Feature Selection for Predictive Asset Health Management in Power Plants Using Random Forest

Authors

  • Muhammad Ghafur Abdulah Winata Santana Faculty of Mathematics and Natural Sciences, Computational Science Study Program, Bandung Institute of Technology, Bandung, Indonesia
  • Mochamad Ikbal Arifyanto Faculty of Mathematics and Natural Sciences, Computational Science Study Program, Bandung Institute of Technology, Bandung, Indonesia

Keywords:

-, feature selection, predictive maintenance, asset health management, Random Forest, power plants, criticality ranking, maintenance priority index

Abstract

In the power generation industry, effective asset health management is essential for optimizing maintenance strategies and preventing costly failures. This study focuses on feature selection for predictive asset health management using the Random Forest algorithm, applied to PLN Indonesia Power's power plant assets. A dataset of 64,999 entries containing asset criticality metrics such as Maintenance Priority Index (MPI), Asset Criticality Ranking (ACR), and other relevant features was analyzed. Using Recursive Feature Elimination (RFE), MPI, ACR, and ACRRANK were identified as the most significant predictors of asset health. The model achieved an accuracy of 93.64%, demonstrating the importance of feature selection in improving prediction performance. This research provides valuable insights into optimizing maintenance efforts through targeted data-driven predictions.

Downloads

Download data is not yet available.

References

Jardine, A. K. S., Lin, D., & Banjevic, D. (2006). A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, 20(7), 1483–1510.

Lee, J., & Ni, J. (2013). Infotronics-based intelligent maintenance system and its impact on closed-loop maintenance operations in predictive manufacturing. Journal of Intelligent Manufacturing, 24(1), 1–11.

Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32.

Singh, R., & Gupta, A. (2019). Predictive maintenance techniques in industry 4.0: A review. Journal of King Saud University - Computer and Information Sciences.

Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., & Gao, R. X. (2017). Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 115, 213–237.

Guyon, I., Weston, J., Barnhill, S., & Vapnik, V. (2002). Gene selection for cancer classification using support vector machines. Machine Learning, 46(1-3), 389–422.

Liu, K., Wang, S., & Yao, X. (2018). Feature selection using hybrid ReliefF and recursive feature elimination for fault diagnosis. Journal of Manufacturing Systems, 47, 35–45.

Wang, C., Wang, J., & Xu, H. (2020). A comprehensive review of machine learning applied to predictive maintenance for wind turbines. Applied Sciences, 10(21), 7820.

Zhang, Y., & Chen, M. (2019). Transformer fault diagnosis using Random Forest algorithm based on feature selection. Energy Reports, 5, 775–783.

Downloads

Published

2025-01-20

How to Cite

Abdulah Winata Santana, M. G., & Arifyanto, M. I. (2025). Feature Selection for Predictive Asset Health Management in Power Plants Using Random Forest. ITB Graduate School Conference, 4(1). Retrieved from https://gcs.itb.ac.id/proceeding-igsc/index.php/igsc/article/view/224

Issue

Vol. 4 No. 1 (2024)

Section

Articles

License

Copyright (c) 2025 ITB Graduate School Conference

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.