Refine
Year of publication
Document Type
- Article (143)
- Monograph/Edited Volume (26)
- Part of a Book (22)
- Conference Proceeding (18)
- Postprint (15)
- Other (7)
- Contribution to a Periodical (5)
- Doctoral Thesis (1)
- Review (1)
Keywords
- knowledge management (7)
- Industrie 4.0 (5)
- Industry 4.0 (5)
- deep reinforcement learning (5)
- production control (5)
- ERP (4)
- Enterprise-Resource-Planning (4)
- digital learning (4)
- machine learning (4)
- systematic literature review (4)
Institute
- Wirtschaftswissenschaften (139)
- Fachgruppe Betriebswirtschaftslehre (86)
- Wirtschafts- und Sozialwissenschaftliche Fakultät (4)
- Hasso-Plattner-Institut für Digital Engineering GmbH (3)
- Fachgruppe Politik- & Verwaltungswissenschaft (2)
- Sozialwissenschaften (2)
- Bürgerliches Recht (1)
- Department Psychologie (1)
- Extern (1)
- Forschungsbereich „Politik, Verwaltung und Management“ (1)
Enhancing economic efficiency in modular production systems through deep reinforcement learning
(2024)
In times of increasingly complex production processes and volatile customer demands, the production adaptability is crucial for a company's profitability and competitiveness. The ability to cope with rapidly changing customer requirements and unexpected internal and external events guarantees robust and efficient production processes, requiring a dedicated control concept at the shop floor level. Yet in today's practice, conventional control approaches remain in use, which may not keep up with the dynamic behaviour due to their scenario-specific and rigid properties. To address this challenge, deep learning methods were increasingly deployed due to their optimization and scalability properties. However, these approaches were often tested in specific operational applications and focused on technical performance indicators such as order tardiness or total throughput. In this paper, we propose a deep reinforcement learning based production control to optimize combined techno-financial performance measures. Based on pre-defined manufacturing modules that are supplied and operated by multiple agents, positive effects were observed in terms of increased revenue and reduced penalties due to lower throughput times and fewer delayed products. The combined modular and multi-staged approach as well as the distributed decision-making further leverage scalability and transferability to other scenarios.
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.
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.
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.
Process oriented knowledge management focuses on knowledge intensive business processes. For modelling and analysis of these processes the modelling technique KMDL (Knowledge Modeling and Description Language) has been developed. KMDL is a method to describe knowledge flows and conversions along and between business processes. Thereby KMDL identifies existing and utilized information as well as knowledge of individual participants and of the entire company. This research-in-progress contribution introduces a practical example in the field of software engineering, in which KMDL models are evaluated to identify process improvements, e.g. by adding knowledge management activities. Therefore three individual views focussing on selected aspects of interest are introduced.
Requirements for an integration of methods analyzing social issues in knowledge organizations
(2006)
CO₂-Fußabdrücke sind ein aktuell viel diskutiertes Thema mit weitreichenden Implikationen für Individuen als auch Unternehmen. Firmen können einen proaktiven Beitrag zur Transparenz leisten, indem der unternehmens- oder produktbezogene CO₂-Fußabdruck ausgewiesen wird. Ist der Entschluss gefasst einen CO₂-Fußabdruck auszuweisen und die entstehenden Treibhausgase zu erfassen, existiert eine Vielzahl unterschiedlicher Normen und Zertifikate, wie die publicly available specification 2050, das Greenhouse Gas Protokoll oder die ISO 14067. Das Ziel dieses Beitrags ist es, diese drei Normen zur Berechnung des produktbezogenen CO₂-Fußabdrucks zu vergleichen, um Gemeinsamkeiten und Unterschiede sowie Vor- und Nachteile in der Anwendung aufzuzeigen. Die Übersicht soll Unternehmen bei der Entscheidungsfindung hinsichtlich der Eignung eines CO₂-Fußabdrucks für ihr Unternehmen unterstützen.
Cyber-physical systems (CPS) have shaped the discussion about Industry 4.0 (I4.0) for some time. To ensure the competitiveness of manufacturing enterprises the vision for the future figures out cyber-physical production systems (CPPS) as a core component of a modern factory. Adaptability and coping with complexity are (among others) potentials of this new generation of production management. The successful transformation of this theoretical construct into practical implementation can only take place with regard to the conditions characterizing the context of a factory. The subject of this contribution is a concept that takes up the brownfield character and describes a solution for extending existing (legacy) systems with CPS capabilities.
