Dual-Criteria Predictive Maintenance System for Chillers Based on Fuzzy Logic

Abstract

This article presents a dual-criteria predictive maintenance system for refrigeration units (chillers), developed using fuzzy logic and implemented in the LabVIEW environment. The objective of the research is to eliminate the shortcomings of traditional maintenance methods through the integration of analysis of the current equipment condition and historical failure data. To achieve this goal, an architecture is proposed, including three interconnected fuzzy controllers: the first processes current parameters (compressor vibration, temperature and pressure characteristics), the second analyzes historical data, and the third integrates the results to form recommendations. The optimized rule base (201 rules) allows classifying the equipment condition without detailing specific levels, which simplifies calculations without loss of accuracy. The system provides a five-level classification of equipment condition, which allows forming targeted maintenance recommendations, from planned monitoring to emergency intervention. Experimental validation on refrigeration units (chillers) at Kadmous Hospital in Syria (2023--2024) confirmed a 29 % reduction in failures, 91.7 % prediction accuracy, and a 35 % reduction in unplanned downtime. The results demonstrate the advantages of the proposed approach over traditional methods and artificial neural networks under conditions of data uncertainty due to interpretability and the use of expert knowledge, which is especially important for critical systems such as medical equipment

Please cite this article in English as:

Mahmoud R., Gavryushin S.S. Dual-criteria predictive maintenance system for chillers based on fuzzy logic. Herald of the Bauman Moscow State Technical University, Series Instrument Engineering, 2026, no. 2 (155), pp. 41--57 (in Russ.). EDN: BGAPIG

References

[1] Rueda E., Tassou S.A., Grace I.N. Fault detection and diagnosis in liquid chillers. Proc. Inst. Mech. Eng. E, 2005, vol. 219, no. 2, pp. 117--125. DOI: https://doi.org/10.1243/095440805X8575

[2] Wu Y., Maravelias C.T., Wenzel M.J., et al. Predictive maintenance scheduling optimization of building heating, ventilation, and air conditioning systems. Energy Build., 2021, vol. 231, art. 110487. DOI: https://doi.org/10.1016/j.enbuild.2020.110487

[3] Koybagarov M.K., Isabekov Zh.N., Kurmangalieva L.A., et al. Development of a predictive maintenance system based on machine learning. Vestnik Universiteta Shakarima. Tekhnicheskie nauki [Bulletin of Shakarim University. Technical Sciences], 2025, no. 2, pp. 121--128 (in Russ.). DOI: https://doi.org/10.53360/2788-7995-2025-2(18)-14

[4] Thomas D.S., Weiss B.A. Economics of manufacturing machinery maintenance: a survey and analysis of U.S. costs and benefits. DOI: https://doi.org/10.6028/NIST.AMS.100-34

[5] Poor P., Zenisek D., Basl J. Historical overview of maintenance management strategies: development from breakdown maintenance to predictive maintenance in accordance with four industrial revolutions. Proc. Int. Conf. on Industrial Engineering and Operations Management, 2019, pp. 495--504.

[6] Yedurkar D.P., Schlech T., Sause M.G.R. A systematic review on smart and predictive maintenance in tool condition monitoring. IEEE Access, 2025, vol. 13, pp. 106259--106281. DOI: https://doi.org/10.1109/ACCESS.2025.3579204

[7] Sokolovich M.G., Aksenenko M.A., Zakharyev V.A. [Systems of predictive maintenance of technological equipment based on artificial intelligence methods]. ITS 2024. Mater. Mezhdunar. nauch. konf. [ITS 2024. Proc. Int. Sc.-Tech. Conf.]. Minsk, BGUIR Publ., 2024, pp. 32--33 (in Russ.).

[8] Elias H. Predictive maintenance: techniques and applications in PLC and IoT --- case study in Jableh Mill. Master’s thesis. Damascus, SVU, 2021.

