IMPROVE - Innovative Modelling Approaches for Production Systems to Raise Validatable Efficiency

This open access work presents selected results from the European research and innovation project IMPROVE which yielded novel data-based solutions to enhance machine reliability and efficiency in the fields of simulation and optimization, condition monitoring, alarm management, and quality prediction.

Provides engineering-lean, unsupervised methods that scale in realistic scenarios Helps to improve reliability and efficiency of complex systems Presents examples and results from real factories and real cyber-physical systems

Autorentext
Prof. Dr. Oliver Niggemann is Professor for Artificial Intelligence in Automation. His research interests are in the fields of machine learning and data analysis for Cyber-Physical Systems and in the fields of planning and diagnosis of distributed systems. He is a board member of the research institute inIT and deputy director at the Fraunhofer Application Center Industrial Automation INA located in Lemgo.

**Dr. Peter Schüller is postdoctoral researcher at Technische Universität Wien. His research interests are hybrid reasoning systems that combine Knowledge Representation and Machine Learning and applications in the fields of Cyber-Physical systems and Natural Language Processing.
**

Inhalt
Concept and Implementation of a Software Architecture for Unifying Data Transfer in Automated Production Systems.- Social Science Contributions to Engineering Projects: Looking Beyond Explicit Knowledge Through the Lenses of Social Theory.- Enable learning of Hybrid Timed Automata in Absence of Discrete Events through Self-Organizing Maps.- Anomaly Detection and Localization for Cyber-Physical Production Systems with Self-Organizing Maps.- A Sampling-Based Method for Robust and Efficient Fault Detection in Industrial Automation Processes.- Validation of similarity measures for industrial alarm flood analysis.- Concept for Alarm Flood Reduction with Bayesian Networks by Identifying the Root Cause.