Conference paper
Data-Driven Control Strategies for the Autonomous Operation of the Pharmaceutical Crystallization Process
KT Consortium, Department of Chemical and Biochemical Engineering, Technical University of Denmark1
PROSYS - Process and Systems Engineering Centre, Department of Chemical and Biochemical Engineering, Technical University of Denmark2
Department of Chemical and Biochemical Engineering, Technical University of Denmark3
In this contribution, we studied the deep neural network (DNN) for the control of the cooling crystallization of a model compound system. To this end, firstly the performance of the different neural network architectures in conjunction with the various combination of the time-series process data was tested for the training of the data-based model in order to assess the best fit model-training data architecture.
The identified network model, which was trained with the offline process data, was utilized in a predictive control strategy. The objective of the control strategy was to optimize the supersaturation generating/decaying variable in the crystallizer to achieve a target crystal-state property profile throughout the process.
The performance of the proposed control strategy was tested in the presence of the process disturbance and benchmarked against a radial basis function (RBF) based control strategy. The results showed that the DNN model was able to approximate the crystallization process input-output relation with R2 ranging between 0.767 and 0.990 and achieve the target profile at the end of the operation with a 22.3 % offset.
Language: | English |
---|---|
Publisher: | Elsevier |
Year: | 2021 |
Pages: | 1271-1276 |
Proceedings: | 31<sup>st</sup> European Symposium on Computer Aided Process Engineering |
Series: | Computer Aided Chemical Engineering |
ISSN: | 15707946 |
Types: | Conference paper |
DOI: | 10.1016/B978-0-323-88506-5.50196-0 |
ORCIDs: | Öner, Merve and Sin, Gürkan |