数据挖掘在三维堆芯仿真中的应用

ata mining is the process in which useful and interesting information are found. Support vector machine for regression (SVR) is a new data mining algorithms, which is the application of support vector machine (SVM) to regression estimation. This paper is based on the three-dimensional core simulation program and the simulation data of core power changes are obtained by running this program. Then these data are processed by SVR algorithm and traditional method, respectively and the corresponding core power distribution curves are obtained. By comparing the results, it is found that SVR do not require a prior knowledge such as parametric trends of data and is dependent on the intrinsic relationship of data directly. Thus, the results handled by SVR are more accurate than those by traditional method and it is suitable for other data processing.