DIAGNOSTIC RULE EXTRACTION FROM TRAINED
โ
YIMIN FAN; C.JAMES LI
๐
Article
๐
2002
๐
Elsevier Science
๐
English
โ 272 KB
This paper describes a method of extracting diagnostic rules from trained diagnostic feedforward neural nets that are constructed to recognise di!erent mechanical faults using automated weight and structure learning algorithms. The rule extracting method is based on an interpretation that considers