The stability analysis of coastal structure is very important because it involves many design parameter s to be considered for the save and economical design of structure. In the present study neural network technique is adopted to predict the stability number of rubble mound breakwater. One model is constructed based on the parameters which influence on the stability of rubble mound breakwater, the back propagation algorithm is used in training network . Agood correlation is obtained between network predicted stabilityand estimated ones. Correlation coefficient=0.88.