0
Technical Briefs

Prognostics of Machine Condition Using Energy Based Monitoring Index and Computational Intelligence

[+] Author and Article Information
B. Samanta1

Department of Mechanical Engineering, Villanova University, 800 Lancaster Avenue, Villanova, PA 19085biswanath.samanta@villanova.edu

C. Nataraj

Department of Mechanical Engineering, Villanova University, 800 Lancaster Avenue, Villanova, PA 19085

1

Corresponding author.

J. Comput. Inf. Sci. Eng 9(4), 044502 (Nov 02, 2009) (6 pages) doi:10.1115/1.3249574 History: Received June 24, 2008; Revised January 06, 2009; Published November 02, 2009; Online November 02, 2009

A study is presented on applications of computational intelligence (CI) techniques for monitoring and prognostics of machinery conditions. The machine condition is assessed through an energy-based feature, termed as “energy index,” extracted from the vibration signals. The progression of the “monitoring index” is predicted using the CI techniques, namely, recursive neural network (RNN), adaptive neurofuzzy inference system (ANFIS), and support vector regression (SVR). The proposed procedures have been evaluated through benchmark data sets for one-step-ahead prediction. The prognostic effectiveness of the techniques has been illustrated through vibration data set of a helicopter drivetrain system gearbox. The prediction performance of SVR was better than RNN and ANFIS. The improved performance of SVR can be attributed to its inherently better generalization capability. The training time of SVR was substantially higher than RNN and ANFIS. The results are helpful in understanding the relationship of machine conditions, the corresponding indicating feature, the level of damage or degradation, and their progression.

FIGURES IN THIS ARTICLE
<>
Copyright © 2009 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Overall schematic of machine prognostics

Grahic Jump Location
Figure 2

Training results for sunspot activity: (a) RNN, (b) ANFIS, and (c) SVR

Grahic Jump Location
Figure 3

Preprocessed vibration signal of a helicopter drivetrain gearbox

Grahic Jump Location
Figure 4

Test results for gear failure prognostics: (a) RNN, (b) ANFIS, and (c) SVR

Tables

Errata

Discussions

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