Refine
H-BRS Bibliography
- yes (28)
Departments, institutes and facilities
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (28) (remove)
Document Type
- Conference Object (13)
- Part of a Book (3)
- Article (2)
- Contribution to a Periodical (2)
- Research Data (2)
- Report (2)
- Book (monograph, edited volume) (1)
- Doctoral Thesis (1)
- Lecture (1)
- Preprint (1)
Year of publication
- 2021 (28) (remove)
Has Fulltext
- no (28) (remove)
Keywords
- Automatic Differentiation (2)
- Generative Models (2)
- Network simulation (2)
- Pytorch (2)
- Quality diversity (2)
- Applications in Energy Transport (1)
- Approximate Matrix Factorization (1)
- Biokunststoff (1)
- Bioökonomie (1)
- Clustering (1)
Die nationale Politik- und Forschungsstrategie Bioökonomie sieht eine Transformation der Wirtschaft vor, bei der die Verwendung fossiler Rohstoffe zunehmend durch den Einsatz nachwachsender Rohstoffe ersetzt wird. Der Einsatz biobasierter Kunststoffe soll dabei gefördert werden. Erste Analysen der Berichterstattung zu Biokunststoffen im Rahmen einer Pilotstudie ergaben, dass der Grundgedanke biologisch abbaubarer Kunststoffe breite Zustimmung im öffentlichen Diskurs erfährt. Abseits der soziopolitischen Diskursebene entwickelt sich jedoch eine medial geführte Diskussion um erhebliche Probleme mit den Stoffen in der Abfallwirtschaft. Die Gefahr besteht nun, dass diese Haltung verbreitet durch die Massenmedien auf die öffentliche Meinung abfärbt. Mangelnde öffentliche Akzeptanz könnte den Erfolg von innovativen Biokunststoff-Produkten gefährden.
In this paper, the electrochemical alkaline methanol oxidation process, which is relevant for the design of efficient fuel cells, is considered. An algorithm for reconstructing the reaction constants for this process from the experimentally measured polarization curve is presented. The approach combines statistical and principal component analysis and determination of the trust region for a linearized model. It is shown that this experiment does not allow one to determine accurately the reaction constants, but only some of their linear combinations. The possibilities of extending the method to additional experiments, including dynamic cyclic voltammetry and variations in the concentration of the main reagents, are discussed.
Künstliche Intelligenz (KI) ist aus der heutigen Gesellschaft kaum noch wegzudenken. Auch im Sport haben Methoden der KI in den letzten Jahren mehr und mehr Einzug gehalten. Ob und inwieweit dabei allerdings die derzeitigen Potenziale der KI tatsächlich ausgeschöpft werden, ist bislang nicht untersucht worden. Der Nutzen von Methoden der KI im Sport ist unbestritten, jedoch treten bei der Umsetzung in die Praxis gravierende Probleme auf, was den Zugang zu Ressourcen, die Verfügbarkeit von Experten und den Umgang mit den Methoden und Daten betrifft. Die Ursache für die, verglichen mit anderen Anwendungsgebieten, langsame An- bzw. Übernahme von Methoden der KI in den Spitzensport ist nach Hypothese des Autorenteams auf mehrere Mismatches zwischen dem Anwendungsfeld und den KI-Methoden zurückzuführen. Diese Mismatches sind methodischer, struktureller und auch kommunikativer Art. In der vorliegenden Expertise werden Vorschläge abgeleitet, die zur Auflösung der Mismatches führen können und zugleich neue Transfer- und Synergiemöglichkeiten aufzeigen. Außerdem wurden drei Use Cases zu Trainingssteuerung, Leistungsdiagnostik und Wettkampfdiagnostik exemplarisch umgesetzt. Dies erfolgte in Form entsprechender Projektbeschreibungen. Dabei zeigt die Ausarbeitung, auf welche Art und Weise Probleme, die heute noch bei der Verbindung zwischen KI und Sport bestehen, möglichst ausgeräumt werden können. Eine empirische Umsetzung des Use Case Trainingssteuerung erfolgte im Radsport, weshalb dieser ausführlicher dargestellt wird.
