Fault Diagnosis of Test-firing Control System of Missile
Luo Gong-chun · Control Engineering of China · 2007
To the complexity of circuit principle in the missile test-fixing control system,a new method of fault diagnosis based on rough-set theory with neural network is introduced.Considering the relation or redundancy of the accessible nodes and components,on the basis of a known fault pattern base,the simplest sample collection is acquired by redundant attributes' reduction to pattern base with rough-set theory firstly.Then fault diagnosis and location are accomplished by training the collection in neural network.Compared with traditional fault diagno- sis based on neural network,the new method which has the advantages like faster diagnosis and accurate localization is illustrated.