Search

Support vector machines (SVMs), a relatively new paradigm in statistical learning theory, are studied for their potential to recognize transient behavior of detector signals corresponding to various accident events at nuclear power plants (NPPs). Transient classification is a major task for any computer-aided system for recognition of various malfunctions. The ability to identify the state of operation or events occurring at an NPP is crucial so that personnel can select adequate response actions. The Modular Accident Analysis Program, version 4 (MAAP4) is a program that can be used to model various normal and abnormal events in an NPP. This study uses MAAP signals describing various loss-of-coolant accidents in boiling water reactors. The simulated sensor readings corresponding to these events have been used to train and test SVM classifiers. SVM calculations have demonstrated that they can produce classifiers with good generalization ability for our data. This in, turn indicates that SVMs show promise as classifiers for the learning problem of identifying transients., QC 20100525

It has been proposed that the fluctuations of the neutron current called the current noise, can be used in addition to the scalar noise in reactor diagnostic problems. The possibility of the localization of a vibrating control rod pin in a pressurized water reactor control assembly is investigated by using the scalar neutron noise and the two-dimensional radial current noise as measured at one central point in the assembly. Art explicit localization technique is elaborated in which the searched position is determined as the absolute minimum of a minimization function. The technique is investigated in numerical simulations. The results of the simulation tests show the potential applicability of the method., QC 20100525