Predicting airflow distribution and contaminant transport in aircraft cabins with a simplified gasper model

This study investigated the air distribution and contaminant transport in aircraft cabins with gaspers by using computational fluid dynamics (CFD). If the detailed gasper geometry were used in the CFD simulations, the grid number would be unacceptably high. To reduce the grid number, this investigation proposed a method for simplifying the gasper geometry. The method was then validated by two sets of experimental data obtained from a cabin mockup and a real aircraft cabin. It was found that for the cabin mockup, the CFD simulation with the simplified gasper model reduced the grid number from 1.58 to 0.3 million and the computing cost from 2 days to 1 hour without compromising the accuracy. In the five-row economy-class cabin of the MD-82 airplane, the CFD simulation with the simplified gasper model was acceptable in predicting the distribution of air velocity, air temperature, and contaminant concentration.     

Prediction of temperature and velocity profiles in a single compartment fire by an improved neural network analysis

A novel hybrid Artificial Neural Network (ANN) model, denoted GRNNFA, has been developed for fire studies. The major feature of the model is its ability to work in a noisy environment, which is usually the case with fire experiment data. The GRNNFA model is applicable in the determination of the location of the thermal interface in a single compartment fire. The performance of the GRNNFA has been proven to be comparable to that of the Computational Fluid Dynamics (CFD) model. In addition, the computational speed of the GRNNFA model is much faster than that of the CFD model. However, the original GRNNFA model is only capable of handling the training samples with scalar output. This shortcoming restricts the application area of the model. Hence, this paper presents a modification of the original GRNNFA model for multi-dimensional prediction problems. It also demonstrates the first application of ANN techniques to predicting the velocity and temperature profiles at the center of the doorway in a single compartment fire. These profiles are commonly used to benchmark the performances of CFD models. They are employed in this study to evaluate the performance of the modified GRNNFA model. The predicted profiles are compared with the experimental results and the results simulated by the CFD model. These results show that the prediction errors of the GRNNFA model are less than those of the CFD model in actual application.     

Optimization of ventilation systems in office environment,Part II: Results and discussions

Whether one considers the issues related to office workers' well-being and productivity or the issues from an energy and environmental perspective, there are clear evidences in favor of improving the quality of office environment. Part I of this paper proposed a simulation-based optimization approach by using computational fluid dynamics (CFD) techniques in conjunction with genetic algorithm (GA), with the integration of an artificial neural network (ANN) for response surface approximation (RSA) and for speeding up fitness evaluations inside GA loop. In this part, the results from data preparation for ANN model construction, ANN training and testing, and sensitivity analysis (regarding the impact of weighting factors in the objective function on the optimization results) are presented. Final optimization results indicate that the present choices of objective function and optimization approach are able to result in great improvement in the design and operation of ventilation systems in an office environment, with the goal of enhancing the thermal comfort and indoor air quality (IAQ) without sacrificing the energy costs of ventilation.     

Modeling dynamic responses of aircraft environmental control systems by coupling with cabin thermal environment simulations

Commercial aircraft use environmental control systems (ECSs) to control the thermal environment in cabins and thus ensure passengers’ safety, health, and comfort. This study investigated the interaction between ECS operation and cabin thermal environment. Simplified models were developed for the thermodynamic processes of the key ECS components in a commercial software program, ANSYS Simplorer. A computational fluid dynamics (CFD) program, ANSYS Fluent, was employed to simulate the thermal environment in a cabin. Through the coupling of Simplorer and Fluent, a PID control method was applied to the aircraft ECS in Simplorer to achieve dynamic control of the temperature of the supply air to the cabin, which was used as a Fluent input. The calculated supply air temperature agreed with the corresponding experimental data obtained from an MD-82 aircraft on the ground. The coupled model was then used to simulate a complete flight for the purpose of studying the interaction between ECS operation and the cabin thermal environment. The results show that the PID controller in the ECS can maintain the cabin air temperature within ±0.6 K of the set point, with an acceptable air temperature distribution. The coupled models can be used for the design and analysis of the ECS and cabin thermal environment for commercial airplanes.     

