Title :
Fault Diagnosis of Marine Diesel Engine by Means of Immune-Rough Sets and RBF Neural Network
Author :
Zhang Xu ; Sun Jian-bo
Author_Institution :
Sch. of Mech. Eng., Dalian Jiaotong Univ., Dalian, China
Abstract :
A new hybrid intelligent model of rough sets and RBF neural networks for fault diagnosis is proposed. Meanwhile, a novel attribute reduction approach of rough set based on artificial immune algorithm is proposed, that can find several different minimal feature set of decision table through clonal selection, mutation and antibody suppressing strategy, then provide more selection for fault diagnosis. The diagnosis of large marine diesel engine showed that the model can reduce the cost of diagnosis and increase the efficiency of diagnosis. There will be well application prospect in practice.
Keywords :
artificial immune systems; diesel engines; fault diagnosis; neural nets; radial basis function networks; rough set theory; RBF neural network; antibody suppressing strategy; artificial immune algorithm; attribute reduction approach; clonal selection; decision table; fault diagnosis; hybrid intelligent model; immune-rough sets; marine diesel engine; mutation; Artificial intelligence; Artificial neural networks; Costs; Diesel engines; Fault diagnosis; Genetic mutations; Intelligent networks; Neural networks; Rough sets; Set theory; RBF neural network; artificial immune algorithm; attribute reduction; fault diagnosis; rough set;
Conference_Titel :
Information and Computing Science, 2009. ICIC '09. Second International Conference on
Conference_Location :
Manchester
Print_ISBN :
978-0-7695-3634-7
DOI :
10.1109/ICIC.2009.354
