This paper presents a preliminary study on the use of adaptive neural fuzzy inference system (ANFIS) to determine the fragility curves in degraded nuclear power plant (NPP) passive components. The goal of this approach is to allow the direct association, using a mapping of input/output patterns, between measurable beam deflections and the structure probability of failure for a severe degradation condition. The present study consists of an Artificial Intelligence framework application considering the information obtained from an original Nuclear Regulatory Commission (NRC) research program. The results indicate that the ANFIS modeling is a promising alternative to traditional approach in nuclear studies of structure degradation in passive components.