Comparison of different decontaminant delivery methods for sterilizing unoccupied commercial airliner cabins

Effective decontamination is crucial if an airliner cabin is contaminated by biological contaminants, such as infectious disease viruses or intentionally released biological agents. This study used computational fluid dynamics (CFD) method as a tool and vaporized hydrogen peroxide (VHP) as an exemplary decontaminant and Geobacillus stearothermophilus spores as a simulant contaminant to investigate three VHP delivery methods for sterilizing two different airliner cabins. The CFD first determined the airflow and the transient distributions of the contaminant and decontaminant in cabins. Auxiliary equations were implemented into the CFD model for evaluating efficacy of the sterilization process. The improved CFD model was validated by the measured airflow and simulated contaminant distributions obtained from a cabin mockup and the measured efficacy data from the literature. The three decontaminant delivery methods were (1) to supply the mixed VHP and air through the environmental control system of a cabin, (2) to send mixed VHP and air through a front door and to extract them from a back door of a cabin, and (3) to send directly VHP to a cabin and enhance the mixing with air in the cabin by fans. The two air cabins studied were a single-aisle and a twin-aisle airliner one. The results show that the second decontaminant delivery method (displacement method) was the best because the VHP distributions in the cabins were most uniform, the sterilization time was moderate, and the corrosion risk was low. The method displaced the existing air by the air/disinfectant solution, rather than dispersive mixing as the other two methods.     

Performance evaluation of air distribution systems in three different China railway high-speed train cabins using numerical simulation

Air distribution system is very important to indoor air quality (IAQ) in China railway high-speed (CRH) train cabin. Air distribution systems in three different CRH train cabins are simulated and evaluated in this paper by using the computational fluid dynamic (CFD) method. CFD models of CRH1, CRH2 and CRH5 train cabins are developed and validated basing on the field experiments in three train cabins. Flow field, temperature field, and airflow pattern in the three train cabins are investigated respectively by using the CFD models developed. Four improved performance indexes which can eliminate influences of geometric dimension are utilized to evaluate the air distribution systems in the cabins. The cough droplets dispersion processes inside the CRH train cabins are simulated to investigate the cough droplets removal ability. Simulation results show that good airflow pattern is very critical to guarantee the uniform distribution of flow field, temperature field and thermal comfort in the train cabin. The air distribution system employed in CRH5 train cabin is the most efficient among the three train cabins. Moreover, CRH5 train cabin has stronger cough droplets removal ability than CRH1 and CRH2 train cabins. Air distribution system in CRH5 train cabin should be adopted in the next generation CRH train cabin in the future.     

基于ANN吸收式冷水机组模型的遗传算法最优控制

文章讨论了吸收式溴化锂冷水机组目前在其系统控制上存在经典控制理论无法解决的问题,所以提出采用人工智能领域的技术来实现它的控制方案,其中结合了遗传算法和神经网络的优点。文章还探讨了如何有效的实现这种结合,并将其运用到实际的模拟控制中,实现最优化控制。同时,分别就可能的最优化控制方案与标准控制方案进行比较,文中给出各种最优化控制方案的性能。     

Novel air distribution systems for commercial aircraft cabins

Air distribution systems in commercial aircraft cabins are important for providing a healthy and comfortable environment for passengers and crew. The mixing air distribution systems used in existing aircraft cabins create a uniform air temperature distribution and dilute contaminants in the cabins. The mixing air distribution systems could spread infectious airborne diseases. To improve the air distribution system design for aircraft cabins, this investigation proposed an under-floor displacement air distribution system and a personalized air distribution system. This study first validated a computational fluid dynamics (CFD) program with the experimental data of airflow, air temperature, and tracer-gas concentration from an environmental chamber. Then the validated CFD program was used to calculate the distributions of the air velocity, air temperature, and CO₂ concentration in a section of Boeing 767 aircraft cabin with the mixing, under-floor displacement, and personalized air distribution systems, respectively. By comparing the air and contaminant distributions in the cabin, this study concluded that the personalized air distribution system provided the best air quality without draft risk.     

