Approach to the detection of abnormal behavior of processes in process control systems based on log analysis
Abstract
The paper proposes an approach to the detection of abnormalities in the behavior of knowledge-capacity business processes on the basis of comparative analysis of tracks in the log of events logging. The approach takes into account the temporal and object aspects of the implementation of the business process. The temporal aspect defines the sequence of events that reflect the execution of the business process. Object defines the characteristics of objects that use the business process when performing these actions. When searching for abnormal fragments, the distance between paths in the attribute event space is calculated. As an indicator of the beginning and end of an abnormal fragment, the angle of deviation between the tracks is used. The approach defines the set of attributes of objects associated with the execution of an anomalous fragment, as well as the values of these attributes, which can then be used to improve the business process.
Keywords
