Effective Maintenance of Industrial 5-Stage Compressor: A Machine Learning Approach

Abstract

Effective maintenance is crucial in the manufacturing industry to ensure equipment reliability, product quality, and worker safety. This study focuses on using machine learning, specifically the Random Forest algorithm, to predict maintenance needs for a 5-stage compressor. Utilizing the Scikit-learn Python toolkit, the model underwent rigorous evaluation through validation, sampling, and confusion matrix inspection. The model achieved an outstanding ROC AUC score of 0.94 and consistently high accuracy, precision, recall, and F1-score metrics above 0.90, showcasing its strong predictive capabilities. By accurately predicting machine failures, the approach aims to improve production schedules, boost productivity, ensure high-quality outputs, save costs, and extend equipment lifespan, demonstrating significant promise for practical use in the manufacturing sector.

Keywords

• Cost-Effective Maintenance
• Industrial Compressor
• Machine Learning
• Predictive Maintenance
• Data-Driven Maintenance
• Maintenance Optimization

References

1. Adetunji, O., Sokunbi, I., Kuye, S., Adesusi, O., and Okediran, I. (2023). Condition-based monitoring of kiln induced draft fan in a dry process cement plant for efficient utilization. Journal of Advanced Industrial Technology and Application, 4(1). https://doi.org/10.30880/jaita.2023.04.01.007
2. Bacak, A., Çolak, A., and Dalkılıç, A. (2023). Investigating hermetic reciprocating compressor performance by using various machine learning methods. Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science, 238(11), 5369-5384. https://doi.org/10.1177/09544062231213276
3. Bahtiar, E., Denih, A., Priadi, T., Putra, G., Koswara, A., Nugroho, N., … and Hermawan, D. (2022). Comparing the building code sawn lumber’s wet service factors (cm) with four commercial wood species laboratory tests. Forests, 13(12), 2094. https://doi.org/10.3390/f13122094
4. Cao, X., Jing, Z., Zhao, X., and Xu, X. (2024). A security‐enhanced equipment predictive maintenance solution for the eto manufacturing. International Journal of Network Management, 34(6). https://doi.org/10.1002/nem.2263
5. Carvalho, T., Soares, F., Vita, R., Francisco, R., Basto, J., and Alcalá, S. (2019). A systematic literature review of machine learning methods applied to predictive maintenance. Computers and Industrial Engineering, 137, 106024. https://doi.org/10.1016/j.cie.2019.106024
6. Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research. https://doi.org/10.48550/arXiv.1106.1813
7. Chicco, D., Warrens, M. J., and Jurman, G. (2021). The Matthews correlation coefficient (MCC) is more informative than Cohen’s Kappa and Brier Score in binary classification assessment. IEEE. https://doi.org/10.1109/ACCESS.2021.3084050
8. García, F., and Salgado, D. (2021). Maintenance strategies for industrial multi-stage machines: The study of a thermoforming machine. Sensors, 21(20), 6809. https://doi.org/10.3390/s21206809

