Abstract With complexities in the control systems, it is natural that the chemical plants may become vulnerable to faults in practice. Alarm systems were designed to raise an alarm when a fault is detected. But modern alarm systems often produce large amounts of false or nuisance alarms which leads to alarm floods. Operators receive far more alarms than they can handle. To reduce the alarm floods, we developed a novel method which combined the Time-delayed Convergent Cross Mapping (TCCM) and Bayesian Network (BN). In this paper, the BN is constructed with application of TCCM to process data and expert knowledge. The alarm data is used to estimate the conditional probability among the nodes of the BN. The BN is used to find the alarms propagation paths and root cause at real-time. Finally, the method is applied to the Tennessee Eastman model to illustrate the applicability.
[1]
Tore Hägglund,et al.
Causal analysis for alarm flood reduction
,
2016
.
[2]
George Sugihara,et al.
Detecting Causality in Complex Ecosystems
,
2012,
Science.
[3]
Iman Izadi,et al.
Pattern matching of alarm flood sequences by a modified Smith–Waterman algorithm
,
2013
.
[4]
Faisal Khan,et al.
Design of scenario-based early warning system for process operations
,
2015
.
[5]
N. Lawrence Ricker,et al.
Decentralized control of the Tennessee Eastman Challenge Process
,
1996
.
[6]
Jinsong Zhao,et al.
Fault Diagnosis of Chemical Processes Using Artificial Immune System with Vaccine Transplant
,
2016
.
[7]
George Sugihara,et al.
Distinguishing time-delayed causal interactions using convergent cross mapping
,
2015,
Scientific Reports.