Max-Ferdinand Stroh
Refine
Document Type
- Conference Proceeding (18) (remove)
Is part of the Bibliography
- no (18)
Keywords
- 3 (1)
- 5G (4)
- 5G use case (1)
- 5G-Technology (1)
- AI (2)
- Agriculture (1)
- Artificial Intelligence (1)
- Auto-ML (2)
- CPS (2)
- Carrier (1)
Institute
5G offers the manufacturing industry a wireless, fast and secure transmission technology with high range, low latency and the ability to connect a large number of devices. Existing transmission technologies are reaching their limits due to the increasing number of networked devices and high demands on reliability, data volume, security and latency. 5G fulfills these requirements and also combines the potential and use cases of previous transmission technologies so that unwanted isolated solutions can be merged. Use cases of transmission technologies that previously required a multitude of solutions can now be realized with a single technology. However, the general literature often refers to 5G use cases that can also be realized over cables in particular. In this paper, a literature review presents the current state of research on the various 5G application scenarios in production . Furthermore, concrete characteristics of 5G use cases are identified and assigned to the identified application scenarios. The goal is to verify the identified 5G use cases and to work out their 5G relevance in order to be able to concretely differentiate them from already existing Industrie 4.0 applications.
Methods of machine learning (ML) are notoriously difficult for enterprises to employ productively. Data science is not a core skill of most companies, and acquiring external talent is expensive. Automated machine learning (Auto-ML) aims to alleviate this, democratising machine learning by introducing elements such as low-code / no-code functionalities into its model creation process. Multiple applications are possible for Auto-ML, such as Natural Language Processing (NLP), predictive modelling and optimization. However, employing Auto-ML still proves difficult for companies due to the dynamic vendor market: The solutions vary in scope and functionality while providers do little to delineate their offerings from related solutions like industrial IoT-Platforms. Additionally, the current research on Auto-ML focuses on mathematical optimization of the underlying algorithms, with diminishing returns for end users. The aim of this paper is to provide an overview over available, user-friendly ML technology through a descriptive model of the functions of current Auto-ML solutions. The model was created based on case studies of available solutions and an analysis of relevant literature. This method yielded a comprehensive function tree for Auto-ML solutions along with a methodology to update the descriptive model in case the dynamic provider market changes. Thus, the paper catalyses the use of ML in companies by providing companies and stakeholders with a framework to assess the functional scope of Auto-ML solutions.
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.
Feasibility Analysis of Entity Recognition as a Means to Create an Autonomous Technology Radar
(2021)
Mit den neuesten Technologietrends auf dem Laufenden zu bleiben, ist für Fertigungsunternehmen eine entscheidende Aufgabe, um auf einem global wettbewerbsfähigen Markt erfolgreich zu bleiben. Die Erstellung eines Technologieradars ist ein etablierter, jedoch meist manueller Prozess zur Visualisierung der neuesten Technologietrends.
Der Herausforderung, Technologien zu identifizieren und zu visualisieren, widmet sich das Projekt TechRad, das maschinelles Lernen einsetzt, um ein autonomes Technologie-Scouting-Radar zu realisieren. Eine der Kernfunktionen ist die Identifizierung von Technologien in Textdokumenten. Dies wird durch natürliche Sprachverarbeitung (NLP) realisiert.
Dieser Beitrag fasst die Herausforderungen und möglichen Lösungen für den Einsatz von Entity Recognition zur Identifikation relevanter Technologien in Textdokumenten zusammen. Die Autoren stellen eine frühe Phase der Implementierung des Entity Recognition Modells vor. Dies beinhaltet die Auswahl von Transfer Learning als geeignete Methode, die Erstellung eines Datensatzes, der aus verschiedenen Datenquellen besteht, sowie den angewandten Modell-Trainings-Prozess. Abschließend wird die Leistungsfähigkeit der gewählten Methode in einer Reihe von Tests überprüft und bewertet.
Manufacturing companies face the challenge of selecting digitalization measures that fit their strategy. Measures that are initiated and not aligned with the company’s strategy carry the risk of failing due to lack of relevance. This leads to an ineffective use of scarce human and financial resources. This paper presents a target system to help companies select relevant digitalization measures compliant with their strategy for IT-OT-integration projects. The target system was developed based on literature research and expert interviews, and later validated in two use cases. The target system considers the goals of production companies and combines them with digitalization measures. The measures are classified by different maturity levels required for their realization. Thus, the target system enables manufacturing companies to evaluate digitalization measures with regards to their strategic relevance and the required Industrie 4.0 maturity level for their realization. This ensures an effective use of resources.
The number of available technologies is constantly rising. Be it additive manufacturing, artificial intelligence (AI) or distributed ledger technologies. The choice of the right technologies may decide the fate of a company. Due to the overwhelming amount of information sources, regular technology market research becomes increasingly challenging, especially for SMEs. In order to assist the technology management process, the authors will introduce the architecture of an automated, AI-based technology radar. The architecture will automatically collect data from relevant sources, assess the relevance of the respective technology (i.e. their maturity level) and then visualize it on the radar map.
This paper addresses the challenge of modelling individual cyber-physical systems (CPS) for small and medium-sized enterprises (SMEs) in manufacturing industries. CPS are key technology building blocks for the implementation of Industrie 4.0. Especially for SMEs the increase of production efficiency and reduction of manufacturing costs through CPS offer potential to maintain their competitiveness and innovation capacity. Although SMEs perceive the potential of CPS, they often lack financial and human resources to acquire the necessary CPS-competencies as well as an overview of all the currently available technological solutions. To overcome this issue a matching platform will offer SMEs support in finding suitable CPS-components by letting them express their functional and technical requirements. The matching logic is based on a set of morphologies that encompasses the functional and requirement spectrum of CPS-components. The matching algorithm analyses the input for congruence of requirements and available technologies and suggests suitable technology combinations. This paper describes the methodology of the matching platform, and introduces the research work to define and to develop the technology morphologies. The presented results facilitate the selection and configuration of CPS for SMEs.
Numerous traditional, agile and hybrid development approaches have been proposed for the development of CPS. As the choice of development process is crucial to the success of development projects, it has become a major challenge to identify the best-suited process. This paper introduces a methodology for identifying the best-suited CPS development process, based on the individual boundary conditions for a certain development project within a company. The authors used a set of eight indicators to assess a CPS-development project. The results of the assessment were matched with CPS-development approaches. Based on the matching results a best-suited development process was selected. The application is shown for a use case in the German manufacturing industry. The developed method aims to reduce the risk of project failure due to the wrong choice of development process.