A Case for the Use of Data-driven Methods in Gas Turbine Prognostics

Márcia Lourenço Baptista, Cairo Lúcio Nascimento Junior, Helmut Prendinger, and Elsa Maria Pires Henriques
Submission Type: 
Full Paper
phmc_17_063.pdf2.47 MBSeptember 6, 2017 - 2:32pm

The goal of data-driven methods is to remove dependence on classical models of structured expert judgment and draw meaningful insights of causal relationships directly from the data. This paper investigates the potential of using data-driven methods, namely uni-variate multiple linear regression, k-nearest neighbours, feed-forward neural networks, random forests and linear support vector regression to predict the end of life (EOL) and remaining useful life (RUL) of gas turbine engines. The algorithms are demonstrated on a real-world large-scale dataset consisting of a multidimensional time series of health monitoring (HM) indicators collected from a set of modern gas turbine engines. A stratified version of 10-fold cross-validation is used to compare the performance of the five prediction models. An experience-based Weibull model is chosen as the baseline method. Models are evaluated according to established metrics in the field including median absolute error, median absolute deviation and relative accuracy.The prediction results indicate that the support vector regression and the random forests are the most accurate models. Neural networks and k-nearest neighbours also show improved forecast skill compared to the baseline model while beating the more traditional technique of linear regression. In regards to error spread, results are not as expressive even though all the selected data-driven methods provide good results, outperforming the baseline.

Publication Year: 
Publication Volume: 
Publication Control Number: 
Page Count: 
Submission Keywords: 
Data-driven Methods
Life Usage Modelling
PHM industrial applications
Submission Topic Areas: 
Data-driven methods for fault detection, diagnosis, and prognosis
Industrial applications
Submitted by: 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed