Research Papers: Gas Turbines: Combustion, Fuels, and Emissions

Creep Life Prediction for Aero Gas Turbine Hot Section Component Using Artificial Neural Networks

[+] Author and Article Information
M. F. Abdul Ghafir

Universiti Tun Hussein Onn Malaysia,
Parit Raja, Johor 86400, Malaysia
e-mail: fahmi@uthm.edu.my

Y. G. Li

e-mail: i.y.li@cranfield.ac.uk

L. Wang

e-mail: L.Wang2010@hotmail.co.uk
School of Engineering,
Cranfield University,
Cranfield, Bedford MK43 0AL, UK

Contributed by the Cycle Innovations Committee of ASME for publication in the JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER. Manuscript received April 29, 2013; final manuscript received September 2, 2013; published online November 14, 2013. Editor: David Wisler.

J. Eng. Gas Turbines Power 136(3), 031504 (Nov 14, 2013) (9 pages) Paper No: GTP-13-1117; doi: 10.1115/1.4025725 History: Received April 29, 2013; Revised September 02, 2013

Accurate and reliable component life prediction is crucial to ensure safety and economics of gas turbine operations. In pursuit of such improved accuracy and reliability, model-based creep life prediction methods have become more complicated and demand higher computational time. Therefore, there is a need to find an alternative approach that is able to provide a quick solution to creep life prediction for production engines while at the same time maintain the same accuracy and reliability as that of the model-based methods. In this paper, a novel creep life prediction approach using artificial neural networks is introduced as an alternative to the model-based creep life prediction approach to provide a quick and accurate estimation of gas turbine creep life. Multilayer feed forward backpropagation neural networks have been utilized to form three neural network–based creep life prediction architectures known as the range-based, functional-based, and sensor-based architectures. The new neural network creep life prediction approach has been tested with a model single-spool turboshaft gas turbine engine. The results show that good generalization can be achieved in all three neural network architectures. It was also found that the sensor-based architecture is better than the other two in terms of accuracy, with 98% of the post-test samples possessing prediction errors within ±0.4%.

Copyright © 2014 by ASME
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Fig. 1

Schematic diagram of a MFBP network

Grahic Jump Location
Fig. 2

Conceptual designs of creep life estimation architectures

Grahic Jump Location
Fig. 3

Range-based architecture

Grahic Jump Location
Fig. 4

Schematic illustration of creep life range classification

Grahic Jump Location
Fig. 5

Functional-based architecture

Grahic Jump Location
Fig. 6

Sensor-based architecture

Grahic Jump Location
Fig. 7

Methodology to finalize individual network

Grahic Jump Location
Fig. 8

Example of the observed MSE for the training, validation, and test samples

Grahic Jump Location
Fig. 9

Accumulated percentages of samples vary with error ranges for RB architecture

Grahic Jump Location
Fig. 10

Accumulated percentages of samples vary with error ranges for FB architecture

Grahic Jump Location
Fig. 11

Accumulated percentages of samples vary with error ranges for SB architecture




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In