Building scalable models for anomaly detection in self-organizing industrial systems

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.