Andreas Selmaier

ORCID: 0000-0002-1008-0716
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Flexible and Reconfigurable Manufacturing Systems
  • Digital Transformation in Industry
  • Digital Innovation in Industries
  • Advanced X-ray and CT Imaging
  • Manufacturing Process and Optimization
  • Technology Assessment and Management
  • Industrial Vision Systems and Defect Detection
  • Assembly Line Balancing Optimization
  • Corporate Governance and Management
  • Electron and X-Ray Spectroscopy Techniques
  • Scheduling and Optimization Algorithms
  • Radiomics and Machine Learning in Medical Imaging
  • Additive Manufacturing Materials and Processes
  • Machine Learning in Materials Science

Institute of Automation
2019-2022

Friedrich-Alexander-Universität Erlangen-Nürnberg
2019-2021

Recent trends like autonomous driving, natural language processing, service robotics or Industry 4.0 are mainly based on the tremendous progress made in field of machine learning (ML). The increased data availability coupled with affordable computing power and easy-to-use software tools have laid foundation for using such algorithms a wide range industrial applications, e.g. predictive maintenance, quality vision. However, systematic guideline identifying implementing economically viable ML...

10.1016/j.procir.2020.01.035 article EN Procedia CIRP 2019-01-01

The discussion about the term "Digital Twin" and its associated concepts has expanded remarkably in scientific community recent years. In context of industrial production, Digital Twin refers to a holistic, linked, virtual representation physical entity. spectrum these entities ranges from individual products specific manufacturing processes up complex automated production systems. Due this diversity, many authors offer different interpretations topic, resulting wide range use case-specific...

10.1109/etfa46521.2020.9212030 article EN 2020-09-01

In product development, early decisions made within the requirements specification and design phase have significant impact on overall functionality, quality lifecycle cost of product. Systems Engineering, these oftentimes iterative phases are steered by underlying development models, providing processes, guidelines best practices. One family "Design for X" (DfX) tools or principles. mechatronic systems e.g. production systems, traditionally mechanical, electric software domain to be...

10.1016/j.procir.2021.01.067 article EN Procedia CIRP 2021-01-01

One of the major trends in 21st century is trend towards digital transformation within Industry 4.0. In order to adapt high volatile market conditions, especially context COVID-19, companies do not only have transfer their knowledge into systems. Furthermore, they be able tailor business processes rapidly changing customer's needs. The implementation efficient and transparent thereby known as process requires its underlying software-architecture highly flexible scalable. Especially a...

10.1016/j.procir.2021.10.023 article EN Procedia CIRP 2021-01-01

Während sich das Verhalten starr verketteter Systeme relativ einfach mittels Materialflusssimulationen modellieren lässt, sind herkömmliche Simulationsansätze für flexible Fertigungssysteme aufgrund des hohen Datenerhebungs- sowie Parametrisieraufwands nur bedingt geeignet. Jedoch kann durch automatische Übertragen von Echtzeitdaten in Simulationsmodell der aktuelle Zustand solcher deutlich verbessert abgebildet werden. Der Beitrag stellt ein Konzept die simulationsgestützte...

10.37544/1436-4980-2019-04-40 article EN wt Werkstattstechnik online 2019-01-01

Convolutional neural network (CNN)-based approaches have recently led to major performance steps in visual recognition tasks. However, only a few industrial applications are described the literature. In this paper, an object detection application for quality evaluation of X-ray scatter grids is and evaluated. To detect small defects on 4K input images, sliding window approach chosen. A special characteristic selected aggregation overlapping prediction results by applying 2D scalar field. The...

10.3390/s22030811 article EN cc-by Sensors 2022-01-21

Digitalisierungsprojekte sind Softwareprojekte. Sequenzielle Planungsmethoden, wie sie im konventionellen Projektmanagement überwiegend Anwendung finden, eignen sich nur bedingt für diesen Projekttyp, da die anwendungsspezifischen Anforderungen sowie Abhängigkeiten der Anlagen und IT-Systeme untereinander zu einem erheblichen Anstieg Gesamtkomplexität führen. In diesem Beitrag wird daher ein Ansatz zur systematischen Auswahl geeigneter Projektmanagementmethoden vorgestellt, welcher...

10.37544/1436-4980-2020-04-60 article DE wt Werkstattstechnik online 2020-01-01

Unternehmen der produzierenden Industrie, insbesondere deutsche Mittelstand, sind bei digitalen Transformation mit vielen Herausforderungen konfrontiert, beginnend Analyse und Identifikation geeigneter Automatisierungsprojekte. In dem Beitrag wird eine ganzheitliche Vorgehensweise vorgestellt, um Potenziale für Automatisierung in Produktion Logistik zu erkennen konkrete Projekte definieren.   Companies the manufacturing industry, especially German small and medium-sized businesses,...

10.37544/1436-4980-2020-09-27 article DE wt Werkstattstechnik online 2020-01-01

Due to ever-increasing data availability, computational power, and algorithmic advances, machine learning enables various novel industrial applications. A field with particularly strong potential for is computer vision. As part of that area, semantic segmentation refers a process links each pixel an image corresponding class. In this task, deep has outperformed traditional processing techniques as well other classical therefore become the new standard approach. Convolutional neural networks...

10.1109/icmla52953.2021.00140 article EN 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) 2021-12-01
Coming Soon ...