Multi-Objective Optimized Machine Learning for Early Fault Detection in Water-Cooled Chillers
DOI:
https://doi.org/10.31272/jeasd.3917Keywords:
EWMA Control Chart, Fault Detection and Diagnosis, M5P Model Tree, Multi-Objective Optimization, NSGA-IIIAbstract
In large office buildings and commercial complexes, HVAC systems account for nearly two-thirds of total electricity consumption. However, early fault detection and diagnosis (FDD) in water-cooled chillers remains challenging because faults usually develop slowly, produce weak initial signatures, and exhibit strongly nonlinear thermodynamic behavior. Moreover, overlapping operational characteristics between faults make accurate diagnosis under mild and moderate conditions difficult. Previous studies using the ASHRAE RP-1043 dataset reported limited diagnostic performance for incipient faults, particularly refrigerant leakage and condenser fouling. To address these gaps, this study proposes a hybrid optimization-based FDD framework for early fault diagnosis in water-cooled chillers, integrating the Non-Dominated Sorting Genetic Algorithm III with Local Search (NSGA-III-LS) and the M5 Prime regression model for hyperparameter tuning and nonlinear operational modeling. The proposed framework offers a balanced trade-off between fault sensitivity, residual stability, and diagnostic accuracy. Validation results demonstrate high detection rates of 62.5-95.83% for mild faults and nearly 100% for severe faults, outperforming conventional methods, especially during incipient fault stages. The proposed method also supports earlier detection of abnormal thermal behavior, contributing to energy savings of approximately 15-30%, extended equipment lifespan, and more effective predictive maintenance planning.
References
P. M. Cuce and E. Cuce, “Role of HVAC in Building Energy Consumption: A Critical Review,” Journal of Thermal Analysis and Calorimetry, vol. 151, pp. 3059–3080, Feb. 2026. doi: https://doi.org/10.1007/s10973-026-15322-9.
Z. Wang et al., "Examining the impact of common faults on chiller performance through experimental investigation and parameter sensitivity analysis", Energy Build., vol. 317, p. 114389, Aug. 2024, doi: https://doi.org/10.1016/j.enbuild.2024.114389.
Z. Wang, J. Guo, S. Zhou, and P. Xia, "Performance Evaluation of Chiller Fault Detection and Diagnosis Using Only Field-Installed Sensors", Processes, vol. 11, no. 12, p. 3299, Nov. 2023, doi: https://doi.org/10.3390/pr11123299.
A. Gharbi, M. Ayari, N. Albalawi, Y. E. Touati, and Z. Klai, "Intelligent HVAC Control: Comparative Simulation of Reinforcement Learning and PID Strategies for Energy Efficiency and Comfort Optimization", Mathematics, vol. 13, no. 14, p. 2311, Jul. 2025, doi: https://doi.org/10.3390/math13142311.
J. Bi et al., "AI in HVAC fault detection and diagnosis: A systematic review", Energy Rev., vol. 3, no. 2, p. 100071, Jun. 2024, doi: https://doi.org/10.1016/j.enrev.2024.100071.
A. Rafati, H. R. Shaker, and S. Ghahghahzadeh, "Fault Detection and Efficiency Assessment for HVAC Systems Using Non-Intrusive Load Monitoring: A Review", Energies, vol. 15, no. 1, p. 341, Jan. 2022, doi: https://doi.org/10.3390/en15010341.
I. Matetić, I. Štajduhar, I. Wolf, and S. Ljubic, "A Review of Data-Driven Approaches and Techniques for Fault Detection and Diagnosis in HVAC Systems", Sensors, vol. 23, no. 1, p. 1, Dec. 2022, doi: https://doi.org/10.3390/s23010001.
H. Wang, D. Mai, Q. Li, and Z. Ding, "Evaluating Machine Learning Models for HVAC Demand Response: The Impact of Prediction Accuracy on Model Predictive Control Performance", Buildings, vol. 14, no. 7, p. 2212, Jul. 2024, doi: https://doi.org/10.3390/buildings14072212
Z. Soltani, K. K. Sørensen, J. Leth, and J. D. Bendtsen, "Fault detection and diagnosis in refrigeration systems using machine learning algorithms", Int. J. Refrig., vol. 144, pp. 34–45, Dec. 2022, doi: https://doi.org/10.1016/j.ijrefrig.2022.08.008.
P. Movahed, S. Taheri, and A. Razban, "A bi-level data-driven framework for fault-detection and diagnosis of HVAC systems", Appl. Energy, vol. 339, p. 120948, Jun. 2023, doi: https://doi.org/10.1016/j.apenergy.2023.120948.
I. D. L. Á. Fallas Calderón, M. K. Heenkenda, T. S. Sahota, and L. S. Serrano, "Canola Yield Estimation Using Remotely Sensed Images and M5P Model Tree Algorithm", Remote Sens., vol. 17, no. 13, p. 2127, Jun. 2025, doi: https://doi.org/10.3390/rs17132127.
