Development of self-adaptive low-dimension ventilation models using OpenFOAM: Towards the application of AI based on CFD data

Abstract Numerous state-of-art CFD (Computational Fluid Dynamics) studies have shown their validity and feasibility in engineering applications but still lack prediction efficiency. It is of great potential to apply artificial intelligence (AI) on the basis of CFD considering their fast development. Thus, the data-dimension reduction of CFD can be very important for the efficiencies of database construction, training and storage. Our previously developed linear low-dimension ventilation model (LLVM) is able to convert high-resolution CFD data into low-dimension grid levels, facilitated the use of fast prediction for ventilation online control. However, limitation still exists considering the dilemma of prediction speed and accuracy, e.g., case of a larger building space. This is due to the neglect of volume contribution ratio from single mesh as well as correlations of cells information when using uniform low-dimension methods. Therefore, we proposed a self-adaptive non-uniform low-dimension model for the data conversion but using lower dimension size with acceptable accuracy. The open-source CFD platform OpenFOAM was used for the package development, called self-adaptive low-dimension tool (LDT), including two modules, i.e., ‘non-uniform dividing’ and ‘self-update’. Error index was defined considering the contribution ratio of individual mesh volume. A series of cases were carried out for demonstration and evaluation. It is found that the proposed model is able to largely improve the data accuracy but with smaller dimension requirement compared to uniform dividing method (e.g., with comparable error index around 16.5% when using zone numbers of 80 for non-uniform and 210 for uniform). Moreover, the self-update module enables users to efficiently and automatically identify the optimal low-dimension zone numbers. This work can be of great importance for the application of CFD-AI techniques.

[1]  J. Templeton,et al.  Reynolds averaged turbulence modelling using deep neural networks with embedded invariance , 2016, Journal of Fluid Mechanics.

[2]  Dong Liu,et al.  CFD study on gaseous pollutant transmission characteristics under different ventilation strategies in a typical chemical laboratory , 2017 .

[3]  Cheuk Ming Mak,et al.  Short-term mechanical ventilation of air-conditioned residential buildings: A general design framework and guidelines , 2016 .

[4]  Yong Cheng,et al.  Modeling non-uniform thermal environment of stratum ventilation with supply and exit air conditions , 2018, Building and Environment.

[5]  Prashant Kumar,et al.  Indoor air quality and energy management through real-time sensing in commercial buildings , 2016 .

[6]  Samuel Geniaut,et al.  Improved adaptive mesh refinement for conformal hexahedral meshes , 2016, Adv. Eng. Softw..

[7]  Zhiqiang Zhai,et al.  Advances in building simulation and computational techniques: A review between 1987 and 2014 , 2016 .

[8]  Zhuangbo Feng,et al.  Fast prediction for indoor environment: Models assessment , 2019, Indoor and Built Environment.

[9]  Qingyan Chen.  COMPARISON OF DIFFERENT k-ε MODELS FOR INDOOR AIR FLOW COMPUTATIONS , 1995 .

[10]  Xiaoying Wu,et al.  Integrated analysis of CFD data with K-means clustering algorithm and extreme learning machine for localized HVAC control , 2015 .

[11]  H. Pedersen,et al.  Feasibility of Deep Neural Network Surrogate Models in Fluid Dynamics , 2019, Modeling, Identification and Control: A Norwegian Research Bulletin.

[12]  S. Hanini,et al.  Particle dispersion modeling in ventilated room using artificial neural network , 2016 .

[13]  Chen Ren,et al.  Development and application of linear ventilation and temperature models for indoor environmental prediction and HVAC systems control , 2019, Sustainable Cities and Society.

[14]  Wei Wang,et al.  Energy efficient HVAC control for an IPS-enabled large space in commercial buildings through dynamic spatial occupancy distribution , 2017 .

[15]  Samrendra Singh,et al.  1D/3D transient HVAC thermal modeling of an off-highway machinery cabin using CFD-ANN hybrid method , 2018 .

[16]  Chuck Wah Yu,et al.  Ventilation online monitoring and control system from the perspectives of technology application , 2019, Indoor and Built Environment.

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

[18]  Zhuangbo Feng,et al.  Study on the impacts of human walking on indoor particles dispersion using momentum theory method , 2017 .

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

[20]  Dong Yang,et al.  Dimensionless design approach, applicability and energy performance of stack-based hybrid ventilation for multi-story buildings , 2015 .

[21]  Teng Long,et al.  Wind field reconstruction using dimension-reduction of CFD data with experimental validation , 2018 .

[22]  Salvatore Carlucci,et al.  The impact of design ventilation rates on the indoor air quality in residential buildings: An Italian case study , 2017 .

[23]  Xiao Qian,et al.  Heat dissipation optimization of lithium-ion battery pack based on neural networks , 2019, Applied Thermal Engineering.

[24]  Johan Meyers,et al.  Asymptotic conditions for the use of linear ventilation models in the presence of buoyancy forces , 2014 .

[25]  Feng Qian,et al.  Three dimensional gas dispersion modeling using cellular automata and artificial neural network in urban environment , 2018, Process Safety and Environmental Protection.

[26]  Jie Ren,et al.  Incorporating online monitoring data into fast prediction models towards the development of artificial intelligent ventilation systems , 2019, Sustainable Cities and Society.

[27]  Tian-hu Zhang,et al.  The use of genetic algorithm and self-updating artificial neural network for the inverse design of cabin environment , 2017 .

[28]  Yelin Deng,et al.  Impact of ventilation rates on indoor thermal comfort and energy efficiency of ground-source heat pump system , 2018 .

[29]  Norhayati Mahyuddin,et al.  A Review of CO2 Measurement Procedures in Ventilation Research , 2012 .

[30]  Tom Ben-David,et al.  Sensor networks for routine indoor air quality monitoring in buildings: Impacts of placement, accuracy, and number of sensors , 2018 .

[31]  Mengxuan Song,et al.  A neural-network enhanced modeling method for real-time evaluation of the temperature distribution in a data center , 2019, Neural Computing and Applications.

[32]  Zhuangbo Feng,et al.  Influence of air change rates on indoor CO2 stratification in terms of Richardson number and vorticity , 2018 .

[33]  Shi-Jie Cao,et al.  Challenges of using CFD simulation for the design and online control of ventilation systems , 2018, Indoor and Built Environment.

[34]  Sara Omrani,et al.  Effect of natural ventilation mode on thermal comfort and ventilation performance: Full-scale measurement , 2017 .

[35]  Andreas Athienitis,et al.  Virtual measurement of the air properties in air-handling units (AHUs) or virtual re-calibration of sensors , 2018, Science and Technology for the Built Environment.

[36]  Qingxin Zhao,et al.  Control of a novel synthetical index for the local indoor air quality by the artificial neural network and genetic algorithm , 2019, Sustainable Cities and Society.

[37]  Masoud Rahimi,et al.  Computational fluid dynamics assists the artificial neural network and genetic algorithm approaches for thermal and flow modeling of air-forced convection on interrupted plate fins , 2016 .

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

[39]  Shengtai Li,et al.  Comparison of refinement criteria for structured adaptive mesh refinement , 2010, J. Comput. Appl. Math..

[40]  Shi-Jie Cao,et al.  Implementation and visualization of artificial intelligent ventilation control system using fast prediction models and limited monitoring data , 2020 .