Title :
PCA-SVM Based Fault Prognosis for Flue Gas Turbine
Author :
Jie Ma ; Qiuyan Wang ; Aiming Dong
Author_Institution :
Dept. of Autom., Beijing Inf. Sci. & Technol. Univ., Beijing, China
Abstract :
In this paper, a multivariate fault prognosis approach based on statistical process monitoring (SPM) methods and time series prediction for flue gas turbine was proposed. A principal component analysis (PCA) model using sample data under normal state was built. Firstly, fault is detected by squared prediction error (SPE) index, then predicted by SVM model. With development of fault process, the SPE will produce a corresponding change and carry important fault information, so calculate statistics of SPE can be characterized and predict the trend of fault and level. A case study on the flue gas turbine shows the efficiency of the proposed approach.
Keywords :
fault diagnosis; flue gases; gas turbines; maintenance engineering; power engineering computing; principal component analysis; support vector machines; PCA-SVM based fault prognosis; flue gas turbine; multivariate fault prognosis; principal component analysis; squared prediction error index; statistical process monitoring methods; time series prediction; Monitoring; Noise reduction; Predictive models; Principal component analysis; Support vector machines; Turbines; Vibrations; SVM model; fault prognosis; principal component analysis; squared prediction error; statistical process monitoring;
Conference_Titel :
Instrumentation, Measurement, Computer, Communication and Control (IMCCC), 2012 Second International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4673-5034-1
DOI :
10.1109/IMCCC.2012.307
