate , 2016 .

[10]  Ronald Christensen.  Plane Answers to Complex Questions , 1987 .

[11]  David G. Stork,et al.  Pattern Classification , 1973 .

[12]  Weeratunge Malalasekera,et al.  An introduction to computational fluid dynamics - the finite volume method , 2007 .

[13]  Malcolm J. Cook,et al.  Buoyancy-driven displacement ventilation flows: Evaluation of two eddy viscosity turbulence models for prediction , 1998 .

[14]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[15]  J. I. Kindangen,et al.  Effects of roof shapes on wind-induced air motion inside buildings , 1997 .

[16]  Stephen R. Marsland,et al.  Machine Learning - An Algorithmic Perspective , 2009, Chapman and Hall / CRC machine learning and pattern recognition series.

[17]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[18]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[19]  Leon R. Glicksman,et al.  Preliminary design method for naturally ventilated buildings using target air change rate and natural ventilation potential maps in the United States , 2015 .

[20]  Leon R. Glicksman,et al.  Application of integrating multi-zone model with CFD simulation to natural ventilation prediction , 2005 .

[21]  Cheuk Ming Mak,et al.  The assessment of the performance of a windcatcher system using computational fluid dynamics , 2007 .

[22]  Thomas Auer,et al.  Numerical assessment of the efficiency of fenestration system and natural ventilation mechanisms in a courtyard house in hot climate , 2017 .

[23]  Abbas Elmualim,et al.  Wind Tunnel and CFD Investigation of the Performance of “Windcatcher” Ventilation Systems , 2002 .

[24]  David Banks,et al.  Combined wind tunnel and CFD analysis for indoor airflow prediction of wind-driven cross ventilation , 2013 .

[25]  Geoffrey I. Webb,et al.  Encyclopedia of Machine Learning , 2011, Encyclopedia of Machine Learning.

[26]  S. R. Searle.  Linear Models , 1971 .

[27]  Ryuichiro Yoshie,et al.  CFD modelling of unsteady cross ventilation flows using LES , 2008 .

[28]  Per Heiselberg,et al.  Natural Ventilation Design , 2004 .

[29]  Maria K. Koukou,et al.  Natural cross-ventilation in buildings: Building-scale experiments, numerical simulation and thermal comfort evaluation , 2008 .

[30]  Shigeki Nishizawa,et al.  A Wind Tunnel Full-Scale Building Model Comparison between Experimental and CFD Results Based on the Standard k-ε Turbulence Representation , 2004 .

[31]  Atila Novoselac,et al.  Cross ventilation with small openings: Measurements in a multi-zone test building , 2012 .

[32]  Zuohuan Zheng,et al.  Nonlinear coupling between thermal mass and natural ventilation in buildings , 2003 .

[33]  K. Visagavel,et al.  Analysis of single side ventilated and cross ventilated rooms by varying the width of the window opening using CFD , 2009 .

[34]  Xiong Shen,et al.  Comparison of different methods for estimating ventilation rates through wind driven ventilated buildings , 2012 .

[35]  G. Evola,et al.  Computational analysis of wind driven natural ventilation in buildings , 2006 .

[36]  Vladimir Cherkassky,et al.  Learning from Data: Concepts, Theory, and Methods , 1998 .

[37]  Jon Hand,et al.  CONTRASTING THE CAPABILITIES OF BUILDING ENERGY PERFORMANCE SIMULATION PROGRAMS , 2008 .

[38]  Tao Lu,et al.  A novel methodology for estimating space air change rates and occupant CO2 generation rates from measurements in mechanically-ventilated buildings , 2010 .

[39]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[40]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[41]  Monika Woloszyn,et al.  Assessment of the air change rate of airtight buildings under natural conditions using the tracer gas technique. Comparison with numerical modelling , 2013 .

[42]  Takashi Kurabuchi,et al.  Applying the Local Dynamic Similarity Model and CFD for the Study of Cross-Ventilation , 2006 .

[43]  Amr Bagneid,et al.  The Creation of a Courtyard Microclimate Thermal Model for the Analysis of Courtyard Houses , 2009 .

[44]  Bert Blocken,et al.  Coupled urban wind flow and indoor natural ventilation modelling on a high-resolution grid: A case study for the Amsterdam ArenA stadium , 2010, Environ. Model. Softw..

[45]  Frédéric Magoulès,et al.  A review on the prediction of building energy consumption , 2012 .

[46]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[47]  Nyuk Hien Wong,et al.  The study of active stack effect to enhance natural ventilation using wind tunnel and computational fluid dynamics (CFD) simulations , 2004 .

[48]  A. C. Rencher.  Linear models in statistics , 1999 .

[49]  Cheuk Ming Mak,et al.  A numerical simulation of wing walls using computational fluid dynamics , 2007 .

[50]  Walter Meile,et al.  Air change rates driven by the flow around and through a building storey with fully open or tilted windows: An experimental and numerical study , 2014 .