TY - GEN
T1 - Building scalable models for anomaly detection in self-organizing industrial systems
AU - Kiermeier, Marie
AU - Werner, Martin
AU - Sauer, Horst
AU - Wieghardt, Jan
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/11/10
Y1 - 2017/11/10
N2 - The main challenge for anomaly detection in Self-Organizing Industrial Systems (SOIS) is the high degree of freedom of the system, which causes a state-space explosion. Since the system is free to choose at runtime any solution out of the vast amount of possible ones, to ensure that the production process is optimal at all times, classic anomaly detection techniques can not be used one-to-one in SOISs. For this reason, we already presented in previous work, a novel anomaly detection method, which exploits the idea that many products will share a larger fraction of the production process. Accordingly, it learns at first such recurrent 'building blocks' of object movements and represents then incoming movements in relation to these known building blocks. With it, anomalous trajectories and global anomalous events like the omitting of a system component, can be detected. In this paper, we present a new algorithm which extracts such 'building blocks' more efficiently. In particular, the new approach scales linear with the number of samples per trajectory, while the existing approach scales quadratic.
AB - The main challenge for anomaly detection in Self-Organizing Industrial Systems (SOIS) is the high degree of freedom of the system, which causes a state-space explosion. Since the system is free to choose at runtime any solution out of the vast amount of possible ones, to ensure that the production process is optimal at all times, classic anomaly detection techniques can not be used one-to-one in SOISs. For this reason, we already presented in previous work, a novel anomaly detection method, which exploits the idea that many products will share a larger fraction of the production process. Accordingly, it learns at first such recurrent 'building blocks' of object movements and represents then incoming movements in relation to these known building blocks. With it, anomalous trajectories and global anomalous events like the omitting of a system component, can be detected. In this paper, we present a new algorithm which extracts such 'building blocks' more efficiently. In particular, the new approach scales linear with the number of samples per trajectory, while the existing approach scales quadratic.
UR - http://www.scopus.com/inward/record.url?scp=85041185713&partnerID=8YFLogxK
U2 - 10.1109/INDIN.2017.8104779
DO - 10.1109/INDIN.2017.8104779
M3 - Conference contribution
AN - SCOPUS:85041185713
T3 - Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017
SP - 245
EP - 250
BT - Proceedings - 2017 IEEE 15th International Conference on Industrial Informatics, INDIN 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th IEEE International Conference on Industrial Informatics, INDIN 2017
Y2 - 24 July 2017 through 26 July 2017
ER -