Artificial Intelligence in Automation, Industrial Communication Technology

AVA: Abstraktion von Verhaltensmodellen für Anlagen des Maschinenbaus aus Messungen in verteilten Automatisierungssystemen

Prof. Dr. rer. nat. Oliver Niggemann
01.09.2011 bis 31.08.2014

Motivation

In automation engineering, methods exist (i) to capture the overall state of production and process plants, and (ii) for the early detection of degradation and anomalies. In this project, these approaches are extended: First, distributed automation systems are used for data collection. Second, new approaches to anomaly detection in computer science such as learning or the automatic parameterization of plant and process models for model-based diagnosis are used.

Projectgoals and researchactivities

To achieve high degree of utilization, and short maintenance periods, signs of degradation should be recognized as early as possible. Today, threshold-based methods often cannot do this. Operators can recognize these behavior changes often too late and this may lead to high maintenance costs and extended downtimes. Here, to overcome this problem, the project uses more complex and more dynamic models of the normal behavior.

The models of the normal behavior are automatically learned based on observations in the operation phase of the system. In this project, algorithms are developed which learn the models in form of hybrid temporal finite automata. The learned models are then used for anomaly detection. During runtime, the forecast of the learned model is compared with the current system observations. For each deviation, an error is signaled.

This project is promoted by:
Bundesministerium für Bildung und Forschung (BMBF)
Sponsors: Projektträger Jülich
Funding Code: 17N1211
Funding Lines: IngenieurNachwuchs
Stakeholders / Contacts: Johann Badinger, M. Sc., Dr. rer. nat. Alexander Maier
Employees: Dr. rer. nat. Alexander Maier, Johann Badinger, M. Sc.
Prof. Dr. rer. nat. Oliver Niggemann¹, Prof. Dr. rer. nat. Oliver Niggemann, Dr. rer. nat. Alexander Maier, Asmir Vodenčarević, Bernhard Jantscher, Bernhard Jantscher²
Fighting the Modeling Bottleneck – Learning Models for Production Plants
¹ First Authors
² Last authors
Asmir Vodenčarević¹, Asmir Vodenčarević, Prof. Dr. rer. nat. Hans Kleine Büning, Prof. Dr. rer. nat. Oliver Niggemann, Dr. rer. nat. Alexander Maier, Dr. rer. nat. Alexander Maier²
Identifying Behavior Models for Process Plants
In: 16th IEEE International Conference on Emerging Technologies Factory Automation (ETFA), Sep 2011
¹ First Authors
² Last authors
Asmir Vodenčarević¹, Asmir Vodenčarević, Prof. Dr. rer. nat. Hans Kleine Büning, Prof. Dr. rer. nat. Oliver Niggemann, Dr. rer. nat. Alexander Maier, Dr. rer. nat. Alexander Maier²
Using Behavior Models for Anomaly Detection in Hybrid Systems.
In: 23rd International Symposium on Information, Communication and Automation Technologies-ICAT 2011, Oct 2011
¹ First Authors
² Last authors
Prof. Dr. rer. nat. Oliver Niggemann¹, Prof. Dr. rer. nat. Oliver Niggemann, Prof. Dr. rer. nat. Benno Stein, Dr. rer. nat. Alexander Maier, Dr. rer. nat. Alexander Maier²
Solving Modeling Problems with Machine Learning - A Classification Scheme of Model Learning Approaches for Technical Systems
¹ First Authors
² Last authors
Dr. rer. nat. Alexander Maier¹, Dr. rer. nat. Alexander Maier, Florian Pethig, B. Sc., Asmir Vodenčarević, Nikolai Schetinin, B. Sc., Prof. Dr. rer. nat. Oliver Niggemann, Prof. Dr. rer. nat. Hans Kleine Büning, Prof. Dr. rer. nat. Hans Kleine Büning²
Analyse und Visualisierung des Energieverbrauchs in Produktionsanlagen
¹ First Authors
² Last authors
Dr. rer. nat. Alexander Maier¹, Dr. rer. nat. Alexander Maier, Tim Tack, M. Sc., Prof. Dr. rer. nat. Oliver Niggemann, Prof. Dr. rer. nat. Oliver Niggemann²
Visual Anomaly Detection in Production Plants
In: 9th International Conference on Informatics in Control, Automation and Robotics (ICINCO), Jul 2012
¹ First Authors
² Last authors
Dr. rer. nat. Alexander Maier¹, Dr. rer. nat. Alexander Maier, Carlos Paiz Gatica, Prof. Dr. rer. nat. Oliver Niggemann, Markus Köster, Dr. Jan Stefan Michels, Dr. Jan Stefan Michels²
Lernen des Zeitverhaltens in verteilten Produktionsanlagen
In: Kommunikation in der Automation (KommA 2012), Nov 2012
¹ First Authors
² Last authors
Asmir Vodenčarević¹, Asmir Vodenčarević, Dr. rer. nat. Alexander Maier, Prof. Dr. rer. nat. Oliver Niggemann, Prof. Dr. rer. nat. Oliver Niggemann²
Evaluating Learning Algorithms for Stochastic Finite Automata
In: 2nd International Conference on Pattern Recognition Applications and Methods (ICPRAM 2013), Feb 2013
¹ First Authors
² Last authors
Dr. rer. nat. Alexander Maier¹, Dr. rer. nat. Alexander Maier, Markus Köster, Carlos Paiz Gatica, Prof. Dr. rer. nat. Oliver Niggemann, Prof. Dr. rer. nat. Oliver Niggemann²
Automated Generation of Timing Models in Distributed Production Plants
In: IEEE International Conference on Industrial Technology (ICIT 2013), Feb 2013
¹ First Authors
² Last authors
Tim Tack, M. Sc.¹, Tim Tack, M. Sc., Dr. rer. nat. Alexander Maier, Prof. Dr. rer. nat. Oliver Niggemann, Prof. Dr. rer. nat. Oliver Niggemann²
Visuelle Anomalie-Erkennung in Produktionsanlagen
In: VDI Kongress AUTOMATION 2013, Jun 2013
¹ First Authors
² Last authors
Prof. Dr. rer. nat. Oliver Niggemann¹, Prof. Dr. rer. nat. Oliver Niggemann, Asmir Vodenčarević, Dr. rer. nat. Alexander Maier, Stefan Windmann, Prof. Dr. rer. nat. Hans Kleine Büning, Prof. Dr. rer. nat. Hans Kleine Büning²
A Learning Anomaly Detection Algorithm for Hybrid Manufacturing Systems
In: The 24th International Workshop on Principles of Diagnosis (DX-2013), Oct 2013
¹ First Authors
² Last authors
Promoted by
Projektträger