Model-based Approach to Automated Calculation of Key Performance Indicators for Industrial Turbines

Gulnar Mehdi, Davood Naderi, Giuseppe Ceschini, Alexey Fishkin, Sebastian Brandt, Stuart Watson, and Mikhail Roshchin
Submission Type: 
Full Paper
AttachmentSizeTimestamp
phmc_15_016.pdf707.17 KBAugust 17, 2015 - 8:55am

In recent years, the service business of the global turbo-machinery industry has undergone important changes. Many of these changes have been motivated by an increased demand for dedicated and systematic approaches to process safety, reliability, asset integrity and the overall health of the system. This has strengthened the role of key performance indicators (KPIs) as a means of providing guidance for the system’s health state and improve risk management. In order to provide trustable and accurate calculations of these performance indicators in an automated fashion, we argue for a model-based solution that deals with the complexity of diverse configurations and interdependences between system components. This paper presents a solution for calculating KPIs by a semi-automated process based on post-data processing from the site and specific system models. The models consist of a combination of system descriptions in terms of ontologies and complex event processing models. By virtue of our models, state indicator rules for KPI calculations can be formulated at different levels, identifying performance gaps and indicating precisely where action should be taken by the service engineers. With the adopted solution, we discuss the practical implementation and present results of our success story at Siemens AG for the Industrial Gas Turbines. Finally, we provide an evaluation and future developments.

Publication Year: 
2015
Publication Volume: 
6
Publication Control Number: 
016
Submission Keywords: 
model-based methods
performance analysis
gas turbines
complex systems
complex event processing
ontology
key performance indicators
Submission Topic Areas: 
Component-level PHM
Industrial applications
Model-based methods for fault detection, diagnostics, and prognosis
Submitted by: 
  
 
 
 

follow us

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