Application of Factor Analysis to a Type Diesel Engine SOA

Author

Tao Liu ; Hongxiang Tian ; Wenyong Guo

Author_Institution

Naval Univ. of Eng., Wuhan, China

Volume

1

fYear

2010

fDate

13-14 March 2010

Firstpage

612

Lastpage

615

Abstract

In order to monitor wear condition of a type of six-cylinder diesel engine, 69 oil samples from an experiment engine in laboratory and 117 oil routine samples on site were taken. With the Spectroil M type Instrument made in U. S. America, 16 elements´ concentrations of every oil sample were detected. All data were analyzed by Factor Analysis. The results shows that mining oil spectroscopy data by Factor Analysis can be used to reveal the sources of different elements, monitor engine condition and diagnose wear fault. Based on the Load Matrix and Factor Scores, Factor Analysis clusters spectrometric oil data according to not only elements but also working conditions effectively.

Keywords

condition monitoring; data mining; diesel engines; fault diagnosis; mechanical engineering computing; oils; pattern clustering; spectroscopy; spectroscopy computing; wear; engine condition monitoring; factor analysis; factor scores; load matrix; oil spectroscopy data mining; six-cylinder diesel engine; spectroil M type instrument; spectrometric oil data clustering; type diesel engine spectrometric oil analysis; wear condition monitoring; wear fault diagnosis; Condition monitoring; Data analysis; Data mining; Diesel engines; Employee welfare; Instruments; Laboratories; Petroleum; Semiconductor optical amplifiers; Spectroscopy; Diesel Engine; Factor Analysi; Lubricating Oil; Spectrometric Oil Analysis (SOA);

fLanguage

English

Publisher

ieee

Conference_Titel

Measuring Technology and Mechatronics Automation (ICMTMA), 2010 International Conference on

Conference_Location

Changsha City

Print_ISBN

978-1-4244-5001-5

Electronic_ISBN

978-1-4244-5739-7

Type

conf

DOI

10.1109/ICMTMA.2010.397

Filename

5458967