Deep learning to develop zero-equation based turbulence model for CFD simulations of the built environment

This study aims to improve the accuracy and speed of predictions for thermal comfort and air quality in built environments by creating a coupled framework between computational fluid dynamics(CFD)simulations and deep learning models.The coupling approach is showcased by the development of a data-driven turbulence model.The new turbulence model is built using a deep learning neural network,whose mapping structure is based on a zero-equation turbulence model for built environment simulations,and is coupled with the CFD software OpenFOAM to create a hybrid framework.The neural network is a standard shallow multi-layer perceptron.The number of hidden layers and nodes per layer was optimized using Bayesan optimization algorithm.The framework is trained on an indoor environment case study,as well as tested on an indoor office simulation and an outdoor building array simulation.Results show that the deep learning based turbulence model is more robust and faster than traditional two-equation Reynolds average Navier-Stokes(RANS)turbulence models,while maintaining a similar level of accuracy.The model also outperforms the standard algebraic zero-equation model due to its superior ability to generalize to various flow scenarios.Despite some challenges,namely the mapping constraint,the limited training dataset size and the source of generation of training data,the hybrid framework demonstrates the viability of the coupling technique and serves as a starting point for future development of more reliable and advanced models.

CFD modeling of dynamic airflow and particle transmission in an aircraft lavatory

Lavatories are frequently used facilities,especially on long-haul flights.Flushing a vacuum toilet in a lavatory can induce strong airflow,produce aerosols in the toilet bowl,and resuspend deposited particles from the floor.However,the exact particle transport routes and the fates of particle after toilet flushing are unclear so far.This investigation used computational fluid dynamics(CFD)to model the transient airflow and pollutant transport after a toilet flushing process in a lavatory of a commercial aircraft.The time-varying pressure profile measured in a laboratory was assigned to the drainage valve as boundary conditions.The aerosols generated inside the toilet bowl during flushing and the particles resuspended from the lavatory floor were used as particle sources.Lagrangian tracking of airborne particles in the lavatory was conducted.In addition,ammonia gas was used to examine odor perception.The multi-physics software program COMSOL 5.4 was employed for numerical solution after being validated.The results revealed that more than 70%of the generated particles in the toilet bowl are drained into sewage.A few particles may leak out of the toilet bowl and remain suspended in the air for more than five minutes when the toilet lid is open during flushing.Flushing the toilet with a closed lid can effectively reduce the particle leakage and the spread of odor gas,but it leads to greater deposition of particles on both the lid and seat.There is a slight inhalation exposure risk in the initial three minutes after flushing with a closed lid.

Simulation study of the purification system for indoor oil mist control in machining factories

High-concentration oil mists can cause serious health problems to workers,which are generally mitigated by ventilation and purification systems.However,the coupling relationship between these systems is not clear.In this study,the effects of purifier outlet direction,purification air volume,installation height,and purification efficiency on indoor oil mist distribution were investigated by numerical simulation using an actual machining factory.The mitigation of oil mist in various combinations of ventilation and purification systems was also discussed.The results show that the outlet direction of the purifier has a great influence on the distribution of oil mist in the factory,and the maximum difference of oil mist concentration in the breathing zone under different orientations is 17%.The best purifier outlet direction is vertically upward.When the purifier outlet direction is upward,a larger purification air volume is beneficial for contaminant removal,and a lower purifier exhaust installation height is helpful for oil mist discharge from the bottom of the factory and reducing the concentration of oil mist in the breathing area.The oil mist concentration of purifier exhaust increases from 0 to 2 mg/m^(3) and the oil mist concentration in the breathing zone increases by 67%.The combined system of purification system with the roof exhaust system and displacement ventilation system has the optimal pollution removal efficiency and the lowest concentration of oil mist in the breathing zone compared to other systems.The research results can provide a reference for the design,installation,and operation of ventilation and purification systems in machining factories.