anomaly detection

Data Quality and Domain Expertise for Resilient AI Deployment

Data Quality and Domain Expertise for Resilient AI Deployment

Integrating anomaly and label error detection in industry
Pavlos Rath-Manakidis, Henry Huick, Erdi Ünal, Björn Krämer ORCID Icon, Laurenz Wiskott ORCID Icon
AI implementation transforms work and worker-technology relationships in industrial quality control. This paper explores how approaches to data quality and model transparency support ethical AI deployment, fostering worker agency, trust, and sustainable work design in automatic surface inspection systems (ASIS). Recurring problems like data inefficiency, variable model confidence, and limited AI expertise point to key challenges of human-centered AI: user trust, agency and responsible data management. A solution co-developed with an ASIS supplier demonstrates that the challenges extend beyond the purely technical, underscoring the value of AI design that augments human capabilities. Technical solutions such as anomaly, label error, and domain drift detection are proposed to enhance data quality and model reliability. The insights emphasize the following generalizable strategies for resilient AI integration: understanding user-reported problems through a human-AI interaction lens, ...
Industry 4.0 Science | Volume 42 | Edition 1 | Pages 128-135 | DOI 10.30844/I4SE.26.1.120
Multi-Stakeholder AI Ethics in Radiology

Multi-Stakeholder AI Ethics in Radiology

Implications for integrated technology and workplace design
Valentin Langholf ORCID Icon, Alexander Ranft, Lena Will, Robin Denz ORCID Icon, Johannes Schwarz ORCID Icon, Majd Syoufi, Pavlos Rath-Manakidis, Marc Kämmerer, Marcus Kremers, Axel Mosig ORCID Icon, Uta Wilkens ORCID Icon, Jörg Wellmer ORCID Icon
AI assistance can be seen as a welcome aid in radiology, a highly complex environment characterized by round-the-clock time pressure and quality expectations. However, it must meet high ethical standards from the perspective of both users and patients. It is a challenge to incorporate this human-centered approach into the development and introduction of AI applications.
Industry 4.0 Science | Volume 42 | Edition 1 | Pages 136-143 | DOI 10.30844/I4SE.26.1.128
Digital Twins Using Semantic Modeling and AI

Digital Twins Using Semantic Modeling and AI

Self-learning development and simulation of industrial production facilities
Wolfram Höpken ORCID Icon, Ralf Stetter ORCID Icon, Markus Pfeil ORCID Icon, Thomas Bayer ORCID Icon, Bernd Michelberger, Markus Till, Timo Schuchter, Alexander Lohr
The AI-driven, self-learning digital twin continuously adapts to real system behavior, ensuring an optimal representation of the production process. A comprehensive semantic model serves as the foundation for advanced artificial intelligence (AI) approaches. Insights derived from AI methods are integrated into this model, enhancing the interpretability and explainability of AI systems. Techniques from the field of eXplainable AI (XAI) facilitate the automated description of AI models and their findings, as well as the development of self-explanatory models.
Industry 4.0 Science | Volume 41 | Edition 2 | Pages 30-36
Custom-Fit Shoes Using 3D Printing

Custom-Fit Shoes Using 3D Printing

Deep Learning Supports Defect Detection in Mass Customization
Markus Trapp, Markus Kreutz, Alexander Böttjer, Michael Lütjen ORCID Icon, Michael Freitag ORCID Icon
3D printing has established itself as a production process and has also found its way into the fashion industry. Individualised shoes can be 3D printed, but this poses significant challenges for automated quality control, as defects are rare. Autoencoders enable to train a system with defect-free data so that detected deviations from this state can be evaluated as defects. Our research shows a ROC AUC score of 0.87, proving that this method is suitable for anomaly detection in 3D-printed shoes.
Industrie 4.0 Management | Volume 38 | 2022 | Edition 4 | Pages 15-18
Secure Processes in Modern Business Models

Secure Processes in Modern Business Models

Alexander Giehl, Peter Schneider
Technological progress offers opportunities for introducing new business models but also opens new paths for attackers. Security-by-design integrates factory security from the start and introduces a continuous security process built upon a variety of components. This article illustrates some of these components by highlighting secure processes with specific case studies: anomaly detection within value networks and secure production planning with simulation.
Industrie 4.0 Management | Volume 34 | 2018 | Edition 1 | Pages 55-58
Anomaly Detection for Industry 4.0 Sensor Data

Anomaly Detection for Industry 4.0 Sensor Data

Astrid Frey, Matthias Hagen, Benno Stein
In the BMBF-funded project “Provenance Analytics” research groups at the Bauhaus-Universität Weimar and the Hochschule Ostwestfalen-Lippe develop approaches for detecting anomalies in sensor data. In this short survey, we review the main methods for predicting failures in the production processes of manufacturing machines and give a brief overview of the activities planned in the project.
Industrie 4.0 Management | Volume 33 | 2017 | Edition 4 | Pages 53-56
Anomaly Detection in Images of Micro Parts

Anomaly Detection in Images of Micro Parts

Statistische Defekterkennung mittels Hauptkomponentenanalyse
Benjamin Staar ORCID Icon, Mirko Kück, Abderrahim Ait Alla ORCID Icon, Michael Lütjen ORCID Icon, Michael Freitag ORCID Icon, Aleksandar Simic
Optical systems are a popular choice for quality inspection because they are not only contactless and precise but also comparably fast. Particularly in cases where a 100% quality inspection is required low measurement and evaluation time is of essential importance. With high production rates of several parts per second, manual inspection is not feasible anymore and the evaluation needs to be automatically carried out by algorithms. In this article we propose a fast method for anomaly detection in image data based on principal component analysis and filtering. The method shows competitive performance on a data set of challenging surface inspection.
Industrie 4.0 Management | Volume 33 | 2017 | Edition 2 | Pages 52-56