Fault diagnosis plays an important role in complex and safety-critical systems such as
nuclear power plants (NPPs). With the development of artificial intelligence (AI), extensive …

A transient is defined as an event when a plant proceeds from a normal state to an abnormal
state. In nuclear power plants (NPPs), recognizing the types of transients during early …

The quantification of the uncertainty associated to the results provided by artificial neural
networks is essential for their confident and reliable use in practice. This is particularly true …

The issue of feature selection is particularly critical for the application of monitoring and" on
condition" diagnostic techniques to complex plants, like the nuclear power plants, where …

The development of empirical classification models for fault diagnosis usually requires a
process of training based on a set of examples. In practice, data collected during plant …

Monitoring the condition of a component is typically based on an empirical model that
estimates the values of some measurable variables (signals) in normal conditions and …

Feature selection for transient classification is the problem of choosing among several
monitored parameters (ie, the features) to be used for efficiently recognizing the developing …

Initiating event identification is essential in managing nuclear power plant (NPP) severe
accidents. In this paper, a novel two-stage feature extraction scheme that incorporates the …

Template matching, which is a pattern recognition method, was adopted to identify the
transient in a pressurized water reactor (PWR). The transient data were generated using a …

In plant accident management, the control room operators are required to identify the causes
of the accident, based on the different patterns of evolution of the monitored process …