Predicting transient particle transport in enclosed environments with the combined computational fluid dynamics and Markov chain method

To quickly obtain information about airborne infectious disease transmission in enclosed environments is critical in reducing the infection risk to the occupants. This study developed a combined computational fluid dynamics (CFD) and Markov chain method for quickly predicting transient particle transport in enclosed environments. The method first calculated a transition probability matrix using CFD simulations. Next, the Markov chain technique was applied to calculate the transient particle concentration distributions. This investigation used three cases, particle transport in an isothermal clean room, an office with an underfloor air distribution system, and the first‐class cabin of an MD‐82 airliner, to validate the combined CFD and Markov chain method. The general trends of the particle concentrations vs. time predicted by the Markov chain method agreed with the CFD simulations for these cases. The proposed Markov chain method can provide faster‐than‐real‐time information about particle transport in enclosed environments. Furthermore, for a fixed airflow field, when the source location is changed, the Markov chain method can be used to avoid recalculation of the particle transport equation and thus reduce computing costs.     

On-line building energy prediction using adaptive artificial neural networks

While most of the existing artificial neural networks (ANN) models for building energy prediction are static in nature, this paper evaluates the performance of adaptive ANN models that are capable of adapting themselves to unexpected pattern changes in the incoming data, and therefore can be used for the real-time on-line building energy prediction. Two adaptive ANN models are proposed and tested: accumulative training and sliding window training. The computational experiments presented in the paper use both simulated (synthetic) data and measured data. In the case of synthetic data, the accumulative training technique appears to have an almost equal performance with the sliding window training approach, in terms of training time and accuracy. In the case of real measurements, the sliding window technique gives better results, compared with the accumulative training, if the coefficient of variance is used as an indicator.     

Deep neural network with high‐order neuron for the prediction of foamed concrete strength

The article presents a deep neural network model for the prediction of the compressive strength of foamed concrete. A new, high‐order neuron was developed for the deep neural network model to improve the performance of the model. Moreover, the cross‐entropy cost function and rectified linear unit activation function were employed to enhance the performance of the model. The present model was then applied to predict the compressive strength of foamed concrete through a given data set, and the obtained results were compared with other machine learning methods including conventional artificial neural network (C‐ANN) and second‐order artificial neural network (SO‐ANN). To further validate the proposed model, a new data set from the laboratory and a given data set of high‐performance concrete were used to obtain a higher degree of confidence in the prediction. It is shown that the proposed model obtained a better prediction, compared to other methods. In contrast to C‐ANN and SO‐ANN, the proposed model can genuinely improve its performance when training a deep neural network model with multiple hidden layers. A sensitivity analysis was conducted to investigate the effects of the input variables on the compressive strength. The results indicated that the compressive strength of foamed concrete is greatly affected by density, followed by the water‐to‐cement and sand‐to‐cement ratios. By providing a reliable prediction tool, the proposed model can aid researchers and engineers in mixture design optimization of foamed concrete.     

浅埋地下工程间歇空调最优启停时间的神经网络控制

将影响最优启停时间的四个主要因素作为控制输入,最优启停时间作为系统输出,建立了最优启停时间的神经网络预测模型。分析了考虑岩土蓄热作用下室内热环境的变化,应用CFD模拟软件建立了采用间歇空调时室内空气与周围岩土的耦合传热模型,将模拟所得数据用来训练神经网络模型,得出的最优模型可用于预测各种复杂的非线性条件下的最优启停时间。通过一小型系统模型验证了该神经网络控制的有效性。     

Feasibility of utilizing numerical viscosity from coarse grid CFD for fast turbulence modeling of indoor environments

