Smart sensing of the axial power and offset in NPPs using GMDH method

Abstract

The status of nuclear power plants' conditions must be checked to avoid initial events which may eventually lead to accidents. Axial power and axial offset (AO) are key parameters which are usually used to state 3-dimensional core power peaking, in the form of a practical parameter. Group method of data handling (GMDH) has a wide range of applications. Here, a GMDH is used and modified as an efficient method to predict the axial power and AO of the reactor core as well as fuel assemblies. In this paper, axial power offset of the whole reactor core is reconstructed by using in-core detectors. By using the developed GMDH algorithm, the optimum relationship between the independent in-core detector signals and the dependent variables, the core axial power and AO, is determined. Two separate sets of big data are prepared and analyzed. The first set includes power at each of 24 axial nodes at different core states. The second set is similar to the first set except as it also contains fuel assembly data.