Zobrazeno 1 - 10
of 146
pro vyhledávání: '"Dahmen, Manuel"'
Time-series information needs to be incorporated into energy system optimization to account for the uncertainty of renewable energy sources. Typically, time-series aggregation methods are used to reduce historical data to a few representative scenari
Externí odkaz:
http://arxiv.org/abs/2411.14320
Autor:
Velioglu, Mehmet, Zhai, Song, Rupprecht, Sophia, Mitsos, Alexander, Jupke, Andreas, Dahmen, Manuel
In chemical engineering, process data are expensive to acquire, and complex phenomena are difficult to fully model. We explore the use of physics-informed neural networks (PINNs) for modeling dynamic processes with incomplete mechanistic semi-explici
Externí odkaz:
http://arxiv.org/abs/2406.01528
We present a method for end-to-end learning of Koopman surrogate models for optimal performance in a specific control task. In contrast to previous contributions that employ standard reinforcement learning (RL) algorithms, we use a training algorithm
Externí odkaz:
http://arxiv.org/abs/2403.14425
Autor:
Germscheid, Sonja H. M., Nilges, Benedikt, von der Assen, Niklas, Mitsos, Alexander, Dahmen, Manuel
This work studies synergies arising from combining industrial demand response and local renewable electricity supply. To this end, we optimize the design of a local electricity generation and storage system with an integrated demand response scheduli
Externí odkaz:
http://arxiv.org/abs/2401.12759
Autor:
Hilger, Hannes, Witthaut, Dirk, Dahmen, Manuel, Gorjao, Leonardo Rydin, Trebbien, Julius, Cramer, Eike
Trading on the day-ahead electricity markets requires accurate information about the realization of electricity prices and the uncertainty attached to the predictions. Deriving accurate forecasting models presents a difficult task due to the day-ahea
Externí odkaz:
http://arxiv.org/abs/2311.14033
(Economic) nonlinear model predictive control ((e)NMPC) requires dynamic models that are sufficiently accurate and computationally tractable. Data-driven surrogate models for mechanistic models can reduce the computational burden of (e)NMPC; however,
Externí odkaz:
http://arxiv.org/abs/2308.01674
Autor:
Doncevic, Danimir T., Mitsos, Alexander, Guo, Yue, Li, Qianxiao, Dietrich, Felix, Dahmen, Manuel, Kevrekidis, Ioannis G.
Meta-learning of numerical algorithms for a given task consists of the data-driven identification and adaptation of an algorithmic structure and the associated hyperparameters. To limit the complexity of the meta-learning problem, neural architecture
Externí odkaz:
http://arxiv.org/abs/2211.12386
Autor:
Schweidtmann, Artur M., Rittig, Jan G., Weber, Jana M., Grohe, Martin, Dahmen, Manuel, Leonhard, Kai, Mitsos, Alexander
Publikováno v:
Computers and Chemical Engineering Volume 172, April 2023, 108202
Graph neural networks (GNNs) are emerging in chemical engineering for the end-to-end learning of physicochemical properties based on molecular graphs. A key element of GNNs is the pooling function which combines atom feature vectors into molecular fi
Externí odkaz:
http://arxiv.org/abs/2207.13779
Publikováno v:
Machine Learning and Hybrid Modelling for Reaction Engineering, Royal Society of Chemistry, ISBN 978-1-83916-563-4, 159-181, 2023
Molecular property prediction is of crucial importance in many disciplines such as drug discovery, molecular biology, or material and process design. The frequently employed quantitative structure-property/activity relationships (QSPRs/QSARs) charact
Externí odkaz:
http://arxiv.org/abs/2208.04852
Publikováno v:
Computers & Chemical Engineering 171, 108153, 2023
Ionic liquids (ILs) are important solvents for sustainable processes and predicting activity coefficients (ACs) of solutes in ILs is needed. Recently, matrix completion methods (MCMs), transformers, and graph neural networks (GNNs) have shown high ac
Externí odkaz:
http://arxiv.org/abs/2206.11776