Advanced Gas Turbine Rotor Shaft Fault Diagnosis Using Artificial Neural Network
Keywords:artificial intelligence, condition monitoring, excitation force, amplitude, resonance
AbstractThe effect of vibration in plant leads to catastrophic failure of a system. This is why vibration monitoring of a system constitutes a very key practice of ensuring power plant availability. Force, Amplitude and Resonance a program written in Visual Basic Programming language was utilized in this study to monitor the vibration level of the Gas Turbine (GT17) in Afam thermal station and to calculate the force causing vibration on the bearing. The program was also run using the data obtained from the plant. Results show that vibration velocity amplitude of bearing 2 on weeks 5 and 8 were 6.7mm/s and 6.6mm/s and the forces causing vibration were 2.545x104N and 2.272x104N respectively. The comparison of results obtained with maximum vibration velocity amplitude of the machine (7mm/s) showed that the vibration of the machine was tending towards the maximum value. Therefore, proper attention should be given to bearing 2 to avoid failure of the Gas Turbine.
Y. Zhao, “A profit-based approach for gas turbine power plant outage planning,” Journal of Engineering for Gas Turbines and Power, vol. 128, pp. 806-814, 2006.
A. Razak, Industrial Gas Turbines Performance and Operability, UK: Woodhead Publishing, pp. 50- 73. 2007.
I. Loboda, S. Yepifanov and Y. Feldshteyn, “An Integrated Approach to Gas Turbine Monitoring and Diagnostics,” Proceedings of IGTI/ASME Turbo Expo, 2009.
Y. Zhao, “A Sequential Approach for Gas Turbine Power Plant Preventative Maintenance Scheduling,” Journal of Engineering for Gas Turbines and Power, vol. 128, pp. 796-805, 2006.
H. Asgari, C. XiaoQi, and S. Raazesh, “Applications of Artificial Neural Networks (ANNs) to Rotating Equipment”. 3 rd Conference on Rotating Equipment in Oil and Power Industries Nov. 22-23, 2011, Razi Intl. Conference Center, Tehran, Iran.
R. Vicen, Ship Finder, Madrid, Spain Ed. Thilmany J in Computing, Mechanical Engineering, The Magazine of ASME, vol. 133, May 2011.
M. Fast, S. De and M. Assadi, “Condition Based Maintenance of Gas Turbines Using Simulation Data and Artificial Neural Network: A Demonstration of Feasibility”, ASME Turbo Expo, Berlin, 2008.
M.H. Beale, T. Hagan and H. Demuth, Neural Network Toolbox™, User’s Guide, Addison-Wesley Limited, Finland. pp. 69- 74, 2011.
I. Loboda and S. Yepifanov, “A Mixed Data-Driven and Model Based Fault Classification for Gas Turbine Diagnosis”, Proceedings of ASME Turbo Expo 2010: International Technical Congress, 8p., Scotland, UK, June 14-18, Glasgow, ASME Paper No. GT2010-23075, 2010.
E. A. Ogbonnaya and K.T. Johnson, “Optimizing Gas Turbine Rotor Shaft Fault Detection, Identification and Analysis for Effective Condition Monitoring”, Journal of Emerging Trends in Engineering and Applied Sciences (JETEAS), vol. 2, pp. 11-17, 2011.
I.Y. Li, “Performance-Analysis-Based Gas-turbine Diagnostics a Review”, Journal of Power and Energy, vol. 216 Part A IMechE, pp. 363-377, 2002.
R.V. Dukkipati and J. Srinivas, Textbook of Mechanical Vibrations, 1st ed., New Delhi: Prentice-Hall, pp. 92-101, 2006.
How to Cite
Submission of a manuscript implies: that the work described has not been published before that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication. Authors can retain copyright in their articles with no restrictions. Also, author can post the final, peer-reviewed manuscript version (postprint) to any repository or website.
Since Jan. 01, 2019, IJETI will publish new articles with Creative Commons Attribution Non-Commercial License, under Creative Commons Attribution Non-Commercial 4.0 International (CC BY-NC 4.0) License.
The Creative Commons Attribution Non-Commercial (CC-BY-NC) License permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.