zurück zur Liste

P

Johannes Pohlodek

Arbeitsgebiet(e)

Machine learning and estimation; Process engineering of biotechnological processes; Model-based concepts for process control, optimization and analysis

Kontakt

work +49 6151 16-25177

Work S3|10 518
Landgraf-Georg-Str. 4
64283 Darmstadt

Datengetriebene Modellierung dynamischer Systeme

Modellbildung, Simulation und Optimierung

Control of Distributed Cyber-Physical Systems

Thema Typ Status
Two-degrees-of-freedom (2DOF) Controller for Speed Regulation of a DC Motor (wird in neuem Tab geöffnet) Bachelorarbeit offen
Split-range Control for Applications with 2 Manipulated Control Variables (wird in neuem Tab geöffnet) Bachelorarbeit offen
Gaussian Process Regression for Big Data (wird in neuem Tab geöffnet) Masterarbeit in Bearbeitung
Sparse Identification of Nonlinear Dynamics for Model Predictive Control (wird in neuem Tab geöffnet) (Co-Betreuer: Rudolph Kok) Masterarbeit in Bearbeitung
Bayesian Optimization of Battery Fast-charging Protocols (wird in neuem Tab geöffnet) (Co-Betreuer: Joachim Schaeffer) Masterarbeit abgeschlossen
Catching Objects with a Robot Arm (wird in neuem Tab geöffnet) (Co-Betreuer: Alexander Rose, Philipp Holzmann) Projektseminar abgeschlossen
Reinforcement Learning for Control of Bioreactors (wird in neuem Tab geöffnet)
(Co-Betreuer: Sebstián Espinel Ríos) 		Masterarbeit abgeschlossen
Control of a Partial Differential Equation System Using Physics-informed Neural Networks (wird in neuem Tab geöffnet) (Co-Betreuer: Rudolph Kok) Masterarbeit abgeschlossen
Physics-informed Training of Neural Networks for Control of a Bioreactor (wird in neuem Tab geöffnet) (Co-Betreuer: Sebstián Espinel Ríos) Masterarbeit abgeschlossen
Control of a Partial Differential Equation System Using Recurrent Neural Networks (wird in neuem Tab geöffnet) (Co-Betreuer: Rudolph Kok) Projektseminar abgeschlossen
Autotuning eines modellbasierten Zwei-Freiheitsgrade-Reglers (2DOF) (wird in neuem Tab geöffnet) (Co-Betreuerin: Lena Kranert) Projektseminar abgeschlossen
Zeitschriftenartikel
[4] L. Kranert, J. Pohlodek, S. Duvigneau, A. Rose, L. Carius, A. Kienle, and R. Findeisen, „Step experiments enable efficient exploration of microbial microaerobic steady states,“ submitted. Authorea: 10.22541/au.167700378.88413405/v1
[3] S. Espinel-Ríos, G. Behrendt, J. Bauer, B. Morabito, J. Pohlodek, A. Schütze, R. Findeisen, K. Bettenbrock, S. Klamt, „Experimentally implemented dynamic optogenetic optimization of ATPase expression using knowledge-based and Gaussian-process-supported models,“ accepted. arXiv: 2401.08556
[2] J. Pohlodek, B. Morabito, C. Schlauch, P. Zometa, and R. Findeisen, „Flexible development and evaluation of machine-learning-supported optimal control and estimation methods via HILO-MPC,“ International Journal of Robust and Nonlinear Control, 2024. doi: 10.1002/rnc.7275
[1] S. Espinel-Ríos, B. Morabito, J. Pohlodek, K. Bettenbrock, S. Klamt, and R. Findeisen, „Toward a modeling, optimization, and predictive control framework for fed-batch metabolic cybergenetics,“ Biotechnology and Bioengineering, vol. 121, no. 1, pp. 366–379, 2024. doi: 10.1002/bit.28575
Konferenzbeiträge
[7] S. Hirt, A. Höhl, J. Schaeffer, J. Pohlodek, R. D. Braatz, and R. Findeisen, „Learning Model Predictive Control Parameters via Bayesian Optimization for Battery Fast Charging,“ 2024, 12th IFAC Symposium on Advanced Control of Chemical Processes ADCHEM 2024, accepted.
[6] J. Pohlodek, H. Alsmeier, B. Morabito, C. Schlauch, A. Savchenko, and R. Findeisen, „Stochastic Model Predictive Control Utilizing Bayesian Neural Networks,“ in 2023 American Control Conference (ACC). IEEE, 2023, pp. 603–608. doi: 10.23919/ACC55779.2023.10156115
[5] S. Espinel-Ríos, B. Morabito, J. Pohlodek, K. Bettenbrock, S. Klamt, and R. Findeisen, „Optimal control and dynamic modulation of the ATPase gene expression for enforced ATP wasting in batch fermentations,“ IFAC-PapersOnLine, vol. 55, no. 7, pp. 174–180, 2022, 13th IFAC Symposium on Dynamics and Control of Process Systems, including Biosystems DYCOPS 2022. doi: 10.1016/j.ifacol.2022.07.440
[4] B. Morabito, J. Pohlodek, L. Kranert, S. Espinel-Ríos, and R. Findeisen, „Efficient and Simple Gaussian Process Supported Stochastic Model Predictive Control for Bioreactors using HILO-MPC,“ IFAC-PapersOnLine, vol. 55, no. 7, pp. 922–927, 2022, 13th IFAC Symposium on Dynamics and Control of Process Systems, including Biosystems DYCOPS 2022. doi: 10.1016/j.ifacol.2022.07.562
[3] B. Morabito, J. Pohlodek, J. Matschek, A. Savchenko, L. Carius, and R. Findeisen, „Towards Risk-aware Machine Learning Supported Model Predictive Control and Open-loop Optimization for Repetitive Processes,“ IFAC-PapersOnLine, vol. 54, no. 6, pp. 321–328, 2021, 7th IFAC Conference on Nonlinear Model Predictive Control NMPC 2021. doi: 10.1016/j.ifacol.2021.08.564
[2] J. Pohlodek, A. Rose, B. Morabito, L. Carius, and R. Findeisen, „Data-driven Metabolic Network Reduction for Multiple Modes Considering Uncertain Measurements,“ IFAC-PapersOnLine, vol. 53, no. 2, pp. 16866–16871, 2020, 21st IFAC World Congress. doi: 10.1016/j.ifacol.2020.12.1215
[1] L. Carius, J. Pohlodek, B. Morabito, A. Franz, M. Mangold, R. Findeisen, and A. Kienle, „Model-based State Estimation Based on Hybrid Cybernetic Models,“ IFAC-PapersOnLine, vol. 51, no. 18, pp. 197–202, 2018, 10th IFAC Symposium on Advanced Control of Chemical Processes ADCHEM 2018. doi: 10.1016/j.ifacol.2018.09.299