Sie sind im Bereich Qualitätsmanagement tätig und haben die Aufgabe bekommen, ein Problem systematisch zu untersuchen und methodisch zu lösen? Sie haben zu viele Aufgaben und wissen nicht, wie Sie diese priorisieren sollen? Oder haben Sie zu begrenzte Ressourcen, um alle Reklamationen gleichzeitig bearbeiten zu können? Oder wissen nicht, wie Sie einen bestimmten Prozess in seinen Grenzen zielführend verbessern können?
In this thesis it is posed that the central object of preference discovery is a co-creative process in which the Other can be represented by a machine. It explores efficient methods to enhance introverted intuition using extraverted intuition's communication lines. Possible implementations of such processes are presented using novel algorithms that perform divergent search to feed the users' intuition with many examples of high quality solutions, allowing them to take influence interactively. The machine feeds and reflects upon human intuition, combining both what is possible and preferred. The machine model and the divergent optimization algorithms are the motor behind this co-creative process, in which machine and users co-create and interactively choose branches of an ad hoc hierarchical decomposition of the solution space.
The proposed co-creative process consists of several elements: a formal model for interactive co-creative processes, evolutionary divergent search, diversity and similarity, data-driven methods to discover diversity, limitations of artificial creative agents, matters of efficiency in behavioral and morphological modeling, visualization, a connection to prototype theory, and methods to allow users to influence artificial creative agents. This thesis helps putting the human back into the design loop in generative AI and optimization.
Solving transport network problems can be complicated by non-linear effects. In the particular case of gas transport networks, the most complex non-linear elements are compressors and their drives. They are described by a system of equations, composed of a piecewise linear ‘free’ model for the control logic and a non-linear ‘advanced’ model for calibrated characteristics of the compressor. For all element equations, certain stability criteria must be fulfilled, providing the absence of folds in associated system mapping. In this paper, we consider a transformation (warping) of a system from the space of calibration parameters to the space of transport variables, satisfying these criteria. The algorithm drastically improves stability of the network solver. Numerous tests on realistic networks show that nearly 100% convergence rate of the solver is achieved with this approach.
This book discusses the development of the Rosenbrock—Wanner methods from the origins of the idea to current research with the stable and efficient numerical solution and differential-algebraic systems of equations, still in focus. The reader gets a comprehensive insight into the classical methods as well as into the development and properties of novel W-methods, two-step and exponential Rosenbrock methods. In addition, descriptive applications from the fields of water and hydrogen network simulation and visual computing are presented. (Verlagsangaben)
The lattice Boltzmann method (LBM) is an efficient simulation technique for computational fluid mechanics and beyond. It is based on a simple stream-and-collide algorithm on Cartesian grids, which is easily compatible with modern machine learning architectures. While it is becoming increasingly clear that deep learning can provide a decisive stimulus for classical simulation techniques, recent studies have not addressed possible connections between machine learning and LBM. Here, we introduce Lettuce, a PyTorch-based LBM code with a threefold aim. Lettuce enables GPU accelerated calculations with minimal source code, facilitates rapid prototyping of LBM models, and enables integrating LBM simulations with PyTorch's deep learning and automatic differentiation facility. As a proof of concept for combining machine learning with the LBM, a neural collision model is developed, trained on a doubly periodic shear layer and then transferred to a different flow, a decaying turbulence. We also exemplify the added benefit of PyTorch's automatic differentiation framework in flow control and optimization. To this end, the spectrum of a forced isotropic turbulence is maintained without further constraining the velocity field.
We consider multi-solution optimization and generative models for the generation of diverse artifacts and the discovery of novel solutions. In cases where the domain's factors of variation are unknown or too complex to encode manually, generative models can provide a learned latent space to approximate these factors. When used as a search space, however, the range and diversity of possible outputs are limited to the expressivity and generative capabilities of the learned model. We compare the output diversity of a quality diversity evolutionary search performed in two different search spaces: 1) a predefined parameterized space and 2) the latent space of a variational autoencoder model. We find that the search on an explicit parametric encoding creates more diverse artifact sets than searching the latent space. A learned model is better at interpolating between known data points than at extrapolating or expanding towards unseen examples. We recommend using a generative model's latent space primarily to measure similarity between artifacts rather than for search and generation. Whenever a parametric encoding is obtainable, it should be preferred over a learned representation as it produces a higher diversity of solutions.
Die Kunst, Kunst zu zeigen
(2021)