Feature Importance in Predicting Generator  Rotor Thermal Sensitivity: A Random  Forest-LSTM Approach

Aryatama Wisnu Wardhana; Budi Sudiarto

doi:10.62146/ijecbe.v2i4.90

Authors

Aryatama Wisnu Wardhana Universitas Indonesia
Budi Sudiarto Universitas Indonesia

DOI:

https://doi.org/10.62146/ijecbe.v2i4.90

Keywords:

thermal sensitivity, feature importance, random forest, long short term memory

Abstract

Thermal sensitivity incidents on generator rotors at Muara Tawar Power Plant have increased over the past five years, which will have an impact on the overall performance of the power plant. The general method of conducting thermal sensitivity testing requires the generating unit to be in a certain operating pattern, thus limiting the analysis of anticipating events in real time. Correlation analysis between excitation current variables, reactive power, vibration, and temperature needs to be carried out periodically. The acquisition of these operating parameters was carried out on three generator rotors for 14 days per minute and will be implemented into a machine learning model. This study uses the Random Forest model to predict vibrations on the rotor and determine feature
importance values, with the addition of Long Short-Term Memory (LSTM) modeling to predict future trends based on feature importance. The results show that the Random Forest model can predict vibrations in the rotor and determining the importance of the features used, with an average evaluation metric RMSE of 0.92% and R² of 81.62% on the exciter side, and RMSE of 2.75% and R² of 61.42% on the turbine side. The LSTM model also demonstrates good capability in predicting future trends in thermal sensitivity identification based on exciter current features with an RMSE of 7.29% and for reactive power features of 6.52%, indicating that the proposed modeling implementation allows a better understanding of the variables relevant to thermal sensitivity, thus predicting them in the future can produce comprehensive operation and maintenance strategies.

Author Biographies

Aryatama Wisnu Wardhana, Universitas Indonesia

Department of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok, Indonesia

Budi Sudiarto, Universitas Indonesia

Department of Electrical Engineering, Faculty of Engineering, Universitas Indonesia, Depok, Indonesia

References

Ashok Rao. Natural gas-fired combined cycle (NGCC) systems. 2012. DOI: 10.1533/9780857096180.103. URL: https://doi.org/10.1533/9780857096180.103.

Sung-Ho Chang et al. “THE LIFE ASSESSMENT OF STEAM TURBINE ROTORS FOR FOSSIL POWER PLANTS”. In: World Scientific 20.25n27 (Oct. 2006), pp. 4371–4376. DOI: 10.1142/s0217979206041379. URL: https://doi.org/10.1142/s0217979206041379.

Abhishek Singh, W.A. Cronje, and Wesley Doorsamy. “Investigation of thermal instability testing on synchronous generator rotors using an experimental direct mapping method”. In: 27 (June 2017), pp. 321–328. DOI: 10.1109/isie.2017.8001267. URL: https://doi.org/10.1109/isie.2017.8001267.

Yang You-liang and Qing Zhao. “Generator thermal sensitivity analysis with Support Vector Regression”. In: American Control Conference (ACC). June 2010. DOI: 10.1109/acc.2010.5530699. URL: https://doi.org/10.1109/acc.2010.5530699.

Steven Chatterton, Paolo Pennacchi, and A. Vania. “An Unconventional Method for the Diagnosis and Study of Generator Rotor Thermal Bows”. In: ASM International 144.1 (Aug. 2021). DOI: 10.1115/1.4052079. URL: https://doi.org/10.1115/1.4052079.

Ruhai Li et al. “Electromagnetic Vibration Simulation of a 250-MW Large Hydropower Generator with RotorEccentricity and RotorDeformation”. In: Multidisciplinary Digital Publishing Institute 10.12 (Dec. 2017), pp. 2155–2155. DOI: 10.3390/en10122155. URL: https://doi.org/10.3390/en10122155.

Jiarui Xie, Manuel Sage, and Yaoyao Fiona Zhao. “Feature selection and feature learning in machine learning applications for gas turbines: A review”. In: Engineering Applications of Artificial Intelligence (Nov. 2022). DOI: 10.1016/j.engappai.2022.105591. URL: https://doi.org/10.1016/j.engappai.2022.105591.

Li Guo et al. “An Improved Feature Selection Method Based on Random Forest Algorithm for Wind Turbine Condition Monitoring”. In: Multidisciplinary Digital Publishing Institute 21.16 (Aug.2021), pp. 5654–5654. DOI: 10.3390/s21165654. URL: https://doi.org/10.3390/s21165654.

