Improving Operational Efficiency Through Alarm Management in Water Treatment Processes Using Artificial Intelligence

Abstract

Water Treatment Plants are controlled by modern industrial process control systems like SCADA or DCS. This facilitates to monitor, control, and troubleshoot water treatment processes and helps in maintaining continuous supply of water with adequate quality. At times and in contrary, these systems hamper process control by generating far too many alarms than needed. Many of the alarms are nuisance in nature and do not indicate any real abnormality. The true alarms which require prompt operator actions to normalize the process are often buried in the pool of nuisance alarms causing significant challenge for operator to take appropriate corrective actions in a timely manner. Many of the past major incidents occurring in the major process industries were attributed to operators’ inability to identify true alarms and take necessary actions. In this paper, we propose an Artificial Intelligence (AI) based pattern mining and advisory system to improve operational efficiency in alarm management. The identified alarm patterns bring out actionable insights in data by (i) identifying nuisance, chattering, redundant alarms, and (ii) Alarm response Pattern. A novel technique for sequential pattern mining in industrial Alarm & Event log data was developed based on State-of-the-art AI based association rule and pattern mining. The efficacy of the proposed method for systematically improving alarm management system in an actual plant environment is currently being studied in a water treatment plant in Singapore.