Camman, J.J. (2023) Exploring the HIsarna process using SINDy-CRN. Integration Project, Industrial Engineering and Management.
|
Text
IP Final.pdf Download (6MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (130kB) |
Abstract
Abstract—This research aims to expand the current understanding of the SINDy-CRN algorithm by incorporating input, output, and noisy data. The influence of these additional parameters on the algorithm’s performance will be thoroughly examined, leading to insightful recommendations. To validate the effectiveness of these recommendations, they will be rigor- ously tested and verified using the chemical reaction network of the HIsarna process. The SINDy-CRN algorithm, which combines the Sparse Identification of Nonlinear Dynamics (SINDy) method with chemical reaction networks (CRNs), has shown promise in modeling and analyzing complex dynamical systems. However, the algorithm’s existing knowledge base primarily focuses on clean and well-controlled data. By introducing input, output, and noisy data into the SINDy-CRN algorithm, this research will investigate how these factors impact its performance. The study will explore the extent to which input variables affect the accuracy and robustness of the algorithm’s predictive capability. Additionally, the effect of noisy data on the reliability of the algorithm will be examined. Based on these finding some recommendations will be made to improve the algorithm performance. To verify the effectiveness of the recommendations, the chemical reaction network of the HIsarna process will serve as a testbed. Ultimately, this research will contribute to the advancement of the SINDy-CRN algorithm by expanding its applicability to other scenarios
| Item Type: | Thesis (Integration Project) |
|---|---|
| Supervisor name: | Jayawardhana, B. and Munoz Arias, M. |
| Degree programme: | Industrial Engineering and Management |
| Thesis type: | Integration Project |
| Language: | English |
| Date Deposited: | 09 Aug 2023 08:56 |
| Last Modified: | 09 Aug 2023 08:56 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/31112 |
Actions (login required)
 |
View Item |