Title :
The Application of Support Vector Machine on Fault Diagnosis of the Diesel Engine Exhaust Gas Turbocharger
Author :
Pan, Ruliang ; Lin, Xintong
Author_Institution :
Dept. of Marine Eng., Jiangsu Maritime Inst., Nanjing, China
Abstract :
Support vector machine (SVM) is based on structural risk minimum theory, which special study the discipline for small sample cases. First learn support vector machine fault diagnosis theory, Then analysis the common failures of the exhaust gas turbocharger, Finally using support vector machine, research the application on fault diagnosis of the turbocharger, and then through the simulation verify that the support vector machine has excellent fitting ability on fault diagnosis of the turbocharger. The research results can enrich fault diagnosis method of the exhaust gas turbocharger, and then push the further development on fault diagnosis technology of the exhaust gas turbocharger.
Keywords :
diesel engines; exhaust systems; failure analysis; fault diagnosis; fuel systems; learning (artificial intelligence); mechanical engineering computing; support vector machines; diesel engine exhaust gas turbocharger; failure analysis; fault diagnosis; learning; structural risk minimum theory; support vector machine; Diesel engines; Fault diagnosis; Kernel; Support vector machines; Surges; Time domain analysis; Training; fault diagnosis; kernel function; support vector machine; turbocharger;
Conference_Titel :
Computer Distributed Control and Intelligent Environmental Monitoring (CDCIEM), 2012 International Conference on
Conference_Location :
Hunan
Print_ISBN :
978-1-4673-0458-0
DOI :
10.1109/CDCIEM.2012.171