Title :
Large Rotating Machinery Fault Diagnosis and Knowledge Rules Acquiring Based on Improved RIPPER
Author :
Jiang´Hong, Sun ; Xiao´Li, Xu
Author_Institution :
Sch. of Electromech. Eng., Beijing Inf. Sci. & Technol. Univ., Beijing, China
Abstract :
The data of fault monitoring for large rotating machine are large and noisy, there are some relationships between properties and property values, which are coincide with the rules of data mining technology. The data mining technology was studied in order to obtain the laws and classify the faults. The improved RIPPER (Repeated Incremental Pruning to Produce Error Reduction) data mining rule learning algorithm was studied for large rotating machine, the rules set files were obtained by analyzing the fault samples and updated in time. The extracted knowledge rules could also be used as the real time diagnosis of common faults.
Keywords :
data mining; electric machine analysis computing; electric machines; fault diagnosis; learning (artificial intelligence); RIPPER; data mining; fault monitoring; knowledge rules; large rotating machinery fault diagnosis; learning algorithm; real time diagnosis; repeated incremental pruning to produce error reduction; Condition monitoring; Data engineering; Data mining; Electronic mail; Fault diagnosis; Information science; Libraries; Machine intelligence; Machinery; Rotating machines; data mining; fault monitoring; improved RIPPER; large rotating machine; real time diagnosis;
Conference_Titel :
Intelligent Computation Technology and Automation, 2009. ICICTA '09. Second International Conference on
Conference_Location :
Changsha, Hunan
Print_ISBN :
978-0-7695-3804-4
DOI :
10.1109/ICICTA.2009.367
