This　paper　focus　on　the　Pellet-Cladding　Interaction　(PCI)　evaluating　by　a　self-organizing　Radial　Basis　Function　Neural　Network　(RBFNN)　during　the　operation　of　Zircaloy　clad　fuel　in　the　Water　cooled　Reactors.　Using　the　neural　network,　which　built　through　the　analyzing　of　the　existing　data　but　the　physical　process　of　PCI,　is　a　suitable　way　to　reduce　the　calculation　complexity.　In　this　sense,　the　stage　of　PCI　can　be　evaluated　online.　A　self-organized　RBFNN　is　used,　which　can　vary　its　structure　dynamically　in　order　to　maintain　the　prediction　accuracy.　The　hidden　neurons　in　the　RBF　neural　network　can　be　added　or　removed　online　based　on　the　neuron　activity　and　mutual　information,　to　achieve　the　appropriate　network　complexity　and　maintain　overall　computational　efficiency.　The　PCI　experiment　data　from　literatures　is　used　to　test　this　method,　and　the　results　demonstrate　its　effectiveness.　Copyright　©　2015　by　JSME.