
Particle Size Recognition By Deterministic Approaches And Deep Neural Networks Using Astigmatic Particle Tracking Velocimetry (APTV)
S. Sachs (1), M. Ratz (1), P. Mäder (2), J. König (1), C. Cierpka (1)
(1) Institute of Thermodynamics and Fluid Mechanics, Technische Universität Ilmenau, Germany
(2) Group for Software Engineering for Safety-Critical Systems, Technische Universität Ilmenau, Germany
DOI:
The systematic manipulation of components of multimodal particle solutions is a key for the design of modern industrial products and pharmaceuticals with highly customized properties. In order to optimize innovative particle separation devices on the micron scale, a particle size recognition with simultaneous volumetric position determination is essential. In this study, the astigmatism particle tracking velocimetry (APTV) is extended by two deterministic approaches and a deep neural network (DNN) to include size classification of particles of multimodal size distribution. Without any adaptation of the existing measurement setup, a reliable classification of bimodal particle solutions in the size range of 1.14 µm to 5.03 µm is demonstrated with a precision of up to 99.8 %. Concurrently, the high detection rate of the particles is quantified by a recall of 97.6 %. Once various outlier criteria are optimized based on the discrimination of images of bimodal particle mixtures, the application to multimodal classification is performed. The fluorescent polystyrene particles are distinguished into four classes with a precision of up to 99.3 %, while a recall of 91.7 % is maintained. The obtained results demonstrate the capability of a reliable particle size recognition using a standard APTV setup for microfluidics. The introduced algorithms allow a low-cost extension of APTV to particle solutions with multimodal size distribution, which does not require the use of different fluorescent dyes for each particle species. Furthermore, the training of the DNN is based on flow measurements, which can be integrated into the measurement procedure with reasonable effort and do not require rather time consuming measurements of sedimented particles as usual.
