Refine
Year of publication
Document Type
- Article (9)
- Conference Proceeding (8)
- Postprint (6)
- Contribution to a Periodical (5)
- Part of a Book (1)
- Other (1)
Keywords
- deep reinforcement learning (4)
- machine learning (4)
- production control (4)
- systematic literature review (4)
- COVID-19 (3)
- Digitale Plattformen (3)
- ERP (3)
- digital learning (3)
- Geschäftsmodell (2)
- Industrie 4.0 (2)
Yes, we can (?)
(2021)
The COVID-19 crisis has caused an extreme situation for higher education institutions around the world, where exclusively virtual teaching and learning has become obligatory rather than an additional supporting feature. This has created opportunities to explore the potential and limitations of virtual learning formats. This paper presents four theses on virtual classroom teaching and learning that are discussed critically. We use existing theoretical insights extended by empirical evidence from a survey of more than 850 students on acceptance, expectations, and attitudes regarding the positive and negative aspects of virtual teaching. The survey responses were gathered from students at different universities during the first completely digital semester (Spring-Summer 2020) in Germany. We discuss similarities and differences between the subjects being studied and highlight the advantages and disadvantages of virtual teaching and learning. Against the background of existing theory and the gathered data, we emphasize the importance of social interaction, the combination of different learning formats, and thus context-sensitive hybrid learning as the learning form of the future.
In response to the impending spread of COVID-19, universities worldwide abruptly stopped face-to-face teaching and switched to technology-mediated teaching. As a result, the use of technology in the learning processes of students of different disciplines became essential and the only way to teach, communicate and collaborate for months. In this crisis context, we conducted a longitudinal study in four German universities, in which we collected a total of 875 responses from students of information systems and music and arts at four points in time during the spring–summer 2020 semester. Our study focused on (1) the students’ acceptance of technology-mediated learning, (2) any change in this acceptance during the semester and (3) the differences in acceptance between the two disciplines. We applied the Technology Acceptance Model and were able to validate it for the extreme situation of the COVID-19 pandemic. We extended the model with three new variables (time flexibility, learning flexibility and social isolation) that influenced the construct of perceived usefulness. Furthermore, we detected differences between the disciplines and over time. In this paper, we present and discuss our study’s results and derive short- and long-term implications for science and practice.
In response to the impending spread of COVID-19, universities worldwide abruptly stopped face-to-face teaching and switched to technology-mediated teaching. As a result, the use of technology in the learning processes of students of different disciplines became essential and the only way to teach, communicate and collaborate for months. In this crisis context, we conducted a longitudinal study in four German universities, in which we collected a total of 875 responses from students of information systems and music and arts at four points in time during the spring–summer 2020 semester. Our study focused on (1) the students’ acceptance of technology-mediated learning, (2) any change in this acceptance during the semester and (3) the differences in acceptance between the two disciplines. We applied the Technology Acceptance Model and were able to validate it for the extreme situation of the COVID-19 pandemic. We extended the model with three new variables (time flexibility, learning flexibility and social isolation) that influenced the construct of perceived usefulness. Furthermore, we detected differences between the disciplines and over time. In this paper, we present and discuss our study’s results and derive short- and long-term implications for science and practice.
Der Wandel zur automatisierten Produktion, die fortschreitende Digitalisierung der Wertschöpfungsprozesse sowie die stetige Implementierung von mobilen Industrial Internet of Things-Technologien (IIoT) in diese zur Unterstützung der Mitarbeiter stellen betriebliche Weiterbildung vor Herausforderungen. Komple-xere Anforderungen und veränderte Tätigkeitsprofile erfordern Handlungskom-petenzen bei Mitarbeitern im Sinne der Fähigkeit, in unbekannten Situationen auf Basis eigenen Könnens handlungsfähig zu bleiben. Jene sowie dafür notwendiges umfassendes Verständnis gegenüber digitalisierten Produktions-prozessen kann jedoch durch konventionelle Lehrmethoden nicht realisiert werden, da diese der erhöhten Anforderungskomplexität und den komplexen Rückkopplungen im Rahmen der Steuer- und Regelkreise nicht gerecht werden können. Diese Aspekte aufgreifend wird im Folgenden ein szenariobasierter Wei-terbildungsansatz für eine Lernfabrik vorgestellt, der insbesondere die Potenziale mobiler IIoT-Technologien zur Ausgestaltung dieser in den Blick nimmt.
Nowadays, production planning and control must cope with mass customization, increased fluctuations in demand, and high competition pressures. Despite prevailing market risks, planning accuracy and increased adaptability in the event of disruptions or failures must be ensured, while simultaneously optimizing key process indicators. To manage that complex task, neural networks that can process large quantities of high-dimensional data in real time have been widely adopted in recent years. Although these are already extensively deployed in production systems, a systematic review of applications and implemented agent embeddings and architectures has not yet been conducted. The main contribution of this paper is to provide researchers and practitioners with an overview of applications and applied embeddings and to motivate further research in neural agent-based production. Findings indicate that neural agents are not only deployed in diverse applications, but are also increasingly implemented in multi-agent environments or in combination with conventional methods — leveraging performances compared to benchmarks and reducing dependence on human experience. This not only implies a more sophisticated focus on distributed production resources, but also broadening the perspective from a local to a global scale. Nevertheless, future research must further increase scalability and reproducibility to guarantee a simplified transfer of results to reality.