Computational fluid dynamics (CFD) is a useful tool in building indoor environment study. However, the notorious computational effort of CFD is a significant drawback that restricts its applications in many areas and stages. Factors such as grid resolution and turbulence modeling are the main reasons that lead to large computing cost of this method. This study investigates the feasibility of utilizing inherent numerical viscosity induced by coarse CFD grid, coupled with simplest turbulence model, to greatly reduce the computational cost while maintaining reasonable modeling accuracy of CFD. Numerical viscosity introduced from space discretization in a carefully specified coarse grid resolution may have similar magnitude as turbulence viscosity for typical indoor airflows. This presents potentials of substituting sophisticated turbulence models with inherent numerical viscosity models from coarse grid CFD that are often used in fast CFD analysis. Case studies were conducted to validate the analytical findings, by comparing the coarse grid CFD predictions with the grid-independent CFD solutions as well as experimental data obtained from literature. The study shows that a uniform coarse grid can be applied, along with a constant turbulence viscosity model, to reasonably predict general airflow patterns in typical indoor environments. Although such predictions may not be as precise as fine-grid CFDs with well validated complex turbulence models, the accuracy is acceptable for indoor environment study, especially at an early stage of a project. The computing speed is about 100 times faster than a fine-grid CFD, which makes it possible to simulate a complicated 3-dimensional building in real-time (or near real-time) with personal computer.     

ANN and ANFIS performance prediction models for hydraulic impact hammers

Hydraulic impact hammers are mechanical excavators that can be used in tunneling projects economically under geologic conditions suitable for rock breakage by indentation. However, there is relatively less published material in the literature in relation to predicting the performance of that equipment employing rock properties and machine parameters. In tunnel excavation projects, there is often a need for accurate prediction the performance of such machinery. The poor prediction of machine performance can lead to very costly contractual claims. In this study, the application of soft computing methods for data analysis called artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) to predict the net breaking rate of an impact hammer is demonstrated. The prediction capabilities offered by ANN and ANFIS were shown by using field data of obtained from metro tunnel project in Istanbul, Turkey. For this purpose, two prediction models based on ANN and ANFIS were developed and the results obtained from those models were then compared to those of multiple regression-based predictions. Various statistical performance indexes were used to compare the performance of those prediction models. The results suggest that the proposed ANFIS-based prediction model outperforms both ANN model and the classical multiple regression-based prediction model, and thus can be used to produce a more accurate and reliable estimate of impact hammer performance from Schmidt hammer rebound hardness (SHRH) and rock quality designation (RQD) values obtained from the field tests.     

Inverse design of an indoor environment using a filter-based topology method with experimental verification

In order to create a healthy, comfortable, productive, and energy-efficient indoor environment, the computational fluid dynamics (CFD)-based adjoint method with an area-constrained topology method can be used to inversely design the optimal number, size, location, and shape of air supply inlets and air supply parameters. However, this method is not very mature, and the distribution of retained inlets is always scattered. To solve that problem, this investigation introduced a filter method that smooths the intermediate results during the inverse design process. Using a three-dimensional, non-isothermal, asymmetrical office with pre-set air supply inlets as an example, this study verified the performance of the proposed filter-based topology method. The verified method was then used to solve a multi-objective design problem and design an optimal indoor environment for a room. The results indicate that the proposed method was able to find the optimal number, location, and shape of air supply inlets and the optimal air supply temperature, velocity, and angle that led to a thermally comfortable, healthy, productive, and energy-efficient indoor environment. Finally, this investigation installed the optimal inlets in an environmental chamber to mimic the room. The measured air temperature, velocity, and mean age of air in several typical locations in the environmental chamber matched the CFD simulation results very closely.     

Optimization of ventilation system design and operation in office environment,Part I: Methodology

Ventilation principles that integrate flexible and responsive elements have grown in popularity in office buildings due to increasing concerns about the impact of indoor environment quality on office workers' well-being and productivity, as well as concerns over the rising energy costs for space heating and cooling in the office building sector. Such advanced elements as underfloor air distribution (UFAD), passive swirl diffusers, and demand controlled ventilation have posed challenges to system design and operation. This paper is concerned with the development and implementation of a practical and robust optimization scheme, aiming to assist office building designers and operators to enhance thermal comfort and indoor air quality (IAQ) without sacrificing energy costs of ventilation. The objective function was constructed in a way attempting to aggregate and weight indices (for thermal comfort, IAQ, and ventilation energy usage assessment) into one indicator. The path taken was a simulation-based optimization approach by using computational fluid dynamics (CFD) techniques in conjunction with genetic algorithm (GA), with the integration of an artificial neural network (ANN) for response surface approximation (RSA) and for speeding up fitness evaluations inside GA loop.     