9. Hanif, W., and Gunawan, F. (2022). Random forest regression to predict catalyst deactivation in industrial catalytic process. TEM Journal, 104-110. https://doi.org/10.18421/tem111-12
10. Joshi, A. V. (2023). Machine learning and artificial intelligence (2nd ed.). Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-031-12282-8
11. Kagiri, C., Wanjiru, E., Zhang, L., and Xia, X. (2018). Optimized response to electricity time-of-use tariff of a compressed natural gas fuelling station. Applied Energy, 222, 244-256. https://doi.org/10.1016/j.apenergy.2018.04.017
12. Kiangala, K. and Wang, Z. (2020). An effective predictive maintenance framework for conveyor motors using dual time-series imaging and convolutional neural network in an industry 4.0 environment. Ieee Access, 8, 121033-121049. https://doi.org/10.1109/access.2020.3006788
13. Kolar, D., Lisjak, D., Curman, M., and Pająk, M. (2022). Condition monitoring of rotary machinery using industrial iot framework. Tehnički Glasnik, 16(3), 343-352. https://doi.org/10.31803/tg-20220517173151
14. Li, J., Cheng, K., Wang, S., Morstatter, F., Trevino, R. P., Tang, J., and Liu, H. (2017). Feature selection: A data perspective. ACM Computing Surveys (CSUR), 50(6), 1-45.
15. Loukopoulos, P., Zolkiewski, G., Bennett, I., Sampath, S., Pilidis, P., Duan, F., … and David, É. (2019). Reciprocating compressor prognostics of an instantaneous failure mode utilising temperature only measurements. Applied Acoustics, 147, 77-86. https://doi.org/10.1016/j.apacoust.2017.12.003
16. Luo, Y. (2024). Optimizing maintenance strategies for reciprocating compressors using reliability-centered maintenance and on-line fault diagnosis system. https://doi.org/10.1117/12.3026849
17. Monye, S., Afolalu, S., Lawal, S., Oluwatoyin, O., and Adeyemi, A. (2023). Overview and impact of maintenance process in 4th industrial revolution. E3s Web of Conferences, 430, 01220. https://doi.org/10.1051/e3sconf/202343001220
18. Nordal, H. and El‐Thalji, I. (2021). Assessing the technical specifications of predictive maintenance: a case study of centrifugal compressor. Applied Sciences, 11(4), 1527. https://doi.org/10.3390/app11041527
19. Nwamekwe, C. O., & Okpala, C. C. (2025). Machine learning-augmented digital twin systems for predictive maintenance in highspeed rail networks. International Journal of Multidisciplinary Research and Growth Evaluation, 6(1), 1783-1795. https://www.allmultidisciplinaryjournal.com/uploads/archives/20250212104201_MGE-2025-1-306.1.pdf
20. Nwamekwe, C. O., Ewuzie, N. V., Igbokwe, N. C., Okpala, C. C., and U-Dominic, C. M. (2024). Sustainable Manufacturing Practices in Nigeria: Optimization and Implementation Appraisal. Journal of Research in Engineering and Applied Sciences, 9(3). https://qtanalytics.in/journals/index.php/JREAS/article/view/3967
21. Nwamekwe, C. O., Okpala, C. C., and Okpala, S. C., (2024). Machine Learning-Based Prediction Algorithms for the Mitigation of Maternal and Fetal Mortality in the Nigerian Tertiary Hospitals. International Journal of Engineering Inventions, 13(7), PP: 132-138. https://www.ijeijournal.com/papers/Vol13-Issue7/1307132138.pdf
22. Rahman, A., Hoque, M., Rashid, F., Alam, F., and Ahmed, M. (2022). Health condition monitoring and control of vibrations of a rotating system through vibration analysis. Journal of Sensors, 2022, 1-12. https://doi.org/10.1155/2022/4281596
23. Septano, G., Ikbal, I., Fathoni, F., Sriwijaya, S., and Putri, S. (2024). Detection of damage motor and coal crusher in power plant tanjung enim 3 x 10 mw using vibration analysis. Journal of Ocean Mechanical and Aerospace -Science and Engineering- (Jomase), 68(3), 155-160. https://doi.org/10.36842/jomase.v68i3.378
24. Souza, D. V., Santos, J. X., Vieira, H. C., Naide, T. L., Nisgoski, S., and Oliveira, L. E. S. (2020). An automatic recognition system of Brazilian flora species based on textural features of macroscopic images of wood. Wood Science and Technology. https://doi.org/10.1007/s00226-020-01196-z
25. Tounsi, Y., Anoun, H., and Hassouni, L. (2020). CSMAS: Improving multi-agent credit scoring system by integrating big data and the new generation of gradient boosting algorithms. Proceedings of the 2020 International Conference on Advanced Information Networking and Applications Workshops (WAINA), 1-7. https://doi.org/10.1145/3386723.3387851
26. Van Der Maaten, L., Postma, E. O., and van den Herik, H. J. (2009). Dimensionality reduction: A comparative review. Journal of Machine Learning Research, 10, 66-71, 13.
27. Wang, W., Li, L., Gu, H., Chen, Y., Zhen, Y., and Dong, Z. (2022). Random forest-based prediction of acute respiratory distress syndrome in patients undergoing cardiac surgery. The Heart Surgery Forum, 25(6), E854-E859. https://doi.org/10.1532/hsf.5113
28. Yamada, T., Asanuma, H., Hara, Y., and Ertürk, A. (2023). Acceleration-waveform-sending wireless sensor node powered by piezoelectric vibration energy harvester. https://doi.org/10.1117/12.2657742