Die Industrie 5.0 fordert neue Lernansätze und zeitgleich auch passende Lernumgebungen. Parallel müssen diese neben den didaktischen Herausforderungen auch den Transfer- und Übertragungsgedanken auf die industriellen Anwendungen gerecht werden. Durch die täglich steigende Anzahl vielfältiger KI-Tools insbesondere textgenerierenden Tools, braucht es Systeme mit einem breiten Anwendungsbereich. Im Rahmen des vorliegenden Beitrags geben die Autoren einen Einblick in die Wildauer Smart Production, welche den transdisziplinären Gedanken von Lern- und Transferumgebungen Rechnung trägt, Möglichkeiten der Gestaltung komplexer Produktionssysteme widerspiegelt, die Integration menschzentrierter Ansätze ermöglicht und als Forschungsumgebung eingesetzt wird.

The global value creation networks have experienced increased volatility and dynamic behavior in recent years, resulting in an acceleration of a trend already evident in the shortening of product and technology cycles. In addition, the manufacturing industry is demonstrating a trend of allowing customers to make specific adjustments to their products at the time of ordering. Not only do these changes require a high level of flexibility and adaptability from the cyber-physical systems, but also from the employees and the supervisory production planning. As a result, the development of control and monitoring mechanisms becomes more complex. It is also necessary to adjust the production process dynamically if there are unforeseen events (disrupted supply chains, machine breakdowns, or absences of staff) in order to make the most effective and efficient use of the available production resources. In recent years, reinforcement learning (RL) research has gained increasing popularity in strategic planning as a result of its ability to handle uncertainty in dynamic environments in real time. RL has been extended to include multiple agents cooperating on complex tasks as a solution to complex problems. Despite its potential, the real-world application of multi-agent reinforcement learning (MARL) to manufacturing problems, such as flexible job-shop scheduling, has been less frequently approached. The main reason for this is most of the applications in this field are frequently subject to specific requirements as well as confidentiality obligations. Due to this, it is difficult for the research community to obtain access to them, which presents substantial challenges for the implementation of these tools. ...

The manufacturing industry is competitive and is constantly striving to improve OEE. In the transition to smart production, digital technologies such as IIoT are highlighted as important. IIoT platforms enable real-time monitoring. In this sense, digital technologies such as IIoT are expected to improve OEE by enabling the analysis of real-time data and production availability.  A qualitative study with an abductive approach has been conducted. The empirical material has been collected through a case study of a heavy-duty vehicle industry and the theoretical framework is based on a literature study. Lastly, a thematic analysis has been used for the derivation of appropriate themes for analysis. The study concluded that challenges and enablers related to the implementation of IIoT to improve OEE can be divided into technical and cultural factors. Technical challenges and enablers mainly consider the achievement of interoperability, compatibility, and cyber security, while cultural factors revolve around digital acceptance, competence, encouragement of digital curiosity, and creating knowledge and understanding towards OEE. Lastly, conclusions can be drawn that implementation of IIoT has a positive effect on OEE since it ensures consistent and accurate data, which lies a solid foundation for production decisions. Also, digitalization of production enhances lean practices which are considered a key element for improving OEE.

