Deep Learning-Based In Situ Micrograph Synthesis and Augmentation for Crystallization Process Image Analysis

Muyang Li, Tuo Yao, Jian Liu, Ziyi Liu, Zhenguo Gao () and Junbo Gong
Additional contact information
Muyang Li: State Key Laboratory of Chemical Engineering, School of Chemical Engineering and Technology, The Co-Innovation Center of Chemistry and Chemical Engineering of Tianjin, Tianjin University, Tianjin 300072, China
Tuo Yao: State Key Laboratory of Chemical Engineering, School of Chemical Engineering and Technology, The Co-Innovation Center of Chemistry and Chemical Engineering of Tianjin, Tianjin University, Tianjin 300072, China
Jian Liu: State Key Laboratory of Chemical Engineering, School of Chemical Engineering and Technology, The Co-Innovation Center of Chemistry and Chemical Engineering of Tianjin, Tianjin University, Tianjin 300072, China
Ziyi Liu: State Key Laboratory of Chemical Engineering, School of Chemical Engineering and Technology, The Co-Innovation Center of Chemistry and Chemical Engineering of Tianjin, Tianjin University, Tianjin 300072, China
Zhenguo Gao: State Key Laboratory of Chemical Engineering, School of Chemical Engineering and Technology, The Co-Innovation Center of Chemistry and Chemical Engineering of Tianjin, Tianjin University, Tianjin 300072, China
Junbo Gong: State Key Laboratory of Chemical Engineering, School of Chemical Engineering and Technology, The Co-Innovation Center of Chemistry and Chemical Engineering of Tianjin, Tianjin University, Tianjin 300072, China

Mathematics, 2024, vol. 12, issue 22, 1-16

Abstract: Deep learning-based in situ imaging and analysis for crystallization process are essential for optimizing product qualities, reducing experimental costs through real-time monitoring, and controlling the process. However, large and high-quality annotated datasets are required to train accurate models, which are time consuming. Therefore, we proposed a novel methodology that applied image synthesis neural networks to generate virtual information-rich images, enabling efficient and rapid dataset expansion while simultaneously reducing annotation costs. Experiments were conducted on the L-alanine crystallization process to obtain process images and to validate the proposed workflow. The proposed method, aided by interpolation augmentation and data warping augmentation to enhance data richness, utilized only 25% of the training annotations, consistently segmenting crystallization process images comparable to those models utilizing 100% of the training data annotations, achieving an average precision of nearly 98%. Additionally, based on the analysis of Kullback–Leibler divergence, the proposed method demonstrated excellent performance in extracting in situ information regarding aspect ratios and crystal size distributions during the crystallization process. Moreover, its ability to leverage expert labels with a four-fold enhanced efficiency holds great potential for advancing various applications in crystallization processes.

Keywords: deep learning; crystallization; in situ monitoring; image synthesis; data augmentation; data mining (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/22/3448/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/22/3448/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:22:p:3448-:d:1514173

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().