Search

In the absence of experimental air filtration test data, it is difficult to predict the air filtration efficiency and airflow resistance of filter media. In this novel work, an effort is undertaken to predict the air filtration efficiency and airflow resistance of filter media based solely on scanning electron microscopy (SEM) images of the filter fabric. The analytical single fiber efficiency (SFE) model is incorporated into a machine-learning model designed to analyze digital imagery. A convolutional neural network (CNN) is developed and optimized using synthetic training data produced from digital replication of air filter media. Simulated air filter media were created to replicate the physical characteristics of actual nonwoven nanofibrous air filter media. Digital grayscale images of the simulated media provided the input data for the CNN. Analytical calculations of efficiency and resistance based on the SFE model provided target data for the CNN. The regression model included seven convolution layers and two hidden fully connected layers along with width reduction and depth expansion methods. Twelve model parameters were optimized using training and validation data of 2100 iterations of simulated media. The model was then employed to predict the air filtration behavior of actual air filter media based on an SEM image of the media. The resulting predictions of air filtration efficiency and airflow resistance based solely on an SEM image suggests the potential viability of using synthetic data derived from simulated media to train machine learning models for real-world applications. To the knowledge of the authors, this is the first such application of a CNN to predict air filtration efficiency and airflow resistance using an SEM image, synthetic data created from simulated media, and the SFE analytical model. • Convolutional neural networks enable prediction of air filtration efficiency. • Analytical single fiber efficiency models are applied to simulated media. • Computer vision with CNNs enables prediction of airflow pressure resistance. • Machine learning modeling with CNNs will advance the science of air filtration. [ABSTRACT FROM AUTHOR]

Fibrous filters are commonly utilized to remove aerosols from the air to capture contaminants and pollutants prior to atmospheric release, or to clean atmospheric air itself. An ideal filter achieves the highest capture efficiency possible while providing the least airflow resistance possible. From this, the ability to predict how a filter operates based upon its functional parameters, such as filtration velocity and particle size and type, and characteristic parameters, such as its fiber size and media porosity, are integral to not only properly applying and estimating filter performance, but also facilitating the improvement and development of filtration technology. The purpose of this work is to review both classical and contemporary particle loading models to provide a comprehensive discussion built upon a foundation of first principles. The different relevant particle capture mechanisms are presented and discussed in terms of fibrous air filtration, along with the separate loading regimes. Specific loading models are then introduced considering these concepts and are separated into three categories: 1) analytical models, 2) computational models, and 3) experimental models. In short summary, analytical models have been well-covered and benefit from their ease of use but suffer from a difficulty in describing the stochastic nature of realistic particle loading. Computational models benefit from their inherent incorporation of first principles thereby addressing the dynamic nature of particle loading, however they may be difficult to apply outside of research environments due to their complexity and computationally demanding nature. Experimental models benefit from the avoidance of simplifying assumptions and the ability to correlate data describing phenomena that are difficult to quantify but are limited to applications covered by their experimental parameters and have difficulty addressing anomalies that present themselves. Suggested future work from identified research gaps focus on the lack of available data and reliable methods to measure media characteristics as well as developing models that predict the full spectrum of the loading process based upon media and particle characteristics. • Particle loading models predict filter performance from factors such as loaded mass. • Prevalent work is categorized as analytical, computational, or experimental. • Included models are presented in terms of foundational particle capture mechanisms. • Strengths and weaknesses of the model categories are presented and discussed. • Future work is identified through current research gaps. [ABSTRACT FROM AUTHOR]