In-situ multi-phase flow imaging for particle dynamic tracking and characterization: Advances and applications

J Liu, W Kuang, J Liu, Z Gao, S Rohani… - Chemical Engineering …, 2022 - Elsevier
Real-time chemical process monitoring, analysis, and control have become increasingly
important to multi-phase flow process research and development and attracted overt …

Enhanced sustainability with crystallization in continuous flow

P Neugebauer, S Soritz, JG Khinast… - Current Opinion in …, 2024 - Elsevier
At a time of rising raw material and energy prices, as well as growing awareness of the
green transition approach, sustainability is becoming an increasingly important issue in the …

Investigation of transfer learning for image classification and impact on training sample size

W Zhu, B Braun, LH Chiang, JA Romagnoli - Chemometrics and Intelligent …, 2021 - Elsevier
Recent developments in deep learning have brought huge breakthroughs in the image
processing area, which triggered numerous successful applications and positively impacted …

In Situ Imaging Combined with Deep Learning for Crystallization Process Monitoring: Application to Cephalexin Production

H Salami, MA McDonald, AS Bommarius… - … Process Research & …, 2021 - ACS Publications
The online detection of a trace amount of an undesired solid phase within a crystal slurry
can enable feedback control to improve product purity, decrease batch rejection, and …

Learning to navigate a crystallization model with deep reinforcement learning

V Manee, R Baratti, JA Romagnoli - Chemical Engineering Research and …, 2022 - Elsevier
In this work, a combination of a Convolutional Neural Network (CNN) based measurement
sensor and a reinforcement learning (RL) framework that speeds up the control loop is …

Deep learning-based oriented object detection for in situ image monitoring and analysis: A process analytical technology (PAT) application for taurine crystallization

Y Wu, Z Gao, S Rohani - Chemical Engineering Research and Design, 2021 - Elsevier
Image analysis enables the estimation of critical process properties such as crystal size,
morphology, and crystallization kinetics. Despite the rich image information, the lack of a …

Harnessing Birefringence for Real-Time Classification of Molecular Crystals Using Dynamic Polarized Light Microscopy, Microfluidics, and Machine Learning

AYH Chua, EWQ Yeap, DM Walker… - Crystal Growth & …, 2024 - ACS Publications
Molecular crystals are ubiquitous in a variety of industrial contexts, from foods to chemicals
and pharmaceuticals. The timely identification of different molecular crystal forms (and …

Particle characterization with on-line imaging and neural network image analysis

Y Wu, M Lin, S Rohani - Chemical Engineering Research and Design, 2020 - Elsevier
We proposed a deep learning-based in situ microscopic image analysis system for detecting
particles and performing size analysis in a high-density slurry, which shows great potential …

Process analytical technology in Downstream-Processing of Drug Substances–A review

P Neugebauer, M Zettl, D Moser, J Poms… - International Journal of …, 2024 - Elsevier
Abstract Process Analytical Technology (PAT) has revolutionized pharmaceutical
manufacturing by providing real-time monitoring and control capabilities throughout the …

Machine learning-based protein crystal detection for monitoring of crystallization processes enabled with large-scale synthetic data sets of photorealistic images

D Bischoff, B Walla, D Weuster-Botz - Analytical and Bioanalytical …, 2022 - Springer
Since preparative chromatography is a sustainability challenge due to large amounts of
consumables used in downstream processing of biomolecules, protein crystallization offers …