Abstract: Rough set theory and fuzzy neural network are combined,to take full advantages of the two of them.Based on the reduction technology to knowledge of Rough set method,and by drawing the simple rule from a large number of initial data,the fuzzy neural network was set up,which was with better topological structure,improved study speed,accurate judgment,strong fault-tolerant ability,and more practical.In order to test the validity of the method,the inverted U-tubes break accident of Steam Generator and etc are used as examples,and many simulation experiments are performed.The test result shows that it is feasible to incorporate the fault intelligence diagnosis method based on rough set and fuzzy neural network in the nuclear power plant equipment,and the method is simple and convenience,with small calculation amount and reliable result.