Refine
Document Type
- Conference Proceeding (11)
- Working Paper (1)
Is part of the Bibliography
- no (12)
Keywords
- 02 (2)
- 04 (1)
- 5G (2)
- AI (2)
- Artificial intelligence (1)
- Auto-ML (2)
- CPS (1)
- Compliance (2)
- Conversational interfaces (1)
- Data ecosystem (1)
- Datenaustausch (1)
- Datensouveränität (1)
- Delphi study (1)
- Digital sovereignty (1)
- Digital technologies (2)
- Digitalization (2)
- Event-driven IT-Architecture (1)
- Fallstudien (1)
- IT OT Integration (1)
- Industrie 4.0 (3)
- Industrie 5.0 (1)
- Industry 4.0 (2)
- Industry 5.0 (1)
- Informationstechnologie (1)
- KI (1)
- Künstliche Intelligenz (2)
- Machine Learning (2)
- Management (1)
- Manufacturing companies (1)
- Product-Service-Systems (1)
- Regulation (2)
- SV7185 (1)
- Self-managed (1)
- Smart Machines (1)
- Smart Products (1)
- Studie (1)
- Technologiemanagement (2)
- Zielsystem (1)
- agile development (1)
- development process (1)
- rev (6)
- smart products (1)
- smart services (1)
Institute
- Informationsmanagement (12) (remove)
Methods of machine learning (ML) are difficult for manufacturing companies to employ productively. Data science is not their core skill, and acquiring talent is expensive. Automated machine learning (Auto-ML) aims to alleviate this, democratizing machine learning by introducing elements such as low-code or no-code functionalities into its model creation process. Due to the dynamic vendor market of Auto-ML, it is difficult for manufacturing companies to successfully implement this technology. Different solutions as well as constantly changing requirements and functional scopes make a correct software selection difficult. This paper aims to alleviate said challenge by providing a longlist of requirements that companies should pay attention to when selecting a solution for their use case. The paper is part of a larger research effort, in which a structured selection process for Auto-ML solutions in manufacturing companies is designed. The longlist itself is the result of six case studies of different manufacturing companies, following the method of case study research by Eisenhardt. A total of 75 distinct requirements were identified, spanning the entire machine learning and modeling pipeline.
With the development of publicly accessible broker systems within the last decade, the complexity of data-driven ecosystems is expected to become manageable for self-managed digitalisation. Having identified event-driven IT-architectures as a suitable solution for the architectural requirements of Industry 4.0, the producing industry is now offered a relevant alternative to prominent third-party ecosystems. Although the technical components are readily available, the realisation of an event-driven IT-architecture in production is often hindered by a lack of reference projects, and hence uncertainty about its success and risks. The research institute FIR and IT-expert synyx are thus developing an event-driven IT-architecture in the Center Smart Logistics' producing factory, which is designed to be a multi-agent testbed for members of the cluster. With the experience gained in industrial projects, a target IT-architecture was conceptualised that proposes a solution for a self-managed data-ecosystem based on open-source technologies. With the iterative integration of factory-relevant Industry 4.0 use cases, the target is continuously realised and validated. The paper presents the developed solution for a self-managed event-driven IT-architecture and presents the implications of the decisions made. Furthermore, the progress of two use cases, namely an IT-OT-integration and a smart product demonstrator for the research project BlueSAM, are presented to highlight the iterative technical implementability and merits, enabled by the architecture.