Sensors are one of the most vital instruments in Nuclear Power Plants (NPPs), and operators and safety systems monitor and analyze various parameters reported by them. Failure to detect sensors malfunctions or anomalies would lead to the considerable consequences. In this research, a new method based on thermal–hydraulic simulation by RELAP5 code and Feed-Forward Neural Networks (FFNN) is introduced to detect faulty sensors and estimate their correct value. For design an efficient neural net, seven feature selectors (i.e., Information gain, ReliefF, F-regression, mRMR, Plus-L Minus-R, GA, and PSO), three sigmoid activation functions (i.e., Logistic, Tanh and Elliot), and three training algorithms (i.e., Levenberg–Marquardt (LM), Bayesian Regularization (BR) and Scaled Conjugate Gradient (SCG)) have been comprehensively compared and evaluated. The required data have been obtained by simulating LOFA and SBLOCA transients in RELAP5 code for the Bushehr Nuclear Power Plant (BNPP). The main advantage of this method is that with the failure of more than one sensor, the detection of other sensors is not completely disrupted, and are monitored continually and independently.