A nuclear power plant (NPP) consists of an enormous number of components with complex interconnections. Various techniques to detect sensor errors have been developed to monitor the state of the sensors during normal NPP operation, but not for emergency situations. In an emergency situation with a reactor trip, all the plant parameters undergo drastic changes following the sudden decrease in core reactivity. In this paper, a machine learning model adopting a consistency index is suggested for sensor error detection during NPP emergency situations. The proposed consistency index refers to the soundness of the sensors based on their measurement accuracy. The application of consistency index labeling makes it possible to detect sensor error immediately and specify the particular sensor where the error occurred. From a compact nuclear simulator, selected plant parameters were extracted during typical emergency situations, and artificial sensor errors were injected into the raw data. The trained system successfully generated output that gave both sensor error states and error-free states.

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.

Multi-abnormal events, referring to the simultaneous occurrence of multiple single abnormal events in a nuclear power plant, have not been subject to consideration because multi-abnormal events are extremely unlikely to occur and indeed have not yet occurred. Such events, though, would be more challenging to diagnose than general single abnormal events, exacerbating the human error issue. This study introduces an efficient abnormality diagnosis model that covers multi-abnormality diagnosis using a one-vs-rest classifier and compares it with other artificial intelligence models. The multi-abnormality attention diagnosis model deals with multi-label classification problems, for which two methods are proposed. First, a method to effectively cluster single and multi-abnormal events is introduced based on the predicted probability distribution of each abnormal event. Second, a one-vs-rest classifier with high accuracy is employed as an efficient way to obtain knowledge on which particular multi-abnormal events are the most difficult to diagnose and therefore require the most attention to improve the multi-label classification performance in terms of data usage. The developed multi-abnormality attention diagnosis model can reduce human errors of operators due to excessive information and limited time when unexpected multi-abnormal events occur by providing diagnosis results as part of an operator support system.