Tesis por compendio / [ES] Los sistemas tradicionales de planificación y control de la producción (PPC) se centran en producir lo que demanda el mercado, con la calidad, el calendario y los volúmenes previstos al mínimo coste, ajustándose al mismo tiempo a las disrupciones de la cadena de suministro. La exploración e implementación de nuevos avances tecnológicos en el marco de la industria 4.0 (I4.0), como sistemas ciberfísicos (CPS), fabricación en la nube (CMfg), fabricación aditiva (AM), big data, inteligencia artificial y la Internet de las cosas (IoT), podrían cambiar aspectos organizativos tales como las responsabilidades de PPC. En este contexto, no se identificaron estudios sobre un sistema para la toma de decisiones, arquitecturas y marcos conceptuales para los nuevos sistemas inteligentes de PPC e I4.0. En este contexto de nuevos cambios tecnológicos y organizativos a los que tienen que hacer frente las pequeñas y medianas empresas (PYMEs), surge el problema de diseñar herramientas de PPC que permitan la integración y colaboración de las operaciones de producción. Así, basándose en las nuevas tecnologías de producción digital y en las herramientas organizativas que darán soporte a las fábricas inteligentes conectadas del futuro, se identificó la falta de un sistema integrado de PPC e I4.0. Esta tesis doctoral es un compendio de artículos que abordan una amplia revisión bibliográfica sobre la PPC en un entorno de I4.0. También, se propone un marco conceptual y el diseño de modelos y algoritmos para la toma de decisiones y dar soporte a las funciones de PPC en un contexto digital I4.0 basado en las nuevas tecnologías de producción digital y herramientas organizativas que darán soporte a las fábricas inteligentes colaborativas y conectadas del futuro. Los modelos matemáticos y algoritmos propuestos se centran en resolver el problema del diseño y planificación de una cadena de suministro sostenible y resiliente en la que las decisiones estratégicas y tácticas se toman de forma integrada. Los modelos, algoritmos y método de resolución se han programado en Python. Los modelos han sido validados mediante un software que genera instancias de datos sintéticos y permite evaluar la complejidad computacional de los mismos. El desarrollo de este tipo de modelos y algoritmos supone una contribución al ámbito académico e investigador y, concretamente, en el área de PPC. / [CA] En l'actualitat, els sistemes tradicionals de planificació i control de la producció (PPC) se centren en produir el que demanda el mercat, amb la qualitat, el calendari i els volums previstos al mínim cost, ajustant-se al mateix temps a les pertorbacions. L'exploració i implementació de nous avanços tecnològics, com CPS, fabricació en el núvol (CMfg), fabricació additiva (AM), big data, intelligència artificial i el IoT, podrien canviar aspectes organitzatius, com les responsabilitats de PPC. En aquest context, no es van identificar estudis sobre un sistema per a la presa de decisions, arquitectures i marcs conceptuals per als nous sistemes intelligents de PPC i I4.0. En aquest context de nous canvis tecnològics i organitzatius als quals han de fer front les petites i mitjanes empreses (PIME), sorgeix el problema de dissenyar eines de PPC que permeten la integració i collaboració de les operacions de producció. Així, basant-se en les noves tecnologies de producció digital i en les eines organitzatives que donaran suport a les fàbriques intelligents connectades del futur, es va identificar la falta d'un sistema integrat de la PPC i I4.0. Aquesta investigació és un compendi d'articles que aborden una àmplia revisió bibliogràfica sobre la PPC en un entorn I4.0. També proposa un marc conceptual i el disseny de models i algorismes per a la presa de decisions i per a donar suport a les funcions de PPC en un context digital I4.0 basat en les noves tecnologies de producció digital i eines organitzatives que donaran suport a les fàbriques intelligents col·laboratives i connectades del futur. Els models matemàtics i algorismes proposats se centren en resoldre el problema del disseny d'una cadena de subministrament sostenible i resistent en la qual les decisions estratègiques i tàctiques es prenen de forma integrada. Els models, algorismes i mètode de resolució s'han programat en Python. Els models han sigut validats mitjançant un programari que genera instàncies de dades sintètiques i permet avaluar la complexitat computacional dels models. El desenvolupament d'aquesta mena de models i algorismes suposa una important contribució a l'àmbit acadèmic. / [EN] Currently, traditional production planning and control (PPC) systems focus on producing what the market demands with the expected quality, schedule and volumes at a minimum cost, while adjusting for disruption. The exploration and implementation of new technological advances, such as CPS, cloud manufacturing (CMfg), additive manufacturing (AM), big data, artificial intelligence and the Internet of Things (IoT), could change organisational aspects like PPC responsibilities. In this context, no studies on a system for decision making, architectures and conceptual frameworks for the new intelligent systems of PPC and industry 4.0 (I4.0) have been identified. In this context of new technological and organisational changes that small-and medium-sized enterprises (SMEs) have to face, the problem of designing PPC tools that enable the integration and collaboration of production operations arises. Thus, based on the new digital production technologies and organisational tools that will support the connected smart factories of the future, lack of an integrated PPC and I4.0 system was identified. The present doctoral thesis is a compendium of articles addressing a comprehensive literature review on PPC in an I4.0 environment. It also proposes a conceptual framework and the design of models and algorithms for decision making and to support PPC functions in a digital I4.0 context based on the new digital production technologies and organisational tools that will support the collaborative and connected smart factories of the future. The proposed mathematical models and algorithms focus on solving the problem of designing a sustainable and resilient supply chain where strategic and tactical decisions are made in an integrated way. The models, algorithms and resolution method have been programmed in Python. The models have been validated by means of software that generates synthetic data instances and allows the models' computational complexity to be evaluated. The development of this type of models and algorithms is a significant contribution to the academic field. / I would like to thank the following projects and universities for having financed the publications included in this doctoral thesis: • European Commission Horizon 2020 project entitled "Crop diversification and low-input farming cross Europe: From practitioners' engagement and ecosystems services to increased revenues and value chain organisation' (Diverfarming), grant agreement 728003. • Spanish Ministry of Science, Innovation and Universities project entitled 'Optimization of zero-defect production technologies enabling supply chains 4.0 (CADS4.0)' (RTI2018-101344-B-I00). • European Union H2020 program with grant agreement no. 958205 "Industrial Data Services for Quality Control in Smart Manufacturing (i4Q)". • European Union H2020 Program with grant agreement nº 825631 "Zero- Defect Manufacturing Platform (ZDMP)". / Cañas Sánchez, HE. (2023). Models, Algorithms and Digital Technologies for the Automation and Collaboration of Connected Smart Factories in an Industry 4.0 Environment [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/202312 / Compendio