MACHINE LEARNING-DRIVEN MAINTENANCE COST OPTIMIZATION: INSIGHTS FROM A LOCAL INDUSTRIAL COMPRESSOR CASE STUDY
Keywords:
Predictive Maintenance, Machine Learning, Industrial Compressors, Maintenance Cost Optimization, Industry 4.0Abstract
This research explores the application of machine learning (ML) techniques in predictive maintenance for industrial 5-stage compressors, focusing on cost-effectiveness, model performance, and practical implementation. The study evaluates four ML models Random Forest, Decision Trees, Logistic Regression, and Gradient Boosting using real-world data. The Random Forest model demonstrates superior performance with a 94% accuracy, followed closely by Decision Trees. Logistic Regression, while computationally efficient, underperforms in predictive accuracy. Cross-validation and hyperparameter optimization further confirm the Random Forest model’s strong generalization capabilities. Cost analysis reveals significant financial benefits from implementing ML-based predictive maintenance, with reductions in downtime and optimized maintenance schedules outweighing the initial investment. The study also highlights the integration of ML into the broader framework of Industry 4.0, emphasizing its potential to enhance equipment reliability, reduce operational costs, and foster intelligent, data-driven maintenance strategies. The research provides a comprehensive framework for industries transitioning from traditional maintenance to ML-driven approaches, contributing to improved operational efficiency and sustainability in industrial environments.
References
Monye, S. (2023). Overview and impact of maintenance process in 4th industrial revolution. E3s Web of Conferences, 430, 01220. https://doi.org/10.1051/e3sconf/202343001220
Okeagu F. N., Charles Onyeka Nwamekwe, Blessing Precy Nnamani. (2024). Challenges and Solutions of Industrial Development in Anambra State, Nigeria. Iconic Research and Engineering Journals, 7(11), 467-472. https://www.irejournals.com/formatedpaper/1705825.pdf
Chidiebube, I. N., Onyeka, N. C., Sunday, A. P., & Chiedu, E. O. (2025). A Comparative Analysis of Machine Learning Models for Inventory Demand Forecasting in A Food Manufacturing Sme. Indonesian Journal of Innovation Science and Knowledge, 2(3), 35-48. Retrieved from https://knowledge.web.id/index.php/ijisk/article/view/177
Igbokwe, N. C., Okpala, C. C., & Nwamekwe, C. O. (2024). The Implementation of Internet of Things in the Manufacturing Industry: An Appraisal. International Journal of Engineering Research and Development, 20(7), 510-516. https://www.ijerd.com/paper/vol20issue7/2007510516.pdf
Ezeanyim, O. C., Ewuzie, N. V., Aguh, P. S., Nwabueze, C. V., and Nwamekwe, C. O. (2025). Effective Maintenance of Industrial 5-Stage Compressor: A Machine Learning Approach. Gazi University Journal of Science Part A: Engineering and Innovation, 12(1), 96-118. https://dergipark.org.tr/en/pub/gujsa/issue/90827/1646993
Ringler, N. (2023). Machine learning based real time predictive maintenance at the edge for manufacturing systems: a practical example. https://doi.org/10.1109/globconet56651.2023.10150033
Igbokwe, N. C., Nwamekwe, C. O., Ono, C. G., Nwabunwanne, E. C., & Aguh, P. S. A. (2024). The Role of Digital Twins in Optimizing Renewable Energy Utilization and Energy Efficiency in Manufacturing. Siber International Journal of Digital Business (SIJDB), 1(4), 93–111. https://doi.org/10.38035/sijdb.v1i4.262
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
Okpala, C. C., Udu, C. E., & Nwamekwe, C. O. (2025). Artificial Intelligence-Driven Total Productive Maintenance: The Future of Maintenance in Smart Factories. International Journal of Engineering Research and Development (IJERD), (21)1, 68-74. https://www.ijerd.com/paper/vol21-issue1/21016874.pdf
Nwamekwe C. O., and Nwabunwanne E. C. (2025). Circular Economy and Zero-Energy Factories: A Synergistic Approach to Sustainable Manufacturing. Journal of Research in Engineering and Applied Sciences (JREAS), 10(1), 829-835. https://qtanalytics.in/journals/index.php/JREAS/article/view/4567
Townsend, J. and Badar, M. (2018). Impact of condition monitoring on reciprocating compressor efficiency. Journal of Quality in Maintenance Engineering, 24(4), 529-543. https://doi.org/10.1108/jqme-06-2017-0040
Okpala, C. C., Ezeanyim, O. C., & Nwamekwe, C. O. (2024). The Implementation of Kaizen Principles in Manufacturing Processes: A Pathway to Continuous Improvement. International Journal of Engineering Inventions, 13(7), 116-124. https://www.ijeijournal.com/papers/Vol13-Issue7/1307116124.pdf
Nwamekwe, C. O., and Okpala, C. C. (2025). Circular economy strategies in industrial engineering: From theory to practice. International Journal of Multidisciplinary Research and Growth Evaluation, 6(1): 1773-1782. https://www.allmultidisciplinaryjournal.com/uploads/archives/20250212103754_MGE-2025-1-288.1.pdf
Xiao, S., Ang, N., Zhang, Z., Liu, S., Song, M., and Zhang, H. (2020). Fault diagnosis of a reciprocating compressor air valve based on deep learning. Applied Sciences, 10(18), 6596. https://doi.org/10.3390/app10186596
