Review of feature selection methods for Predictive Maintenance Systems

  • 1 AGH University of Krakow, Poland


The development of Industry 4.0 and Predictive Maintenance Systems allows for effective utilization of equipment by incorporating ML methods for identifying tool condition. However, including large number of Condition Indicators for machinery monitoring increases computational complexity, hence the response of the system elongates. Therefore, it is important to check the utility of indicators and reduce them. In this paper, we investigate different feature selection methods: AIC (Akaike Information Criterion), BIC (Bayesian Information Criterion), Random Forest, Lasso Regression (L1 Regularization) for NASA Gearbox Fault Detection Dataset, PHM 2009. We processed the raw data and calculated CI from time domain, frequency domain and envelope. An SVM Classifier model was trained on full collection of indicator and reduced, then performances were compared. The obtained results highlight the advantage of feature selection, proving that effective PdM systems can be based on diminished number of Health Indicators.



  1. Talavera, L. (2005). An Evaluation of Filter and Wrapper Methods for Feature Selection in Categorical Clustering. In: Famili, A.F., Kok, J.N., Peña, J.M., Siebes, A., Feelders, A. (eds) Advances in Intelligent Data Analysis VI. IDA 2005. Lecture Notes in Computer Science, vol 3646. Springer, Berlin, Heidelberg.
  2. A. Jović, K. Brkić and N. Bogunović, "A review of feature selection methods with applications," 2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, Croatia, 2015, pp. 1200-1205
  3. D. Neupane and J. Seok, "Bearing Fault Detection and Diagnosis Using Case Western Reserve University Dataset With Deep Learning Approaches: A Review," in IEEE Access, vol. 8, pp. 93155-93178, 2020
  4. PHM 2009 Data challenge Competition, (2009). []
  5. PHM 2009 Data challenge Competition - labeled version form November. [ Dataset/tree/main/PHM2009%20Gearbox/PHM_Society_2009_Co mpetition_Expanded_txt]
  6. Al-Atat, Hassan & Siegel, David & Lee, Jay. (2011). A Systematic Methodology for Gearbox Health Assessment and Fault Classification. International Journal of Prognostics and Health Management. 2. 10.36001/ijphm.2011.v2i1.1339.
  7. Vikas Sharma and Anand Parey. „A review of gear fault diagnosis using various condition indicators”. W: Elsevier 144 (2016), s. 253–263.
  8. Cédric Peeters, Jérôme Antoni, Jan Helsen, “Blind filters based on envelope spectrum sparsity indicators for bearing and gear vibration-based condition monitoring”, Mechanical Systems and Signal Processing, Volume 138, 2020, 106556
  9. Roque, Antonio & Silva, Tiago & Calado, João & Dias, J.. (2009). An approach to fault diagnosis of rolling bearings. WSEAS Transactions on Systems and Control. 4.
  10. Rossi R, Murari A, Gaudio P, Gelfusa M. Upgrading Model Selection Criteria with Goodness of Fit Tests for Practical Applications. Entropy. 2020; 22(4):447
  11. Albahli S, Yar GNAH. Defect prediction using akaike and bayesian information criterion. Comput Syst Sci Eng. 2022;41(3):1117-1127
  12. Khalili, Abbas. (2011). An Overview of the New Feature Selection Methods in Finite Mixture of Regression Models. Journal of the Iranian Statistical Society JIRSS. 2.
  13. Aurélien Géron. „Hands-on Machine Learning with Scikit- Learn, Keras, and TensorFlow, Concepts, Tools, and Techniques to Build Intelligent Systems (second edition)”. Sebastopol, CA: O’Reilly Media, Inc., 2019

Article full text

Download PDF