Dr.-Ing. Janine Lins
Curriculum Vitae
| Born | April 20th, 1994 in Bochum (Germany) |
| 2004-2012 | Graf-Engelbert Schule, Bochum (Germany) |
| 2012-2016 | B.Sc. Biochemical Engineering Studies, TU Dortmund University Bachelor Thesis: Cost evaluation for the transesterification of racemic 1-phenylethanol in a stirred tank |
| 2014 | Semester abroad at University of Pennsylvania (USA) |
| 2016-2018 | M.Sc. Chemical Engineering Studies, TU Dortmund University Master Thesis: Optimal shared resource allocation in uncertain networks |
| 2018-2021 | PhD at the Laboratory of Plant and Process Design, TU Dortmund University Field of Research: Investigation of agglomeration processes during organic compound crystallization |
Field of Research
The demand for specific, tailor made crystalline products in the chemical, pharmaceutical and food industry is steadily increasing. Whenever high demands are placed on the product, the focus must already be on crystallization, because here the particulate properties are initially defined.
Agglomeration is a phenomenon in crystallization and in the subsequent solid liquid separation and drying which influences key characteristics of the crystals. Therefore, it is of vital importance to investigate and control agglomeration during crystallization. Nevertheless, it is still often considered as incidental phenomenon occurring alongside nucleation and growth and is not fully understood. A promising opportunity to enhance the fundamental understanding of agglomeration on the microscopic scale are imaging techniques. However, there are also some challenges related to image acquisition during the process and to image processing. In recent years, Convolutional Neural Networks (CNNs) have been increasingly used to make image processing more accurate and faster so that a step has been made towards real-time monitoring
Publications
Dissertation
- J. Lins
Image Analysis for Sophisticated Particle Characterization of Crystalline Products
TU Dortmund, 2023, Verlag Dr. Hut, München, ISBN 978-3-8439-5342-9
Paper
- J. Lins, T. Harweg, F. Weichert, K. Wohlgemuth
Potential of Deep Learning Methods for Deep Level Particle Characterization in Crystallization
Applied Sciences 12, 5 (2022), 2465, doi.org/10.3390/app12052465
- J. Lins, S. Heisel, K. Wohlgemuth
Quantification of internal crystal defects using image analysis
Powder Technology 377 (2021) 733-738, doi.org/10.1016/j.powtec.2020.09.015
- M. Wierschem, A. Langen, J. Lins, R. Spitzer, M. Skiborowski
Model validation for enzymatic reactive distillation to produce chiral compound
Journal of Chemical Technology & Biotechnology 93 (2), (2018) 498–507, //doi.org/10.1002/jctb.5380
Oral presentations
- Janine Lins; Ute Ebeling; Hessam Ramezani; Kerstin Wohlgemuth
On the choice of image analysis sensor for the study of phenomena during crystallization
Jahrestreffen der ProcessNet Fachgruppe Kristallisation 2021 (digital)
- J. Lins, C. Schwenk, T. Dahlmanns, F. Weichert, K. Wohlgemuth
Artificial intelligence- the manifold opportunities using deep convolutional neural networks for image analysis during crystallization
Jahrestreffen der ProcessNet Fachgruppe Kristallisation 2020 (digital)
- J. Lins, F. Weichert, K. Wohlgemuth
Particle classification during crystallization using deep convolutional neural networks
Workshop Deep Learning- What is Deep Learning and where in the (Chemical) Process Industry can it be applied?, Dortmund (2020)
Poster presentations
- J.Lins, S.Heisel, S.Krause, K.Wohlgemuth
Identification of primary particles in agglomerates
Jahrestreffen der ProcessNet Fachgruppe Kristallisation 2019, Bamberg