Comparison of different deep neural network architectures for isothermal indoor airflow prediction

The rising awareness about energy conservation calls for more energy-efficient designs of heating, ventilation and air-conditioning (HVAC) systems and advanced control strategies. A rapid and accurate prediction method for indoor environment is thus of great importance. As one of the popular artificial intelligence models, a deep neural network (DNN) performs well in establishing a non-linear relationship between variables. This study aims to explore the feasibility of adopting DNN for predicting indoor airflow distribution. The detailed process of computational fluid dynamics (CFD) database establishment and construction of DNN are presented herein. To reveal the influence of DNN architecture on prediction performance, two DNNs, namely DNN A and DNN B, were constructed in consideration of different prediction strategies, and their performances on both training dataset and test dataset were compared. DNN A represents a DNN that outputs velocity values of the whole domain simultaneously, whereas DNN B outputs one velocity value of a target location for each run. Results indicate that the performance of DNN A and DNN B on the training dataset show slightly difference; however, DNN A performs much better than DNN B on test dataset. DNN A shows similar accuracies on predicting airflow distributions with different resolutions, whereas the prediction accuracy of DNN B deteriorated for airflow distributions with higher resolution. Both DNNs would output unreliable predictions for cases of which inputs are out of the range of those of training cases. The results confirm the possibility of rapid prediction of indoor airflow via a well-trained DNN which requires about 320 μs for each case, resulting in about 1.9 million times faster than CFD simulation in this study.

[1]  Yurong Liu,et al.  A survey of deep neural network architectures and their applications , 2017, Neurocomputing.

[2]  Qingyan Chen,et al.  Simulating buoyancy-driven airflow in buildings by coarse-grid fast fluid dynamics , 2015 .

[3]  Ziwei Li,et al.  An ANN-based fast building energy consumption prediction method for complex architectural form at the early design stage , 2019, Building Simulation.

[4]  Tian-hu Zhang,et al.  A simulation-based inverse design of preset aircraft cabin environment , 2014 .

[5]  John E. Taylor,et al.  Inter-building effect: Simulating the impact of a network of buildings on the accuracy of building energy performance predictions , 2012 .

[6]  Parham A. Mirzaei,et al.  Development of a dynamic external CFD and BES coupling framework for application of urban neighbourhoods energy modelling , 2018, Building and Environment.

[7]  Zhiqiang John Zhai,et al.  Evaluation of Various Turbulence Models in Predicting Airflow and Turbulence in Enclosed Environments by CFD: Part 2—Comparison with Experimental Data from Literature , 2007 .

[8]  Zhanxing Zhu,et al.  Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes , 2017, ArXiv.

[9]  Brian J. Polidoro,et al.  Development and application of an updated whole-building coupled thermal, airflow and contaminant transport simulation program (TRNSYS/CONTAM) , 2015 .

[10]  Shi-Jie Cao,et al.  Ventilation control strategy using low-dimensional linear ventilation models and artificial neural network , 2018, Building and Environment.

[11]  Liang Zhou,et al.  Optimization of ventilation system design and operation in office environment , 2009 .

[12]  Peter V. Nielsen,et al.  Computational Fluid Dynamics and Building Energy Performance Simulation , 1998 .

[13]  Laura Bellia,et al.  A coupled numerical approach on museum air conditioning: Energy and fluid-dynamic analysis , 2013 .

[14]  E.J. Teshome,et al.  Zonal Models for Indoor Air Flow - A Critical Review , 2004 .

[15]  Haralambos Sarimveis,et al.  Optimization of window-openings design for thermal comfort in naturally ventilated buildings , 2012 .

[16]  You Xueyi,et al.  The inverse optimization of exhaust hood by using intelligent algorithms and CFD simulation , 2017 .

[17]  S. Kato,et al.  Control of indoor thermal environment based on concept of contribution ratio of indoor climate , 2010 .

[18]  Cheuk Ming Mak,et al.  Flow and dispersion in coupled outdoor and indoor environments: Issue of Reynolds number independence , 2019, Building and Environment.

[19]  Tian-Hu Zhang,et al.  Inverse design of aircraft cabin environment by coupling artificial neural network and genetic algorithm , 2014 .

[20]  Arun Kumar,et al.  A review on modeling and simulation of building energy systems , 2016 .

