Abstract

This work presents a methodology that relies on the application of the radial basis functions network (RBF)-based feedback control algorithms to a pharmaceutical crystallization process. Within the scope of the model-based evaluation of the proposed strategy, firstly strategies for the data treatment, data structure and the training methods reflecting the possible scenarios in the industry (Moving Window, Growing Window and Golden Batch strategies) were introduced. This was followed by the incorporation of such RBF strategies within a soft sensor application and a nonlinear predictive data-driven control application. The performance of the RBF control strategies was tested for the undisturbed cases as well as in the presence of disturbances in the process. The promising results from both RBF soft sensor control and the RBF predictive control demonstrated great potential of these techniques for the control of the crystallization process. In particular, both Moving Window and Golden Batch strategies performed the best results for an RBF soft sensor, and the Growing Window outperformed the remaining methodologies for predictive control.

Highlights

  • Process and Systems Engineering Center (PROSYS), Department of Chemical and Biochemical Engineering, Abstract: This work presents a methodology that relies on the application of the radial basis functions network (RBF)-based feedback control algorithms to a pharmaceutical crystallization process

  • The Thin Plate Spline transfer function displayed an irregular behavior: despite achieving a higher coefficient of determination first, the irregular sudden decrease of its stabilization indicated that certain sets of data do not provide accurate predictions from the same transfer function nodes for the ibuprofen crystallization

  • The cross-validation score achieved its peak at around 60% of having the full set of training data, which corresponds to a better mean squared error (MSE) score of the Thin

Read more

Summary

Introduction

Within the scope of the model-based evaluation of the proposed strategy, firstly strategies for the data treatment, data structure and the training methods reflecting the possible scenarios in the industry (Moving Window, Growing Window and Golden Batch strategies) were introduced. This was followed by the incorporation of such RBF strategies within a soft sensor application and a nonlinear predictive data-driven control application. The promising results from both RBF soft sensor control and the RBF predictive control demonstrated great potential of these techniques for the control of the crystallization process Both Moving Window and Golden Batch strategies performed the best results for an RBF soft sensor, and the Growing

Objectives
Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.