Data-driven anomaly detection in cyber-physical production systems

Abstract Due to global competition and increasing product complexity, the complexity of production systems has grown significantly in recent years. This places an increasing burden on automation developers, systems engineers and plant constructors. Intelligent assistance systems and smart automation systems are a possible solution to face this complexity: The machines, i.e. the software and assistance systems, take over tasks that were previously carried out manually by experts. At the heart of this concept are intelligent anomaly detection approaches based on models of the system behaviors. Intelligent assistance systems learn these models automatically: Based on data, these systems extract most necessary knowledge about the diagnosis task. This paper outlines this data-driven approach to plant analysis using several use cases from industry.

[1]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[2]  Oliver Niggemann,et al.  A stochastic method for the detection of anomalous energy consumption in hybrid industrial systems , 2013, 2013 11th IEEE International Conference on Industrial Informatics (INDIN).

[3]  Gautam Biswas,et al.  Model-Based Diagnosis of Hybrid Systems , 2003, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[4]  Oliver Niggemann,et al.  System modeling based on machine learning for anomaly detection and predictive maintenance in industrial plants , 2014, Proceedings of the 2014 IEEE Emerging Technology and Factory Automation (ETFA).

[5]  Peter Struss,et al.  Diagnosis of Bottling Plants - First Success and Challenges , 2009 .

[6]  Sicco Verwer.  Efficient Identification of Timed Automata: Theory and practice , 2010 .

[7]  Benno Stein,et al.  Learning Behavior Models for Hybrid Timed Systems , 2012, AAAI.

[8]  Insup Lee,et al.  Cyber-physical systems: The next computing revolution , 2010, Design Automation Conference.

[9]  Oliver Niggemann,et al.  A generic synchronized data acquisition solution for distributed automation systems , 2012, Proceedings of 2012 IEEE 17th International Conference on Emerging Technologies & Factory Automation (ETFA 2012).

[10]  Jörg Neidig,et al.  Improved diagnosis by combining structural and process knowledge , 2011, ETFA2011.

[11]  C. W. Frey.  Monitoring of complex industrial processes based on self-organizing maps and watershed transformations , 2012, 2012 IEEE International Conference on Industrial Technology.

[12]  Edward A. Lee.  Cyber Physical Systems: Design Challenges , 2008, 2008 11th IEEE International Symposium on Object and Component-Oriented Real-Time Distributed Computing (ISORC).

[13]  René David,et al.  On Hybrid Petri Nets , 2001, Discret. Event Dyn. Syst..

[14]  Rolf Isermann,et al.  Model-based fault-detection and diagnosis - status and applications , 2004, Annu. Rev. Control..

[15]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[16]  Hans Kleine Büning,et al.  Using behavior models for anomaly detection in hybrid systems , 2011, 2011 XXIII International Symposium on Information, Communication and Automation Technologies.

[17]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[18]  Alexander Maier,et al.  Identification of timed behavior models for diagnosis in production systems , 2015 .

[19]  José Oncina,et al.  Learning deterministic regular grammars from stochastic samples in polynomial time , 1999, RAIRO Theor. Informatics Appl..

[20]  Thomas A. Henzinger,et al.  The Algorithmic Analysis of Hybrid Systems , 1995, Theor. Comput. Sci..

[21]  Thomas A. Henzinger,et al.  The theory of hybrid automata , 1996, Proceedings 11th Annual IEEE Symposium on Logic in Computer Science.