Okpala C. C., Chukwudi Emeka Udu, & Charles Onyeka Nwamekwe. (2025). Sustainable HVAC Project Management: Strategies for Green Building Certification. International Journal of Industrial and Production Engineering, 3(2), 14-28. https://journals.unizik.edu.ng/ijipe/article/view/5595
Nwamekwe, C. O., and 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
Raja, H., Kudelina, K., Asad, B., Vaimann, T., Kallaste, A., Rassõlkin, A., … and Khang, H. (2022). Signal spectrum-based machine learning approach for fault prediction and maintenance of electrical machines. Energies, 15(24), 9507. https://doi.org/10.3390/en15249507
Nwamekwe, C. O., and Igbokwe, N. C. (2024). Supply Chain Risk Management: Leveraging AI for Risk Identification, Mitigation, and Resilience Planning. International Journal of Industrial Engineering, Technology & Operations Management, 2(2), 41–51. https://doi.org/10.62157/ijietom.v2i2.38
Davari, N., Veloso, B., Costa, G., Pereira, P., Ribeiro, R., and Gama, J. (2021). A survey on data-driven predictive maintenance for the railway industry. Sensors, 21(17), 5739. https://doi.org/10.3390/s21175739
Nwamekwe, C. O., Chidiebube, I. N., Godfrey, O. C., Celestine, N. E., & Sunday, A. P. (2025). Resilience and Risk Management in Social Robot Systems: An Industrial Engineering Perspective. Culture Education and technology research (Cetera), 2(2), 1–12. Retrieved from https://cetera.web.id/index.php/ctr/article/view/154
Wang, Y., Gogu, C., Binaud, N., Bès, C., Haftka, R., and Kim, N. (2018). Predictive airframe maintenance strategies using model-based prognostics. Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability, 232(6), 690-709. https://doi.org/10.1177/1748006x18757084
Koops, L. (2018). Roc-based business case analysis for predictive maintenance – applications in aircraft engine monitoring. PHM Society European Conference, 4(1). https://doi.org/10.36001/phme.2018.v4i1.460
Nwamekwe, C. O., Chinwuko, C. E. & Mgbemena, C. E. (2020). Development and Implementation of a Computerised Production Planning and Control System. UNIZIK Journal of Engineering and Applied Sciences, 17(1), 168-187
Ameeri, T. (2023). Analysing effective and ineffective impacts of maintenance strategies on electric power plants: a comprehensive approach. Energies, 16(17), 6243. https://doi.org/10.3390/en16176243
Alves, F., Badikyan, H., Moreira, H., Azevedo, J., Moreira, P., Romero, L., … and Leitão, P. (2020). Deployment of a smart and predictive maintenance system in an industrial case study. https://doi.org/10.1109/isie45063.2020.9152441
Nwamekwe, C. O., Ewuzie, N. V., Igbokwe, N. C., U-Dominic, C. M., & Nwabueze, C. V. (2024). Adoption of Smart Factories in Nigeria: Problems, Obstacles, Remedies and Opportunities. International Journal of Industrial and Production Engineering, 2(2). Retrieved from https://journals.unizik.edu.ng/ijipe/article/view/4167
Tounsi, Youssef and Anoun, Houda & Hassouni, Larbi. (2020). CSMAS: Improving Multi-Agent Credit Scoring System by Integrating Big Data and the new generation of Gradient Boosting Algorithms. 1-7. 10.1145/3386723.3387851.
Nwamekwe, C. O., Ewuzie, N.V., Igbokwe, N. C., Nwabunwanne, E. C., & Ono, C. G. (2025). Digital Twin-Driven Lean Manufacturing: Optimizing Value Stream Flow. Letters in Information Technology Education (LITE), 8 (1), pp.1-13. https://hal.science/hal05127340/
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.
Alrabghi, A. and Tiwari, A. (2015). State of the art in simulation-based optimisation for maintenance systems. Computers & Industrial Engineering, 82, 167-182. https://doi.org/10.1016/j.cie.2014.12.022
Nwamekwe, C. O., Ewuzie, N. V., Okpala, C. C., Ezeanyim, C., Nwabueze, C. V., & Nwabunwanne, E. C. (2025). Optimizing Machine Learning Models for Soil Fertility Analysis: Insights from Feature Engineering and Data Localization. Gazi University Journal of Science Part A: Engineering and Innovation, 12(1), 36-60. https://dergipark.org.tr/en/pub/gujsa/issue/90827/1605587
Mobtahej, P., Zhang, X., Hamidi, M., and Zhang, J. (2022). An lstm-autoencoder architecture for anomaly detection applied on compressors audio data. Computational and Mathematical Methods, 2022, 1-22. https://doi.org/10.1155/2022/3622426
Igbokwe, N. C., Nwamekwe, C. O., Godwin, H. C., & Mba W. (2025). Optimization of Overall Equipment Effectiveness Factors in A Food Manufacturing Small and Medium Enterprise. Journal of Research in Engineering and Applied Sciences (JREAS), 10(1), 836-845. https://qtanalytics.in/journals/index.php/JREAS/article/view/4660
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. Retrieved from https://doi.org/10.1007/s00226-020-01196-z
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
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. Retrieved from https://doi.org/10.48550/arXiv.1106.1813
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. Retrieved from https://doi.org/10.1109/ACCESS.2021.3084050.
3.png)
1.png)
1.png)
