Grants and Contributions:

Grant or Award spanning more than one fiscal year (2017-2018 to 2018-2019).

Abnormal situations cost industry millions of dollars every year. Alarm systems play important roles inx000D
ensuring safe and efficient operation of modern industrial plants. However, most existing industrial alarmx000D
systems suffer from alarm overloading. This implies that operators have to deal with too many alarms thatx000D
exceed the operators' capacity. Typically, plant operators receive much more alarms than they can handle.x000D
There has been an increasing interest in industry to address this issue and seek remedies to reduce the numberx000D
of false and nuisance alarms. Moreover, the current alarm messages do not indicate the root causes of thex000D
alarms or how to solve the alarms. An effective root cause analysis is highly desired.x000D
NTWIST Inc. provides advanced real-time alarm management solutions to process industries. Their goal is tox000D
eliminate preventable valve closures, unplanned equipment shutdowns and unplanned facilityx000D
outages/shutdowns caused by alarm flooding and alarm suppression. Currently, NTWIST is developing ax000D
real-time alarm management system based on artificial intelligence. In this project, NTWIST works togetherx000D
with Dr. Liu's group in the University of Alberta to learn from historical alarm data using reinforcementx000D
learning and deep learning to address the issues with alarm flooding based on each alarm's impact on thex000D
process and safety conditions.