Assessing artificial neural network performance for predicting interlayer conditions and layer modulus of multi-layered flexible pavement

The objective of this study is to evaluate the performance of the artificial neural network (ANN) approach for predicting interlayer conditions and layer modulus of a multi-layered flexible pavement structure. To achieve this goal, two ANN based back-calculation models were proposed to predict the interlayer conditions and layer modulus of the pavement structure. The corresponding database built with ANSYS based finite element method computations for four types of a structure subjected to falling weight deflectometer load. In addition, two proposed ANN models were verified by comparing the results of ANN models with the results of PADAL and double multiple regression models. The measured pavement deflection basin data was used for the verifications. The comparing results concluded that there are no significant differences between the results estimated by ANN and double multiple regression models. PADAL modeling results were not accurate due to the inability to reflect the real pavement structure because pavement structure was not completely continuous. The prediction and verification results concluded that the proposed back-calculation model developed with ANN could be used to accurately predict layer modulus and interlayer conditions. In addition, the back-calculation model avoided the back-calculation errors by considering the interlayer condition, which was barely considered by former models reported in the published studies.     

Predicting the capacity of perfobond rib shear connector using an ANN model and GSA method

Due to recent advances in the field of artificial neural networks (ANN) and the global sensitivity analysis (GSA) method, the application of these techniques in structural analysis has become feasible. A connector is an important part of a composite beam, and its shear strength can have a significant impact on structural design. In this paper, the shear performance of perfobond rib shear connectors (PRSCs) is predicted based on the back propagation (BP) ANN model, the Genetic Algorithm (GA) method and GSA method. A database was created using push-out test test and related references, where the input variables were based on different empirical formulas and the output variables were the corresponding shear strengths. The results predicted by the ANN models and empirical equations were compared, and the factors affecting shear strength were examined by the GSA method. The results show that the use of ANN model optimization by GA method has fewer errors compared to the empirical equations. Furthermore, penetrating reinforcement has the greatest sensitivity to shear performance, while the bonding force between steel plate and concrete has the least sensitivity to shear strength.     

Influence of local airflow on the pollutant emission from indoor building surfaces

This article reports the results of an investigation, based on fundamental fluid dynamics and mass transfer theory, carried out to obtain a general understanding of the mechanisms involved in the emissions from building materials in ventilated rooms. In addition, a generally applicable method for the prediction of surface emissions is proposed. The work focused on the emission of vapours and gases and no particulate emissions were considered. The methods used were numerical calculations by computational fluid dynamics (CFD) and full-scale laboratory experiments. It was found that the emissions are a strong function of air-change rate, local air velocity and local turbulence, as the mass transfer coefficient increases in proportion to these parameters. The findings further show that the mass transfer coefficient increases in proportion to the velocity when the emission is controlled by evaporation from the surface. With regard to diffusion-controlled emissions, the mass transfer coefficient is unaffected by the velocity.     

Computational fluid dynamics modelling of the air movement in an environmental test chamber with a respiring manikin

In recent years, computational fluid dynamics (CFD) has been widely used as a method of simulating airflow and addressing indoor environment problems. The complexity of airflows within the indoor environment would make experimental investigation difficult to undertake and also imposes significant challenges on turbulence modelling for flow prediction. This research examines through CFD visualization how air is distributed within a room. Measurements of air temperature and air velocity have been performed at a number of points in an environmental test chamber with a human occupant. To complement the experimental results, CFD simulations were carried out and the results enabled detailed analysis and visualization of spatial distribution of airflow patterns and the effect of different parameters to be predicted. The results demonstrate the complexity of modelling human exhalation within a ventilated enclosure and shed some light into how to achieve more realistic predictions of the airflow within an occupied enclosure.