[9] Ran Y., Zhou X., Lin P., et al. A survey on Intelligent Predictive Maintenance (IPdM) in the era of fully connected intelligence. IEEE Commun. Surv. Tutor., 2019, vol. 28, pp. 633--671. DOI: https://doi.org/10.1109/COMST.2025.3567802

[10] Myntsov A.A., Myntsova O.V. Organization of predictive maintenance of dynamic equipment. Informatizatsiya i sistemy upravleniya v promyshlennosti, 2020, no. 1, pp. 50--53 (in Russ.).

[11] Mitrofani I.A., Emiris D.M., Koulouriotis D.E. An industrial maintenance decision support system based on fuzzy inference to optimize scope definition. Procedia Manuf., 2020, vol. 51, pp. 1538--1543. DOI: https://doi.org/10.1016/j.promfg.2020.10.214

[12] Prommachan W., Pipathattakul M., Surin P., et al. Predictive maintenance model for rotating machinery using a fuzzy logic. IEEE ICPEI, 2022. DOI: https://doi.org/10.1109/ICPEI55293.2022.9987151

[13] Dutta S. Fuzzy logic applications: technological and strategic issues. IEEE Trans. Eng. Manag., 1993, vol. 40, no. 3, pp. 237--254. DOI: https://doi.org/10.1109/17.233185

[14] Fouad R.H., Samhouri M. A fuzzy logic approach for scheduling preventive maintenance in ERP systems. Int. Conf. on Management and Service Science, 2011. DOI: https://doi.org/10.1109/ICMSS.2011.5999330

[15] Frigura-Iliasa M., Simo A., Dzitac S., et al. Fuzzy-logic based diagnosis for high voltage equipment predictive maintenance. In: Intelligent methods in computing, communications and control. Springer, 2021, pp. 245--253. DOI: https://doi.org/10.1007/978-3-030-53651-0_21

[16] Baban C., Baban M., Darius S.M. Using a fuzzy logic approach for the predictive maintenance of textile machines. J. Intell. Fuzzy Syst., 2016, vol. 30, no. 2, pp. 999--1006. DOI: https://doi.org/10.3233/IFS-151822

[17] Baban M., Baban C.F., Moisi B. A fuzzy logic-based approach for predictive maintenance of grinding wheels of automated grinding lines. 23rd MMAR, 2018, pp. 483--486. DOI: https://doi.org/10.1109/MMAR.2018.8486144

[18] Dapshima B., Chuupa Y.E., Chaturvedi S. Fault detection and protection of power transformer using fuzzy logic. IJRASET, 2023, vol. 11, no. 1, pp. 1816--1824. DOI: https://doi.org/10.22214/ijraset.2023.48748

[19] Pezeshki Z., Mazinani S.M. Comparison of artificial neural networks, fuzzy logic and neuro fuzzy for predicting optimization of building thermal consumption: a survey. Artif. Intell. Rev., 2018, vol. 52, no. 1, pp. 495--525. DOI: https://doi.org/10.1007/s10462-018-9630-6

[20] Singhala P., Shah D., Patel B. Temperature control using fuzzy logic. IJICS, 2014, vol. 4, no. 1. DOI: https://doi.org/10.5121/ijics.2014.4101

[21] Merfi K. Choosing the most suitable predictive maintenance sensor. Elektronika: nauka, tekhnologiya, biznes [Electronics: Science, Technology, Business], 2020, no. 9, pp. 96--103 (in Russ.). DOI: https://doi.org/10.22184/1992-4178.2020.200.9.96.102

[22] Yakovleva M.V., Shalina A.I. Developing recommendations for implementing predictive maintenance in high-tech companies. Voprosy innovatsionnoy ekonomiki [Russian Journal of Innovation Economics], 2023, vol. 13, no. 3, pp. 1531--1550 (in Russ.). DOI: https://doi.org/10.18334/vinec.13.3.118259