Industry specialization and wireless convergence in Daejeon

박재수,; 박정용,

doi:10.6109/jkiice.2015.19.11.2739

Cited by 2 publications

(1 citation statement)

References 147 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This simulator has been used as a source of several data-driven machine learning applications in the nuclear field. The CNS can generate emergency or accident data with detailed malfunction options; while it is a simplified one-dimensional model with theoretical assumptions that cannot simulate all accident phenomena, it can generate a large amount of data in a short time [ 45 , 46 , 47 , 48 ]. Among the 2217 process parameters the CNS generated, 41 parameters were selected here based on the existent diagnosis procedure in the EOPs and to include parameters that indicate specific accident symptoms.…”

Section: Sensor Fault-tolerant Diagnosis System Test Resultsmentioning

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

Section: Sensor Fault-tolerant Diagnosis System Test Resultsmentioning

confidence: 99%