An IoT-Enabled Hybrid Neuro-Fuzzy Smart Cooling System for Predictive Industrial Cooling and Energy Optimization
Document Type : Original Research Article
Received: 02 March 2026
|
Revised: 25 March 2026
|
Accepted: 08 April 2026
|
Published: 29 June 2026
Authors
Noor Ul Amin
1,*
1
Taylor’s University, Subang Jaya, Malaysia
*
Author to whom correspondence should be addressed.
Abstract
The modern era of smart industries has increased heat generation and energy consumption tremendously, creating a huge demand for intelligent industrial cooling and energy optimization. But the existing coolers cannot perform adaptive prediction, intelligent monitoring and overheating prevention in dynamic industrial environment. To overcome these limitations, a Hybrid Neuro-Fuzzy Smart Cooling System (HNF-SCS) using IoT is introduced in this research. The proposed framework is a combination of Artificial Neural Networks (ANN), Fuzzy Logic Controller (FLC) and Proportional-Integral-Derivative (PID) based cooling control and sensor monitoring using IoT for intelligent thermal management. First, the industrial sensors gather real-time parameters like temperature, humidity, machine loading and power consumption. Future thermal conditions are predicted by the ANN model and overheating risk is identified by thermal analysis. The fuzzy logic controller calculates the needed cooling level based on the forecasted state and the PID controller controls the HVAC systems, fans and cooling pumps to keep the temperature stable without wasting too much power. Experimental results showed that the proposed HNF-SCS gave the maximum heat reduction rate of 98.85%, consumed 48.55 kWh and had small prediction errors. The proposed framework thus effectively enhanced the energy optimization, thermal stability, cooling efficiency and industrial safety in the smart industry.
Keywords:
Adaptive Cooling
,
Artificial Neural Network
,
Energy Optimization
,
Fuzzy Logic
,
Industrial Thermal Management
,
Internet of Things (IoT)
References
[1]
Sirisumrannukul, S., Intaraumnauy, T., & Piamvilai, N. (2024). Optimal control of cooling management system for energy conservation in smart home with ANNs-PSO data analytics microservice platform. Heliyon, 10(6), e26937.
https://doi.org/10.1016/j.heliyon.2024.e26937
[2]
Qureshi, M., Arbab, M. A., & Rehman, S. (2024). Deep learning-based forecasting of electricity consumption. Scientific Reports, 14, 6489.
https://doi.org/10.1038/s41598-024-56602-4
[3]
Chaganti, R., Rustam, F., Daghriri, T., de la Torre Díez, I., Vidal Mazón, J. L., Rodríguez, C. L., & Ashraf, I. (2022). Building heating and cooling load prediction using ensemble machine learning model. Sensors, 22(19), 7692.
https://doi.org/10.3390/s22197692
[4]
Njimbouom, S. N., Lee, K., Lee, H., & Kim, J. (2022). Predicting site energy usage intensity using machine learning models. Sensors, 23(1), 82.
https://doi.org/10.3390/s23010082
[5]
Luo, J., & Lee, J. (2024). Machine learning-assisted thermoelectric cooling for on-demand multi-hotspot thermal management. Journal of Applied Physics, 135(24), 244503.
https://doi.org/10.1063/5.0206287
[6]
Zhao, Y., Guo, Y., Diao, A., Zhang, J., & Peng, X. (2024). Thermodynamic analysis of diaphragm compressor in hydrogen refuelling stations by using fluid-structure interaction method. Applied Thermal Engineering, 242, 122394.
https://doi.org/10.1016/j.applthermaleng.2024.122394
[7]
Odufuwa, O. Y., Tartibu, L. K., Kusakana, K., Hohne, P. A., & Numbi, B. P. (2024). Application of artificial neural networks in predicting the performance of ice thermal energy storage systems. Journal of Energy Storage, 95, 112547.
https://doi.org/10.1016/j.est.2024.112547
[8]
Machacuay, J., Manrique-Silupu, J., & Ipanaqué, W. (2025). LSTM with shallow NNs for indoor temperature long-term predictions in refrigeration systems. Neural Computing and Applications, 37, 1067–1088.
https://doi.org/10.1007/s00521-024-10477-8
[9]
Çolak, A. B., Inanli, M., Aydin, D., et al. (2025). Development of a machine-learning-based performance prediction model for indirect regenerative evaporative cooling applications supported by experimental and numerical techniques. Journal of Thermal Analysis and Calorimetry, 150, 5271–5294.
https://doi.org/10.1007/s10973-025-14117-8
[10]
Zhu, Q., Liu, M., Liu, H., & Zhu, Y. (2022). Application of machine learning and its improvement technology in modeling of total energy consumption of air conditioning water system. Mathematical Biosciences and Engineering, 19(5), 4841–4855.
https://doi.org/10.3934/mbe.2022226
[11]
Abuhussain, M. A., Alotaibi, B. S., Aliero, M. S., Asif, M., Alshenaifi, M. A., & Dodo, Y. A. (2023). Adaptive HVAC system based on fuzzy controller approach. Applied Sciences, 13(20), 11354.
https://doi.org/10.3390/app132011354
[12]
Rajeswari Subramaniam, K., Cheng, C.-T., & Pang, T. Y. (2023). Fuzzy logic controlled simulation in regulating thermal comfort and indoor air quality using a vehicle heating, ventilation, and air-conditioning system. Sensors, 23(3), 1395.
https://doi.org/10.3390/s23031395
[13]
Liu, L., Xue, D., & Zhang, S. (2023). General type industrial temperature system control based on fuzzy fractional-order PID controller. Complex & Intelligent Systems, 9, 2585–2597.
https://doi.org/10.1007/s40747-021-00431-9
[14]
Huang, P. (2024). Fuzzy adaptive PID algorithm in temperature control system of lead patenting furnace. Advances in Civil Engineering, 2024, 4519537.