Increasingly fast development cycles and individualized products pose major challenges for today's smart production systems in times of industry 4.0. The systems must be flexible and continuously adapt to changing conditions while still guaranteeing high throughputs and robustness against external disruptions. Deep reinforcement learning (RL) algorithms, which already reached impressive success with Google DeepMind's AlphaGo, are increasingly transferred to production systems to meet related requirements. Unlike supervised and unsupervised machine learning techniques, deep RL algorithms learn based on recently collected sensorand process-data in direct interaction with the environment and are able to perform decisions in real-time. As such, deep RL algorithms seem promising given their potential to provide decision support in complex environments, as production systems, and simultaneously adapt to changing circumstances. While different use-cases for deep RL emerged, a structured overview and integration of findings on their application are missing. To address this gap, this contribution provides a systematic literature review of existing deep RL applications in the field of production planning and control as well as production logistics. From a performance perspective, it became evident that deep RL can beat heuristics significantly in their overall performance and provides superior solutions to various industrial use-cases. Nevertheless, safety and reliability concerns must be overcome before the widespread use of deep RL is possible which presumes more intensive testing of deep RL in real world applications besides the already ongoing intensive simulations.
In nowadays production, fluctuations in demand, shortening product life-cycles, and highly configurable products require an adaptive and robust control approach to maintain competitiveness. This approach must not only optimise desired production objectives but also cope with unforeseen machine failures, rush orders, and changes in short-term demand. Previous control approaches were often implemented using a single operations layer and a standalone deep learning approach, which may not adequately address the complex organisational demands of modern manufacturing systems. To address this challenge, we propose a hyper-heuristics control model within a semi-heterarchical production system, in which multiple manufacturing and distribution agents are spread across pre-defined modules. The agents employ a deep reinforcement learning algorithm to learn a policy for selecting low-level heuristics in a situation-specific manner, thereby leveraging system performance and adaptability. We tested our approach in simulation and transferred it to a hybrid production environment. By that, we were able to demonstrate its multi-objective optimisation capabilities compared to conventional approaches in terms of mean throughput time, tardiness, and processing of prioritised orders in a multi-layered production system. The modular design is promising in reducing the overall system complexity and facilitates a quick and seamless integration into other scenarios.
In nowadays production, fluctuations in demand, shortening product life-cycles, and highly configurable products require an adaptive and robust control approach to maintain competitiveness. This approach must not only optimise desired production objectives but also cope with unforeseen machine failures, rush orders, and changes in short-term demand. Previous control approaches were often implemented using a single operations layer and a standalone deep learning approach, which may not adequately address the complex organisational demands of modern manufacturing systems. To address this challenge, we propose a hyper-heuristics control model within a semi-heterarchical production system, in which multiple manufacturing and distribution agents are spread across pre-defined modules. The agents employ a deep reinforcement learning algorithm to learn a policy for selecting low-level heuristics in a situation-specific manner, thereby leveraging system performance and adaptability. We tested our approach in simulation and transferred it to a hybrid production environment. By that, we were able to demonstrate its multi-objective optimisation capabilities compared to conventional approaches in terms of mean throughput time, tardiness, and processing of prioritised orders in a multi-layered production system. The modular design is promising in reducing the overall system complexity and facilitates a quick and seamless integration into other scenarios.
Nowadays, production planning and control must cope with mass customization, increased fluctuations in demand, and high competition pressures. Despite prevailing market risks, planning accuracy and increased adaptability in the event of disruptions or failures must be ensured, while simultaneously optimizing key process indicators. To manage that complex task, neural networks that can process large quantities of high-dimensional data in real time have been widely adopted in recent years. Although these are already extensively deployed in production systems, a systematic review of applications and implemented agent embeddings and architectures has not yet been conducted. The main contribution of this paper is to provide researchers and practitioners with an overview of applications and applied embeddings and to motivate further research in neural agent-based production. Findings indicate that neural agents are not only deployed in diverse applications, but are also increasingly implemented in multi-agent environments or in combination with conventional methods — leveraging performances compared to benchmarks and reducing dependence on human experience. This not only implies a more sophisticated focus on distributed production resources, but also broadening the perspective from a local to a global scale. Nevertheless, future research must further increase scalability and reproducibility to guarantee a simplified transfer of results to reality.
Increasingly fast development cycles and individualized products pose major challenges for today's smart production systems in times of industry 4.0. The systems must be flexible and continuously adapt to changing conditions while still guaranteeing high throughputs and robustness against external disruptions. Deep rein- forcement learning (RL) algorithms, which already reached impressive success with Google DeepMind's AlphaGo, are increasingly transferred to production systems to meet related requirements. Unlike supervised and unsupervised machine learning techniques, deep RL algorithms learn based on recently collected sensor- and process-data in direct interaction with the environment and are able to perform decisions in real-time. As such, deep RL algorithms seem promising given their potential to provide decision support in complex environments, as production systems, and simultaneously adapt to changing circumstances. While different use-cases for deep RL emerged, a structured overview and integration of findings on their application are missing. To address this gap, this contribution provides a systematic literature review of existing deep RL applications in the field of production planning and control as well as production logistics. From a performance perspective, it became evident that deep RL can beat heuristics significantly in their overall performance and provides superior solutions to various industrial use-cases. Nevertheless, safety and reliability concerns must be overcome before the widespread use of deep RL is possible which presumes more intensive testing of deep RL in real world applications besides the already ongoing intensive simulations.