To solve the defects of traditional fault diagnosis neural network, such as long training time, complex structure and single-valued input, a fault diagnosis system for civil aircraft based on rough-neural network was proposed. Rough set theory was applied to the front-end neural network to reduce the data of civil aircraft fault sample so as to remove the disturbance of redundant attributes, and overcome the impaction of unrelated data that imposed on the performance of network learning, simplify network structure. Secondly, by using the rough neurons instead of the traditional neurons, the performance of network was improved, and the scope of the application of network was expanded. The effectiveness of this method was verified by Airbus A320 aircraft fault diagnosis test .
����,���.���ڴֲڼ����۵ĺ��շ������������[J]. ���շ�����, 2005, 31(4):51-53 Wang Guang, Li Jun. Aeroengine fault diagnosis based on rough sets theory[J]. Aeroengine, 2005, 31(4):51-53(in Chinese)
������,�����,����. ���ڴֲ�������ļ������������ܹ������[J]. �Ͼ�ʦ����ѧѧ��(���̼�����), 2004, 4(3):1-9 Hu Shousong, Xu Deyou, Zhang Min. Intelligent fault diagnosis of fighter control surfaces based on rough neural network[J]. Journal of Nanjing Normal University (Engineering and Technology), 2004, 4(3):1-9(in Chinese)
�Ų�ƽ,�ܵ���,����ΰ.�ֲ�������ĺ��յ���ϵͳ������Ϸ���[J]. ������ָ�ӿ���, 2006, 31(10):48-50 Du Changping, Zhou Deyun, Jiang Aiwei. A fault diagnose method of avionics system based on rough set neural network[J]. Fire Control and Command Control, 2006, 31(10):48-50(in Chinese)
Pawlak Z. Rough sets: theoretical aspects of reasoning about data[M]. London: Kluwer Acasemic Publishers, 1991
����ط.Rough��������֪ʶ��ȡ[M].����: ������ͨ��ѧ������.[J].2001 Wang Guoyin. Rough sets theory and knowledge acquisition[M]. Xi’an: Xi’an Jiaotong University Press.2001,:-
�����, ���ɽ.�ִ����ݷ���[M].����: ��е��ҵ������, 2006 Wu Jinpei, Sun Deshan. Modern data analysis[M]. Beijing: China Machine Press, 2006(in Chinese)
Lingras P. Comparison of neofuzzy and rough neural networks[J].Information Sciences.1998, 110:207-215