A. Behnood and D. Daneshvar, "A machine learning study of the dynamic modulus of asphalt concretes: An application of M5P model tree algorithm", Constr. Build. Mater., vol. 262, p. 120544, Nov. 2020, doi: https://doi.org/10.1016/j.conbuildmat.2020.120544
H. U. Ahmed, A. S. Mohammed, and A. A. Mohammed, "Proposing several model techniques including ANN and M5P-tree to predict the compressive strength of geopolymer concretes incorporated with nano-silica", Environ. Sci. Pollut. Res., vol. 29, no. 47, pp. 71232–71256, Oct. 2022, doi: https://doi.org/10.1007/s11356-022-20863-1.
P. Jimeno-Sáez, R. Martínez-España, J. Casalí, J. Pérez-Sánchez, and J. Senent-Aparicio, "A comparison of performance of SWAT and machine learning models for predicting sediment load in a forested Basin, Northern Spain", CATENA, vol. 212, p. 105953, May 2022, doi: https://doi.org/10.1016/j.catena.2021.105953.
F. Hutter, L. Kotthoff, and J. Vanschoren, Automated Machine Learning. Cham: Springer International Publishing, 2019. doi: https://doi.org/10.1007/978-3-030-05318-5.
M. Kaveh and M. S. Mesgari, "Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review", Neural Process. Lett., vol. 55, no. 4, pp. 4519–4622, Aug. 2023, doi: https://doi.org/10.1007/s11063-022-11055-6.
A. Gogna and A. Tayal, "Metaheuristics: review and application", J. Exp. Theor. Artif. Intell., vol. 25, no. 4, pp. 503–526, Dec. 2013, doi: https://doi.org/10.1080/0952813X.2013.782347.
A. K. Srivastava et al., "A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature Selection", Energies, vol. 16, no. 2, p. 867, Jan. 2023, doi: https://doi.org/10.3390/en16020867.
Y. Xia, J. Zhao, Q. Ding, and A. Jiang, "Incipient Chiller Fault Diagnosis Using an Optimized Least Squares Support Vector Machine with Gravitational Search Algorithm", Front. Energy Res., vol. 9, p. 755649, Nov. 2021, doi: https://doi.org/10.3389/fenrg.2021.755649.
Y. Liu, T. Liang, M. Zhang, N. Jing, Y. Xia, and Q. Ding, "Fault Diagnosis of Centrifugal Chiller Based on Extreme Gradient Boosting", Buildings, vol. 14, no. 6, p. 1835, Jun. 2024, doi: https://doi.org/10.3390/buildings14061835.
M. Li, H. Tao, M. Liu, and T. He, "Study on enhanced fault diagnosis of chiller units in HVAC systems under the imbalanced data environment using GA-Optimized LightGBM", Energy Build., vol. 330, p. 115360, 2025. doi: https://doi.org/10.1016/j.enbuild.2025.115360
T. Ghosh and K. Martinsen, "Generalized approach for multi-response machining process optimization using machine learning and evolutionary algorithms", Eng. Sci. Technol. Int. J., vol. 23, no. 3, pp. 650–663, Jun. 2020, doi: https://doi.org/10.1016/j.jestch.2019.09.003.
F. Mostafazadeh, S. J. Eirdmousa, and M. Tavakolan, "Energy, economic and comfort optimization of building retrofits considering climate change: A simulation-based NSGA-III approach", Energy Build., vol. 280, p. 112721, Feb. 2023, doi: https://doi.org/10.1016/j.enbuild.2022.112721.
L. Gao, D. Li, and N. Liang, "Genetic algorithm-aided ensemble model for sensor fault detection and diagnosis of air-cooled chiller system", Build. Environ., vol. 233, p. 110089, Apr. 2023, doi: https://doi.org/10.1016/j.buildenv.2023.110089.
L. Ma and D. Zou, "An Improved NSGA‐III With Hybrid Crossover Operator for Multi‐Objective Optimization of Complex Combined Cooling, Heating, and Power Systems", Energy Sci. Eng., vol. 13, no. 4, pp. 1509–1543, Apr. 2025, doi: https://doi.org/10.1002/ese3.2039.
K. Deb and H. Jain, "An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point-Based Nondominated Sorting Approach, Part I: Solving Problems with Box Constraints", IEEE Trans. Evol. Comput., vol. 18, no. 4, pp. 577–601, Aug. 2014, doi: https://doi.org/10.1109/TEVC.2013.2281535.
J. R. Quinlan, "Combining instance-based and model-based learning", presented at the Proceedings of the tenth international conference on machine learning, 1993, pp. 236–243. https://dl.acm.org/doi/10.5555/3091529.3091560
Y. Wang and I. H. Witten, "Inducing model trees for continuous classes", presented at the Proceedings of the ninth European conference on machine learning, vol. 9, no.1, pp. 128–137. 1997. Wang-Witten-Induct.pdf
Q. Gu, Q. Xu, and X. Li, "An improved NSGA-III algorithm based on distance dominance relation for many-objective optimization", Expert Syst. Appl., vol. 207, p. 117738, Nov. 2022, doi: https://doi.org/10.1016/j.eswa.2022.117738.
