In a nuclear power plant (NPP), most of the systems are linked due to processes of fluid flow, heat transfer etc., and their natural tendency to respond to changes during accident conditions. These relationships can be utilized to develop smart applications for plant accident monitoring and management. In this research, the statistical relationships among the process parameters have been analyzed. It has been embarked that the characteristics of a safety system during a particular interval can be estimated by utilizing the other affected parameters, employing statistical correlation and regression models developed from the simulation data offline, when evaluated for the same set of conditions on accident sequence and safety systems. The proposed methodology has been demonstrated for a specific loss of coolant accident scenario using correlation coefficient and neural networks, for the time interval when containment spray system was initiated at the particular stage of accident progression and remained operational for some designed time. Virtual sensor networks were constructed for the estimation of reactor vessel level during that time period, which demonstrates the realization of methodology. The estimations from such virtual sensor networks are expected to improve by utilizing the importance measures and concepts to generalize the neural networks. Also, correlation voting index (CVI) provides a capability to select a set of related outputs, which would be used as a yardstick for comparing results in case, missing or uncertain inputs are present.