Innovation in nonwovens analysis and optimization using artificial intelligence (AI) with GeoDict
The study of the micro-structure of the filter media is the starting point to understand, analyze and optimize a filter. The first simulation step on the media scale consists of processing of µCT-scan images of a real media to prepare a detailed 3D micro-structure model of the filter media.
µCT-scans are a powerful tool to gain deep insights and ideas for innovation and for quality control in material engineering. GeoDict provides the tools for a better understanding of CT-images and paves the way to overcome the challenges of modern material engineering. Nonwovens are used in many industries, including fibrous media for filtration, glass or carbon-fiber reinforced plastics used in mechanical applications, or gas-diffusion layers used in fuel cells.
The performance of nonwovens is governed mainly by the spatial distribution, orientation, length, curvature and center line of the individual fibers. For fibrous media with binder, the volume/weight percentage and the spatial distribution of the binder material are also essential. With GeoDict, binder can be segmented from fibers in CT-scans even if they have the same gray values.
Using nonwoven micro-structures modelled with GeoDict, a neural network is trained to label binder with artificial 3-D scans, for which the distribution of the binder is known. After the training, the neural network also recognizes the binder in 3-D scans of real nonwovens, which were scanned with µCT or FIB-SEM. The results are high-precision detection and analyses of the binder distribution in the nonwovens that occur during production.
The same method is applied to identify individual fibers in complex micro-structures. Once all fibers are identified (Fig. 1 left), detailed insights into the properties of fibers in a material are obtained. For example, the trajectory of a fiber after deposition in a nonwoven, the length of fibers in glass fiber-reinforced plastic, or local deformations of fibers in weaves.
The geometrical parameters of a filter media are identified precisely, and the fiber and pore characteristics are computed respectively. Afterwards, the fluid flow through the filter media to obtain the permeability, followed by the transport of particles and deposition of particles, are simulated with the FlowDict and FilterDict-Media modules (Fig. 1 right). The simulations provide all the specifics on deposition location, fractional filtration efficiencies and pressure drop over time . These results help filter media makers and filter element manufacturers to design and develop novel, optimized products while strongly saving in prototyping and experimental costs and time.
Speaker: Andreas Wiegmann, PhD / Math2Market GmbH
 M. Azimian, C. Kühnle, A. Wiegmann, Design and optimization of fibrous filter media using life-time multi-pass simulations, Chemical Engineering & Technology 41, No. 5 (2018) 1-9. doi.org/10.1002/ceat.201700585