Title :
PCA-AR based fault prognosis for turbine machine
Author :
Wang, Qiuyan ; Ma, Jie ; Xu, Xiaoli
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 turbine machine 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 AR 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 huge stack gas turbine shows the efficiency of the proposed approach.
Keywords :
fault diagnosis; gas turbines; petrochemicals; principal component analysis; time series; turbines; PCA model; PCA-AR based fault prognosis; gas turbine; multivariate fault prognosis; principal component analysis; sample data; squared prediction error index; statistical process monitoring; time series prediction; turbine machine; Indexes; Monitoring; Noise reduction; Predictive models; Principal component analysis; Turbines; Vibrations; AR model; fault prognosis; principal component analysis; squared prediction error; statistical process monitoring;
Conference_Titel :
Mechatronics and Automation (ICMA), 2011 International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-8113-2
DOI :
10.1109/ICMA.2011.5985954
