Search

Your search keyword '"Lang, Sebastian"' showing total 265 results
Start Over Author "Lang, Sebastian"
265 results on '"Lang, Sebastian"'

1. Methoden des bestärkenden Lernens für die Produktionsablaufplanung

Author

Lang, Sebastian

Subjects
Produktion, Künstliche Intelligenz, Reinforcement Learning, Logistik, Maschinelles Lernen, Scheduling, bic Book Industry Communication::U Computing & information technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning, bic Book Industry Communication::T Technology, engineering, agriculture::TG Mechanical engineering & materials::TGP Production engineering
Abstract

In diesem Open-Access-Buch wird eine Methode zur Adaption, Integration und Anwendung von bestärkenden Lernverfahren (Reinforcement Learning) für die Produktionsablaufplanung beschrieben. Die Methode wird anhand von typischen Problemstellungen der Produktionsablaufplanung hergeleitet und evaluiert. Die Produktionsablaufplanung ist eine Kernaufgabe der Produktion und Logistik, bei welcher Aufträge auf Ressourcen so verteilt und in Reihenfolge gebracht werden müssen, dass geforderte Nebenbedingungen der Planung erfüllt werden. Entsprechende Optimierungsprobleme sind meist NP-schwer, wodurch eine optimale Lösung gewöhnlich nicht unter wirtschaftlichen Bedingungen erzielbar ist. In der Industrie werden stattdessen Prioritätsregeln, Heuristiken oder Metaheuristiken verwendet, die entweder zeiteffizient zu Lasten der Lösungsgüte rechnen oder qualitativ hochwertige Lösungen unter hohem Rechenaufwand erzeugen. Das bestärkende Lernen ist eine Unterart des maschinellen Lernens und eine weitere Klasse potenzieller Lösungsstrategien. Probleme der Produktionsablaufplanung sind insoweit vergleichbar, als dass sie sich ebenfalls als stufenartige Entscheidungsketten modellieren lassen. Trotz ihrer Vorteile existiert bisher kaum allgemeines Wissen hinsichtlich der Anwendung des bestärkenden Lernens für die Produktionsablaufplanung.

Published
2023
Full Text
View/download PDF

16. Static force characteristic of annular gaps -- Experimental and simulation results

Author

Kuhr, Maximilian M. G., Lang, Sebastian R., and Pelz, Peter F.

Subjects
Physics - Fluid Dynamics
Abstract

We discuss the static force characteristic of annular gaps resulting from an axial flow component. So far there is a severe lack of understanding of the flow inside the annulus. First, the state-of-the-art modelling approaches to describe the flow inside the annulus are recapped and discussed. The discussion focuses in particular on the modelling of inertia effects. Second, a new calculation method, the Clearance-Averaged Pressure Model (CAPM) is presented. The CAPM uses an integro-differential approach in combination with power law ansatz functions for the velocity profiles and a Hirs' model to calculate the resulting pressure field. Third, for experimental validation, a setup is presented using magnetic bearings to inherently measure the position as well as the force on the rotor induced by the flow field inside the gap. The experiments focus on the characteristic load behaviour, attitude angle and pressure difference across the annulus. Fourth, the experimental results are compared to the calculation results., Comment: Pre-validation chapter was added. Order of magnitude analysis for the hydrodynamic entrance length was added in chapter II. Layout of the pre-print was changed

Published
2021
Full Text
View/download PDF

27. A review on reinforcement learning algorithms and applications in supply chain management.

Author

Rolf, Benjamin, Jackson, Ilya, Müller, Marcel, Lang, Sebastian, Reggelin, Tobias, and Ivanov, Dmitry

Subjects
MACHINE learning, SUPPLY chain management, INVENTORY control, LITERATURE reviews, REINFORCEMENT learning, SUPPLY chains
Abstract

Decision-making in supply chains is challenged by high complexity, a combination of continuous and discrete processes, integrated and interdependent operations, dynamics, and adaptability. The rapidly increasing data availability, computing power and intelligent algorithms unveil new potentials in adaptive data-driven decision-making. Reinforcement Learning, a class of machine learning algorithms, is one of the data-driven methods. This semi-systematic literature review explores the current state of the art of reinforcement learning in supply chain management (SCM) and proposes a classification framework. The framework classifies academic papers based on supply chain drivers, algorithms, data sources, and industrial sectors. The conducted review revealed a few critical insights. First, the classic Q-learning algorithm is still the most popular one. Second, inventory management is the most common application of reinforcement learning in supply chains, as it is a pivotal element of supply chain synchronisation. Last, most reviewed papers address toy-like SCM problems driven by artificial data. Therefore, shifting to industry-scale problems will be a crucial challenge in the next years. If this shift is successful, the vision of data-driven decision-making in real-time could become a reality. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

28. Design of a Li-Fi Transceiver for Distributed Factory Planning Applications

Author

Mukku, Vasu Dev, Lang, Sebastian, Reggelin, Tobias, Reichardt, Paul, Rannenberg, Kai, Editor-in-Chief, Soares Barbosa, Luís, Editorial Board Member, Goedicke, Michael, Editorial Board Member, Tatnall, Arthur, Editorial Board Member, Neuhold, Erich J., Editorial Board Member, Stiller, Burkhard, Editorial Board Member, Tröltzsch, Fredi, Editorial Board Member, Pries-Heje, Jan, Editorial Board Member, Kreps, David, Editorial Board Member, Reis, Ricardo, Editorial Board Member, Furnell, Steven, Editorial Board Member, Mercier-Laurent, Eunika, Editorial Board Member, Winckler, Marco, Editorial Board Member, Malaka, Rainer, Editorial Board Member, Dolgui, Alexandre, editor, Bernard, Alain, editor, Lemoine, David, editor, von Cieminski, Gregor, editor, and Romero, David, editor

Published
2021
Full Text
View/download PDF

43. Consumer-Driven API Testing with Performance Contracts

Author

Stählin, Johannes, Lang, Sebastian, Kajzar, Fabian, Zirpins, Christian, Barbosa, Simone Diniz Junqueira, Series editor, Chen, Phoebe, Series editor, Filipe, Joaquim, Series editor, Kotenko, Igor, Series editor, Sivalingam, Krishna M., Series editor, Washio, Takashi, Series editor, Yuan, Junsong, Series editor, Zhou, Lizhu, Series editor, Lazovik, Alexander, editor, and Schulte, Stefan, editor

Published
2018
Full Text
View/download PDF

49. Metamodelling of Inventory-Control Simulations Based on a Multilayer Perceptron

Author

Jackson Ilya, Tolujevs Jurijs, Lang Sebastian, and Kegenbekov Zhandos

Subjects
metamodelling, simulation, inventory control, artificial neural network, industrial artificial intelligence, Transportation and communication, K4011-4343
Abstract

Inventory control problems arise in various industries, and each single real-world inventory is replete with non-standard factors and subtleties. Practical stochastic inventory control problems are often analytically intractable, because of their complexity. In this regard, simulation-optimization is becoming more and more popular tool for solving complicated business-driven problems. Unfortunately, simulation, especially detailed, is both time and memory consuming. In the light of this fact, it may be more reasonable to use an alternative cheaper-to-compute metamodel, which is specifically designed in order to approximate an original simulation. In this research we discus metamodelling of stochastic multiproduct inventory control system with perishable products using a multilayer perceptron with a rectified linear unit as an activation function.

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results