Title :
The Application of Random Forest and Morphology Analysis to Fault Diagnosis on the Chain Box of Ships
Author :
Yang, ZhiYuan ; Tan, Qinming
Author_Institution :
Dept. of Marine Eng., Shanghai Maritime Univ. Shanghai, Shanghai, China
Abstract :
The Random Forest Algorithm (RFA), a classification and prediction models, developed by Leo Breima is generally known as the use of tree-classifier combination method. It has achieved good results when being applied to medicine, biology machine learning and other areas. However, only X. Di, T. Han, and B. S. Yang apply the RF to machinery fault diagnosis. This paper attempts to use RFA for fault classification. The results of simulation experiment indicate that RFA can effectively bring about the ship intelligent fault diagnosis of chain box.
Keywords :
fault diagnosis; learning (artificial intelligence); pattern classification; trees (mathematics); biology machine learning; classification-prediction models; fault classification; random forest-morphology analysis; ship chain box; ship intelligent fault diagnosis; tree-classifier combination method; Biological system modeling; Classification algorithms; Classification tree analysis; Fault diagnosis; Machine learning; Machine learning algorithms; Marine vehicles; Medical diagnostic imaging; Morphology; Predictive models; Morphology Analysis; Random Forest; chain box; fault diagnosis;
Conference_Titel :
Intelligent Information Technology and Security Informatics (IITSI), 2010 Third International Symposium on
Conference_Location :
Jinggangshan
Print_ISBN :
978-1-4244-6730-3
Electronic_ISBN :
978-1-4244-6743-3
DOI :
10.1109/IITSI.2010.84
