IMPROVE - Innovative Modelling Approaches for Production Systems to Raise Validatable Efficiency : : Intelligent Methods for the Factory of the Future.

• Superior document: Technologien Für Die Intelligente Automation Series ; v.8
• Author: Niggemann, Oliver.
• TeilnehmendeR: Schüller, Peter.
• Place / Publishing House: Berlin, Heidelberg : : Springer Berlin / Heidelberg,, 2018.; ©2018.
• Year of Publication: 2018
• Edition: 1st ed.
• Language: English
• Series: Technologien Für Die Intelligente Automation Series
• Physical Description: 1 online resource (132 pages)

Table of Contents

• Intro
• Preface
• Table of Contents
• 1 Concept and Implementation of a Software Architecture for Unifying Data Transfer in Automated Production Systems. Utilization of Industrie 4.0 Technologies for Simplifying Data Access
• 1 Introduction and Motivation
• 2 Requirements for a System Architecture to Support Industrie 4.0 Principles
• 3 State-of-the-Art of Industrie 4.0 System Architectures
• 4 Concept of a Unified Data Transfer Architecture (UDaTA) in Automated Production Systems
• 5 Evaluation
• 5.1 Expert Evaluation
• 5.2 Prototypical Lab-Scale Implementation
• 6 Conclusion and Outlook
• Acknowledgment
• References
• 2 Social Science Contributions to Engineering Projects: Looking Beyond Explicit Knowledge Through the Lenses of Social Theory
• 1 Introduction
• 2 Introducing our role(s) as social science researchers
• 2.1 What do social scientists do?
• 2.2 What did we do as IMPROVE (social science) researchers?
• 3 Empirical findings on socio-technical arrangements in HMI supported operating of smart factory plants
• 4 Social Theory Plugins
• 4.1 A systems theory of (smart) factories
• 4.2 Tacit knowledge beyond explicity
• 4.3 Conceptualizing human-machine agency
• 5 Summary and outlook
• Acknowledgments
• References
• 3 Enable learning of Hybrid Timed Automata in Absence of Discrete Events through Self-Organizing Maps
• 1 Introduction
• 2 Methodologies
• 2.1 Hybrid Timed Automata
• 2.2 Self-Organizing Map
• 2.3 Watershed Transformation
• 3 Learning hybrid timed automata without discrete events
• 4 Experiments
• 4.1 Artificial test data
• 4.2 High Rack Storage System
• 4.3 Film-Spool Unwinder
• 5 Conclusion
• Acknowledgments.
• References
• 4 Anomaly Detection and Localization for Cyber-Physical Production Systems with Self-Organizing Maps
• 1 Introduction
• 2 Self-Organizing Map.
• 2.1 Anomaly detection with quantization error
• 2.2 Localization of anomalies
• 2.3 SOM trajectory tracking with timed automata
• 3 Experiments
• 3.1 Quantization error anomaly detection and anomaly localization
• 3.2 Trajectory tracking with automata
• 4 Conclusion
• Acknowledgments.
• References
• 5 A Sampling-Based Method for Robust and Efficient Fault Detection in Industrial Automation Processes
• 1 Introduction
• 2 Fault detection with stochastic process models
• 3 Fault detection for application cases with noisy measurements
• 3.1 Probability density models
• 3.2 Particle filter based fault detection
• 3.3 Parallel implementation
• 4 Evaluation and Discussion
• 4.1 Fault detection results
• 4.2 Runtime analysis
• 5 Conclusion
• Acknowledgments.
• Appendix A: Fault detection for observable process variables
• Appendix B: Metropolis Resampling
• References
• 6 Validation of similarity measures for industrial alarm flood analysis
• 1 Introduction
• 2 Clustering methodology
• 2.1 Alarm log acquisition
• 2.2 Flood detection and preprocessing
• 2.3 Alarm flood clustering
• 2.4 Distance matrix postprocessing
• 3 Evaluation methodology
• 3.1 Synthetic flood generation
• 3.2 Cluster Membership of Synthetic Floods
• 3.3 Cluster Stability
• 4 Empirical evaluation results
• 4.1 Visualization on a demonstrative set of 25 floods
• 4.2 Clustering with synthetic floods on the full dataset
• 5 Conclusion
• Acknowledgement
• References
• 7 Concept for Alarm Flood Reduction with Bayesian Networks by Identifying the Root Cause
• 1 Introduction
• 2 State of the Art of Alarm Management
• 3 Knowledge Representation
• 4 Concept for Alarm Flood Reduction
• 4.1 Learning Phase
• 4.2 Operation Phase
• 5 Conclusion
• Acknowledgment
• References.