From employee to expert
(2021)
In the context of the collaborative project Ageing-appropriate, process-oriented and interactive further training in SME (API-KMU), innovative solutions for the challenges of demographic change and digitalisation are being developed for SMEs. To this end, an approach to age-appropriate training will be designed with the help of AR technology. In times of the corona pandemic, a special research design is necessary for the initial survey of the current state in the companies, which will be systematically elaborated in this paper. The results of the previous methodological considerations illustrate the necessity of a mix of methods to generate a deeper insight into the work processes. Video-based retrospective interviews seem to be a suitable instrument to adequately capture the employees' interpretative perspectives on their work activities. In conclusion, the paper identifies specific challenges, such as creating acceptance among employees, open questions, e.g., how a transfer or generalization of the results can succeed, and hypotheses that will have to be tested in the further course of the research process.
To cope with the already large, and ever increasing, amount of information stored in organizational memory, "forgetting," as an important human memory process, might be transferred to the organizational context. Especially in intentionally planned change processes (e.g., change management), forgetting is an important precondition to impede the recall of obsolete routines and adapt to new strategic objectives accompanied by new organizational routines. We first comprehensively review the literature on the need for organizational forgetting and particularly on accidental vs. intentional forgetting. We discuss the current state of the art of theory and empirical evidence on forgetting from cognitive psychology in order to infer mechanisms applicable to the organizational context. In this respect, we emphasize retrieval theories and the relevance of retrieval cues important for forgetting. Subsequently, we transfer the empirical evidence that the elimination of retrieval cues leads to faster forgetting to the forgetting of organizational routines, as routines are part of organizational memory. We then propose a classification of cues (context, sensory, business process-related cues) that are relevant in the forgetting of routines, and discuss a meta-cue called the "situational strength" cue, which is relevant if cues of an old and a new routine are present simultaneously. Based on the classification as business process-related cues (information, team, task, object cues), we propose mechanisms to accelerate forgetting by eliminating specific cues based on the empirical and theoretical state of the art. We conclude that in intentional organizational change processes, the elimination of cues to accelerate forgetting should be used in change management practices.
To cope with the already large, and ever increasing, amount of information stored in organizational memory, "forgetting," as an important human memory process, might be transferred to the organizational context. Especially in intentionally planned change processes (e.g., change management), forgetting is an important precondition to impede the recall of obsolete routines and adapt to new strategic objectives accompanied by new organizational routines. We first comprehensively review the literature on the need for organizational forgetting and particularly on accidental vs. intentional forgetting. We discuss the current state of the art of theory and empirical evidence on forgetting from cognitive psychology in order to infer mechanisms applicable to the organizational context. In this respect, we emphasize retrieval theories and the relevance of retrieval cues important for forgetting. Subsequently, we transfer the empirical evidence that the elimination of retrieval cues leads to faster forgetting to the forgetting of organizational routines, as routines are part of organizational memory. We then propose a classification of cues (context, sensory, business process-related cues) that are relevant in the forgetting of routines, and discuss a meta-cue called the "situational strength" cue, which is relevant if cues of an old and a new routine are present simultaneously. Based on the classification as business process-related cues (information, team, task, object cues), we propose mechanisms to accelerate forgetting by eliminating specific cues based on the empirical and theoretical state of the art. We conclude that in intentional organizational change processes, the elimination of cues to accelerate forgetting should be used in change management practices.
Developing a new product generation requires the transfer of knowledge among various knowledge carriers. Several factors influence knowledge transfer, e.g., the complexity of engineering tasks or the competence of employees, which can decrease the efficiency and effectiveness of knowledge transfers in product engineering. Hence, improving those knowledge transfers obtains great potential, especially against the backdrop of experienced employees leaving the company due to retirement, so far, research results show, that the knowledge transfer velocity can be raised by following the Knowledge Transfer Velocity Model and implementing so-called interventions in a product engineering context. In most cases, the implemented interventions have a positive effect on knowledge transfer speed improvement. In addition to that, initial theoretical findings describe factors influencing the quality of knowledge transfers and outline a setting to empirically investigate how the quality can be improved by introducing a general description of knowledge transfer reference situations and principles to measure the quality of knowledge artifacts. To assess the quality of knowledge transfers in a product engineering context, the Knowledge Transfer Quality Model (KTQM) is created, which serves as a basis to develop and implement quality-dependent interventions for different knowledge transfer situations. As a result, this paper introduces the specifications of eight situation-adequate interventions to improve the quality of knowledge transfers in product engineering following an intervention template. Those interventions are intended to be implemented in an industrial setting to measure the quality of knowledge transfers and validate their effect.