Z.-M. Gu and G.-G. Wang, "Improving NSGA-III algorithms with information feedback models for large-scale many-objective optimization", Future Gener. Comput. Syst., vol. 107, pp. 49–69, Jun. 2020, doi: https://doi.org/10.1016/j.future.2020.01.048.
M. Hazbei, N. Rafati, N. Kharma, and U. Eicker, "Optimizing architectural multi-dimensional forms; a hybrid approach integrating approximate evolutionary search, clustering and local optimization", Energy Build., vol. 318, p. 114460, Sep. 2024, doi: https://doi.org/10.1016/j.enbuild.2024.114460.
P. Sihag, S. Mohsenzadeh Karimi, and A. Angelaki, "Random Forest, M5P and regression analysis to estimate the field unsaturated hydraulic conductivity", Appl. Water Sci., vol. 9, no. 5, p. 129, Jul. 2019, doi: https://doi.org/10.1007/s13201-019-1007-8.
M. C. Comstock, J. E. Braun, and R. Bernhard, Development of analysis tools for the evaluation of fault detection and diagnostics in chillers. Master Thesis, 45870. Purdue University,ME, DEC, 1999. https://purdue.primo.exlibrisgroup.com/discovery/fulldisplay/alma99130475630001081/01PURDUE_PUWL:PURDUE
Q. Zhou, S. Wang, and F. Xiao, "A Novel Strategy for the Fault Detection and Diagnosis of Centrifugal Chiller Systems", HVACR Res., vol. 15, no. 1, pp. 57–75, Jan. 2009, doi: https://doi.org/10.1080/10789669.2009.10390825.
D. A. T. Tran, Y. Chen, M. Q. Chau, and B. Ning, "A robust online fault detection and diagnosis strategy of centrifugal chiller systems for building energy efficiency", Energy Build., vol. 108, pp. 441–453, Dec. 2015, doi: https://doi.org/10.1016/j.enbuild.2015.09.044.
X. Zhao, M. Yang, and H. Li, "A virtual condenser fouling sensor for chillers", Energy Build., vol. 52, pp. 68–76, Sep. 2012, doi: https://doi.org/10.1016/j.enbuild.2012.05.018.
V. Bolón-Canedo and B. Remeseiro, "Feature selection in image analysis: a survey", Artif. Intell. Rev., vol. 53, no. 4, pp. 2905–2931, Apr. 2020, doi: https://doi.org/10.1007/s10462-019-09750-3.
H. Kabir and N. Garg, "Machine learning enabled orthogonal camera goniometry for accurate and robust contact angle measurements", Sci. Rep., vol. 13, no. 1, p. 1497, Jan. 2023, doi: https://doi.org/10.1038/s41598-023-28763-1.
Y. Bezyan, F. Nasiri, and M. Nik-Bakht, "Feature Selection and Fault Detection Under Dynamic Conditions of Chiller Systems", Electronics, vol. 15, no. 1, p. 208, Jan. 2026, doi: https://doi.org/10.3390/electronics15010208.
D. A. T. Tran, Y. Chen, H. L. Ao, and H. N. T. Cam, "An enhanced chiller FDD strategy based on the combination of the LSSVR-DE model and EWMA control charts", Int. J. Refrig., vol. 72, pp. 81–96, Dec. 2016, doi: https://doi.org/10.1016/j.ijrefrig.2016.07.024.
Y. Zhao, S. Wang, and F. Xiao, "A statistical fault detection and diagnosis method for centrifugal chillers based on exponentially-weighted moving average control charts and support vector regression", Appl. Therm. Eng., vol. 51, no. 1–2, pp. 560–572, Mar. 2013, doi: https://doi.org/10.1016/j.applthermaleng.2012.09.030
J. Liu et al., "A statistical-based online cross-system fault detection method for building chillers", Build. Simul., vol. 15, no. 8, pp. 1527–1543, Aug. 2022, doi:https://doi.org/10.1007/s12273-021-0877-5
A. Moayedikia, S. Fin, and U. K. Wiil, "Multi-objective optimization formulation for Alzheimer’s disease trial patient selection", J. Biomed. Inform., vol. 172, p. 104955, Dec. 2025, doi: https://doi.org/10.1016/j.jbi.2025.104955.
H.-L. Shieh and C.-C. Kuo, "A reduced data set method for support vector regression", Expert Syst. Appl., vol. 37, no. 12, pp. 7781–7787, Dec. 2010, doi: https://doi.org/10.1016/j.eswa.2010.04.062.
C. Li, Y. Shao, D. Zhao, Y. Guo, and X. Hua, "Feature selection for high‐dimensional regression via sparse LSSVR based on Lp‐norm", Int. J. Intell. Syst., vol. 36, no. 2, pp. 1108–1130, Feb. 2021, doi: https://doi.org/10.1002/int.22334.
M. F. Ahmad, N. A. M. Isa, W. H. Lim, and K. M. Ang, 'Differential evolution: A recent review based on state-of-the-art works", Alex. Eng. J., vol. 61, no. 5, pp. 3831–3872, May 2022, doi: https://doi.org/10.1016/j.aej.2021.09.013.
Downloads
Key Dates
Received
Revised
Accepted
Published Online First
Issue
Section
License
