@article{YuwonoHussainSchwungetal.2025, author = {Yuwono, Steve and Hussain, Ahmar Kamal and Schwung, Dorothea and Schwung, Andreas}, title = {Self-optimization in distributed manufacturing systems using Modular State-based Stackelberg games}, series = {Journal of Manufacturing Systems}, volume = {80}, journal = {Journal of Manufacturing Systems}, publisher = {Elsevier}, issn = {0278-6125}, doi = {10.1016/j.jmsy.2025.03.025}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-55471}, pages = {578 -- 594}, year = {2025}, abstract = {In this study, we introduce Modular State-based Stackelberg Games (Mod-SbSG), a novel game structure developed for distributed self-learning in modular manufacturing systems. Mod-SbSG enhances cooperative decision-making among self-learning agents within production systems by integrating State-based Potential Games (SbPG) with Stackelberg games. This hierarchical structure assigns more important modules of the manufacturing system a first-mover advantage, while less important modules respond optimally to the leaders' decisions. This decision-making process differs from typical multi-agent learning algorithms in manufacturing systems, where decisions are made simultaneously. We provide convergence guarantees for the novel game structure and design learning algorithms to account for the hierarchical game structure. We further analyse the effects of single-leader/multiple-follower and multiple-leader/multiple-follower scenarios within a Mod-SbSG. To assess its effectiveness, we implement and test Mod-SbSG in an industrial control setting using two laboratory-scale testbeds featuring sequential and serial parallel processes. The proposed approach delivers promising results compared to the vanilla SbPG, which reduces overflow by 97.1\%, and in some cases, prevents overflow entirely. Additionally, it decreases power consumption by 5\%-13\% while satisfying the production demand, which significantly improves potential (global objective) values.}, subject = {Intelligente Fertigung}, language = {en} } @article{YuwonoSchwungSchwung2025, author = {Yuwono, Steve and Schwung, Andreas and Schwung, Dorothea}, title = {Integrating Deep Model-Based Learning With Modular State-Based Stackelberg Games for Self-Optimizing Distributed Production Systems}, series = {IEEE Transactions on Cybernetics}, journal = {IEEE Transactions on Cybernetics}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, issn = {2168-2267}, doi = {10.1109/TCYB.2025.3610707}, pages = {12}, year = {2025}, subject = {Intelligente Fertigung}, language = {en} } @article{YuwonoSchwungSchwung2025, author = {Yuwono, Steve and Schwung, Dorothea and Schwung, Andreas}, title = {Automated leaders and followers selection in Stackelberg games for modular manufacturing systems}, series = {Journal of Intelligent Manufacturing}, journal = {Journal of Intelligent Manufacturing}, publisher = {Springer Nature}, issn = {0956-5515}, doi = {10.1007/s10845-025-02650-0}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-57990}, year = {2025}, abstract = {We propose an automated data-driven mechanism to evaluate each actuator's influence on modular manufacturing system objectives. This mechanism enables automated leader and follower selection in Stackelberg games, which have gained traction in engineering. While leaders typically hold greater priority or influence, systematic methods for assigning leaders and followers remain limited, especially in large-scale applications. As a result, many rely on empirical analysis to assign leaders and followers, without confirming if the selected setup is optimal. Therefore, in this paper, we develop an automated mechanism to evaluate the influence of each player on the global objectives of modular manufacturing systems, applicable to both single- and multi-objective scenarios. We validate the proposed approach within an industrial control scenario, using a modular Bulk Good System and its larger-scale arrangement with sequential and serial-parallel processes. We focus on three objectives, including production flow disruption prevention, power consumption reduction, and production demand fulfilment. Finally, we implement a self-learning algorithm utilizing Modular State-based Stackelberg Games, where leaders and followers are selected using our approach, which leads to encouraging results.}, subject = {Industrie 4.0}, language = {en} }