Abstract: A rough neural network method is proposed to solve the problems in an information system with interval numbers. The topologic structure and learning algorithm of the rough neural network are given, and the approximation theorem of the rough neural network is presented. Finally, to prove the feasibility of the method the rough neural network for fault verification of a fighter plane is constructed, and the simulation results show that the method is feasible and efficient.

Key words: interval numbers, fault verification, rough sets, rough neural network