Data-driven failure analysis of emergency shutdown systems in oil and gas industry

Zhu, Pengyu; Liyanage, Jayantha P.; Jeeves, Simon

doi:10.1108/jqme-03-2018-0022

Cited by 11 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In emergency situations in medical, aviation, and oil and gas industries, automated systems that support the responses to the situation have been researched applying several data-driven methods [ 54 , 55 , 56 , 57 ]. In the nuclear field, where safety is of utmost importance, even though NPPs are equipped with numerous autonomous safety systems, responses to abnormal states still largely depend on the judgments of plant operators.…”

Section: Discussionmentioning

confidence: 99%

A Sensor Fault-Tolerant Accident Diagnosis System

Choi

Lee

2020

Sensors

View full text Add to dashboard Cite

Emergency situations in nuclear power plants are accompanied by an automatic reactor shutdown, which gives a big task burden to the plant operators under highly stressful conditions. Diagnosis of the occurred accident is an essential sequence for optimum mitigations; however, it is also a critical source of error because the results of accident identification determine the task flow connected to all subsequent tasks. To support accident identification in nuclear power plants, recurrent neural network (RNN)-based approaches have recently shown outstanding performances. Despite the achievements though, the robustness of RNN models is not promising because wrong inputs have been shown to degrade the performance of RNNs to a greater extent than other methods in some applications. In this research, an accident diagnosis system that is tolerant to sensor faults is developed based on an existing RNN model and tested with anticipated sensor errors. To find the optimum strategy to mitigate sensor error, Missforest, selected from among various imputation methods, and gated recurrent unit with decay (GRUD), developed for multivariate time series imputation based on the RNN model, are compared to examine the extent that they recover the diagnosis accuracies within a given threshold.

show abstract