[21]  Carlos Alberto Conceição António,et al.  Air temperature fields inside refrigeration cabins: A comparison of results from CFD and ANN modelling , 2011 .

[22]  Yi Jiang,et al.  Research on a dynamic simulation method of atrium thermal environment based on neural network , 2012 .

[23]  Wangda Zuo,et al.  Coupling fast fluid dynamics and multizone airflow models in Modelica Buildings library to simulate the dynamics of HVAC systems , 2017 .

[24]  S-J Cao,et al.  On the construction and use of linear low-dimensional ventilation models. , 2012, Indoor air.

[25]  Ricardo C. L. F. Oliveira,et al.  Intelligent co-simulation: neural network vs. proper orthogonal decomposition applied to a 2D diffusive problem , 2018 .

[26]  Wangda Zuo,et al.  A systematic evaluation of accelerating indoor airflow simulations using cross-platform parallel computing , 2017 .

[27]  Surya Ganguli,et al.  Identifying and attacking the saddle point problem in high-dimensional non-convex optimization , 2014, NIPS.

[28]  Q Chen,et al.  Real-time or faster-than-real-time simulation of airflow in buildings. , 2009, Indoor air.

[29]  Jing Wang,et al.  A fast deep learning system using GPU , 2014, 2014 IEEE International Symposium on Circuits and Systems (ISCAS).

[30]  Yann LeCun,et al.  The Loss Surfaces of Multilayer Networks , 2014, AISTATS.

[31]  Wei Tian,et al.  Coupling indoor airflow, HVAC, control and building envelope heat transfer in the Modelica Buildings library , 2016 .

[32]  Zhimin Du,et al.  Temperature sensor placement optimization for VAV control using CFD–BES co-simulation strategy , 2015 .

[33]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[34]  Gang Wu,et al.  Study on simulation methods of atrium building cooling load in hot and humid regions , 2010 .

[35]  Hyeran Byun,et al.  Real-time traffic sign recognition based on a general purpose GPU and deep-learning , 2017, PloS one.

[36]  Haralambos Sarimveis,et al.  Development of a computational tool to quantify architectural-design effects on thermal comfort in naturally ventilated rural houses , 2010 .

[37]  Kazuhide Ito,et al.  Energy consumption analysis intended for real office space with energy recovery ventilator by integrating BES and CFD approaches , 2012 .

[38]  Zhiqiang Zhai,et al.  Numerical determination and treatment of convective heat transfer coefficient in the coupled building energy and CFD simulation , 2004 .

[39]  Zhiqiang John Zhai,et al.  Sensitivity analysis and application guides for integrated building energy and CFD simulation , 2006 .

[40]  Qingyan Chen,et al.  On approaches to couple energy simulation and computational fluid dynamics programs , 2002 .

[41]  Takashi Kurabuchi,et al.  CFD Benchmark Tests for Indoor Environmental Problems: Part 1, Isothermal/Non-Isothermal Flow in 2D and 3D Room Model , 2015 .

[42]  Zhiqiang Zhai,et al.  Numerical investigation on thermal performance and correlations of double skin façade with buoyancy-driven airflow , 2008 .

[43]  J. Allegrini,et al.  Simulations of local heat islands in Zürich with coupled CFD and building energy models , 2017, Urban Climate.

[44]  Zhiqiang John Zhai,et al.  Performance of coupled building energy and CFD simulations , 2005 .

[45]  Chao Huan,et al.  Development of a nodal model for predicting the vertical temperature profile in a stratum-ventilated room , 2018 .

[46]  Ricardo C. L. F. Oliveira,et al.  An artificial intelligence-based method to efficiently bring CFD to building simulation , 2018 .

[47]  M. Sohn,et al.  Building energy simulation coupled with CFD for indoor environment: A critical review and recent applications , 2018 .

[48]  Wangda Zuo,et al.  Fast and informative flow simulations in a building by using fast fluid dynamics model on graphics processing unit , 2010 .

[49]  Jelena Srebric,et al.  A Coupled Airflow and Energy Simulation Program for Indoor Thermal Environmental Studies , 2000 .

[50]  Philippe Rigo,et al.  A review on simulation-based optimization methods applied to building performance analysis , 2014 .