Categorization of Anomalies in Smart Manufacturing Systems to Support the Selection of Detection Mechanisms

Abstract

An important issue in anomaly detection in smart manufacturing systems is the lack of consistency in the formal definitions of anomalies, faults, and attacks. The term anomaly is used to cover a wide range of situations that are addressed by different types of solutions. In this letter, we categorize anomalies in machines, controllers, and networks along with their detection mechanisms, and unify them under a common framework to aid in the identification of potential solutions. The main contribution of the proposed categorization is that it allows the identification of gaps in anomaly detection in smart manufacturing systems.