Real-time identification of most critical alarms for alarm flood reduction

In complex processes, the activation of a single alarm can trigger a cascade of consequences that affect multiple interconnected components. This can lead to a rapid increase in the number of active alarms. This sudden surge in alarms is often referred to as an alarm flood. Alarm floods are a common source of operational burden for operators, overwhelming them with a high volume of alarm notifications. If critical alarms are not promptly and accurately identified, decision-making processes can be undermined. This paper addresses these challenges by introducing a novel approach for identifying and prioritizing critical alarms from each alarm flood. The contributions of this work are twofold: First, hidden Markov models (HMMs) are employed to construct a likelihood matrix that uncovers relationships among alarm variables and identifies the most critical alarms through a directed acyclic graph (DAG). Second, expectation-maximization (EM) algorithm is applied to update the likelihood matrix dynamically and generate time-evolving plots for real-time identification of critical alarms. Case studies are conducted using a vinyl acetate monomer simulator to demonstrate the effectiveness of the proposed approach. The results highlight accurate identification and prioritization of critical alarms, enabling operators to focus on the most important process abnormalities.