[HTML][HTML] Closed-loop optimisation of neural networks for the design of feedback policies under uncertainty

EM Turan, J Jäschke - Journal of Process Control, 2024 - Elsevier
Solving model predictive control (MPC) problems online can be computationally intractable,
especially when considering uncertainty and nonlinear systems. One approach to avoid this …

Closed-loop training of static output feedback neural network controllers for large systems: A distillation case study

EM Turan, J Jäschke - arXiv preprint arXiv:2402.19309, 2024 - arxiv.org
The online implementation of model predictive control for constrained multivariate systems
has two main disadvantages: it requires an estimate of the entire model state and an …

[PDF][PDF] Learning convex objectives to reduce the complexity of model predictive control

EM Turan, Z Mdoe, J Jäschke - arXiv preprint arXiv:2312.02650, 2023 - researchgate.net
For large systems that consider uncertainty the online solution of model predictive control
problems can be computationally taxing, and even infeasible. This can be offset by using a …

[PDF][PDF] Implementing Neural Network-based Control Policy for Nonlinear Compressor Surge Control

H Dawlatshahi - 2024 - ntnuopen.ntnu.no
Denne masteroppgaven utforsker implementeringen av en kontrollpolitikk basert på nevrale
nettverk for ̊a evaluere ytelsen til kontrollsystemet. Tradisjonelle modell-prediktiv kontroll …