José V. Bernardes et al. “Hydropower Operation Optimization Using Machine Learning: A Systematic Review”. In: Artificial Intelligence (Feb. 2022). DOI: 10.3390/ai3010006. URL: https://doi.org/10.3390/ai3010006.

Bartolomeus Irwanto, Lothar Eckert, and Thorsten Prothmann. “Thermal Unbalance Behaviour of Turbogenerator Rotors”. In: Lecture Notes in Mechanical Engineering. 2015. DOI: 10.1007/978-3-31906590-8_183. URL: https://doi.org/10.1007/978-3-319-06590-8_183.

Abhishek Singh, Wesley Doorsamy, and W.A.Cronje.“Thermographical analysis of turbo-generatorrotor”. In: Electric Power Systems Research 163 (July 2018), pp. 252–260. DOI: 10.1016/j.epsr.2018.06.019. URL: https://doi.org/10.1016/j.epsr.2018.06.019.

Ronald J. Zawoysky and William M. Genovese. “Generator Rotor Thermal Sensitivity — Theory and Experience”. In: (Apr. 2001).

Alexi S. Rakow et al. “Root Cause Failure Analysis of a 373 Megawatt Steam Turbine Generator Exhibiting Both Reversible and Irreversible Thermal Sensitivity”. In: ASME Power Conference. Jan.2011, pp. 499–506. DOI: 10.1115/power2011-55011. URL: https://doi.org/10.1115/power2011-55011.

Yu.V. Shurub and Yu. L. Tsitsyurskiy. “Turbo generator Rotor Heating in Presence of Rotor Winding Defects and Excitation Current Forcing”. In: (Feb. 2020).

Andri Febriyanto and Hilarius Tutut Sandewan. “Rotor Thermal Sensitivity experience on 143.4 MVA hydrogen-cooled turbo generator with direct-cooled rotor design”. In: International Conference on Electrical Engineering and Informatics (ICEEI). July 2011, pp. 1–6. DOI: 10.1109/iceei.2011.6021643. URL: https://doi.org/10.1109/iceei.2011.6021643.

Leo Breiman. Random Forests. Jan. 2001.

Andy Liaw and Matthew C. Wiener. “Classification and Regression by randomForest”. In: (Jan.2007). URL: http://cogns.northwestern.edu/cbmg/LiawAndWiener2002.pdf.

Mark R. Segal. “Machine Learning Benchmarks and Random Forest Regression”. In: (Apr. 2004). URL: https://escholarship.org/content/qt35x3v9t4/qt35x3v9t4.pdf.

Carolin Strobl and Achim Zeileis. “Why and howtouserandomforest variable importance measures (and how you shouldn’t)”. In: use R Conference. Jan. 2008. URL: https://www.r-project.org/conferences/useR-2008/abstracts/Strobl+Zeileis.pdf.

S. Hochreiter and J. Schmidhuber. Long Short-Term Memory. Feb. 2023. URL: https://www.semanticscholar . org/paper/Long-Short-Term-Memory-Hochreiter-%20Schmidhuber/44d2abe2175df8153f465f6c39b68b76a0d40ab9.

Osami Matsushita et al. Vibrations of Rotating Machinery. Jan. 2019. DOI: 10.1007/978-4-431-55453-0. URL: https://doi.org/10.1007/978-4-431-55453-0.

Bob Grissom,CharlesT.Hatch,andDonaldE.Bently.FundamentalsofRotating Machinery Diagnostics.Jan. 2002. DOI: 10.1115/1.801frm. URL: https://doi.org/10.1115/1.801frm.

Chung-Shih Hsu and Mo-Shing Chen. “Reactive power planning and operating in the deregulated power utilities”. In: International Conference on Electric Utility Deregulation and Restructuring and Power Technologies (DRPT). Nov. 2002, pp. 72–77. DOI: 10.1109/drpt.2000.855641. URL: https://doi.org/10.1109/drpt.2000.855641.

Manuel Ángel Graña-López et al. “Study of the Sustainability of Electrical Power Systems: Analysis of the Causes that Generate Reactive Power”. In: Multidisciplinary Digital Publishing Institute 11.24 (Dec. 2019), pp. 7202–7202. DOI: 10.3390/su11247202. URL: https://doi.org/10.3390/su11247202