Discovering Systematic Relations between Alarms for Alarm Flows Reduction

Alarm systems play an important role for the safe and efficient operation of modern industrial plants. However, in most of industrial alarm systems, alarm flows cannot always be correctly managed by the operators as they often turn into alarm floods, sequences of numerous alarms occurring in a short period of time. To reduce the alarm flows, this paper focuses on detection of redundant alarms that could be removed. This objective is met by, first, looking for two systematic causality relations between alarms, called domination and mutual dependency, in the alarm log. Once these relations discovered, alarms removal requires an expert analysis. To ease this analysis, the discovered relations are depicted in the form of Petri nets. The proposed method has been applied on a dataset coming from power industry and provided by General Electric. The results of this case study show the benefits of the approach.