https://doi.org/10.1155/2024/4519537
[15]
Liu, C., Wang, Y., Zhang, M., Wang, P., Liu, S., Wu, W., & Sun, Y. (2023). The investigation of a fuzzy-internal mode PID-based temperature control system for solid state electric storage heaters. Journal of Computational Methods in Sciences and Engineering, 23(2).
https://doi.org/10.3233/JCM-226856
[16]
Boutahri, Y., & Tilioua, A. (2024). Machine learning-based predictive model for thermal comfort and energy optimization in smart buildings. Results in Engineering, 22, 102148.
https://doi.org/10.1016/j.rineng.2024.102148
[17]
Pham, D.-A., Han, S.-H., et al. (2024). Development of an adaptive fuzzy-neural controller for temperature control in a brick tunnel kiln. Electronics, 13(2), 342.
https://doi.org/10.3390/electronics13020342
[18]
Mharakurwa, E. T., & Gicheru, D. W. (2024). Transformer hot spot temperature estimation through adaptive neuro-fuzzy inference system approach. Heliyon, 10, e26338.
https://doi.org/10.1016/j.heliyon.2024.e26338
[19]
Cherian, S. K., Nanaji, K., Sarada, B. V., Rao, T. N., & Sharma, C. S. (2024). Sulfur confinement into highly porous banana peduncle-derived carbon for high-rate performance lithium-sulfur battery. Journal of Energy Storage, 89, 111803.
https://doi.org/10.1016/j.est.2024.111803
[20]
Shanmugam, S., & Sharmila, A. (2024). An intelligent adaptive neuro-fuzzy based control for multiport DC-AC converter with differential power processing converter for hybrid renewable power generation systems. Frontiers in Energy Research, 12,
https://doi.org/10.3389/fenrg.2024.1471265
[21]
Elboughdiri, N., Kriaa, K., & Bakare, M. S. et al. (2025). Intelligent demand-side energy management via optimized ANFIS–gene expression programming in hybrid renewable–grid systems. Scientific Reports, 15, 43065.
https://doi.org/10.1038/s41598-025-26988-w
[22]
Arzate-Rivas, O., Sámano-Ortega, V., Martínez-Nolasco, J., Santoyo-Mora, M., Martínez-Nolasco, C., & De León-Lomelí, R. (2024). IoT energy management system based on a wireless sensor/actuator network. Technologies, 12(9), 140.
https://doi.org/10.3390/technologies12090140
[23]
Quispe-Astorga, A., Coaquira-Castillo, R. J., Utrilla Mego, L. W., Herrera-Levano, J. C., Concha-Ramos, Y., Sacoto-Cabrera, E. J., & Moreno-Cardenas, E. (2025). Data-driven fault detection and diagnosis in cooling units using sensor-based machine learning classification. Sensors, 25(12), 3647.
https://doi.org/10.3390/s25123647
[24]
Yang, H., Zhu, Y., Chong, H. M. H., & Huang, R. (2026). Accurate and efficient design and optimization of thermoelectric cooler via machine learning technologies. Applied Thermal Engineering, 285, 129224.
https://doi.org/10.1016/j.applthermaleng.2025.129224
[25]
Boutahri, Y., & Tilioua, A. (2025). Reinforcement learning for HVAC control and energy efficiency in residential buildings with BOPTEST simulations and real-case validation. Discover Computing.
https://doi.org/10.1007/s10791-025-09544-y
[26]
Donmez, M., Tekin, M., & Karamangil, M. I. (2025). Artificial neural network predictions for temperature: Utilizing numerical analysis in immersion cooling systems using mineral oil and an engineered fluid for 32700 LiFePO4. International Journal of Thermal Sciences, 211, 109742.
https://doi.org/10.1016/j.ijthermalsci.2025.109742
[27]
Ekinci, S., Izci, D., Gider, V., et al. (2025). Efficient control strategy for electric furnace temperature regulation using quadratic interpolation optimization. Scientific Reports, 15, 154.
https://doi.org/10.1038/s41598-024-84085-w
[28]
Shrivastava, D., & Goswami, P. (2025). Internet of things driven hybrid neuro-fuzzy deep learning building energy management system for cost and schedule optimization. Frontiers in Artificial Intelligence, 8, 1544183.
https://doi.org/10.3389/frai.2025.1544183
[29]
Al Shahrani, A. M., Alomar, M. A., Alqahtani, K. N., Basingab, M. S., Sharma, B., & Rizwan, A. (2023). Machine learning-enabled smart industrial automation systems using Internet of Things. Sensors, 23(1), 324.
https://doi.org/10.3390/s23010324
[30]
Xu, J., Li, H., & Zhang,Q. (2024). Adaptive control for circulating cooling water system using deep reinforcement learning. PLOS ONE, 19(7), e0307767.
https://doi.org/10.1371/journal.pone.0307767
[31]
Ra, S. J., Kim, J. H., & Park, C. S. (2023). Real-time model predictive cooling control for an HVAC system in a factory building. Energy and Buildings, 285, 112860.
https://doi.org/10.1016/j.enbuild.2023.112860
[32]
Elakkiya, E., Antony Raj, S., Balakrishnan, A., Sanisetty, B., & Bandaru, R. B. (2025). Stacked hybrid model for load forecasting: Integrating transformers, ANN, and fuzzy logic. Scientific Reports, 15, 2025.
https://doi.org/10.1038/s41598-025-04210-1
[33]
Boutahri, Y., & Tilioua, A. (2024). Machine learning-based predictive model for thermal comfort and energy optimization in smart buildings. Results in Engineering, 22, 102148.
https://doi.org/10.1016/j.rineng.2024.102148
[34]
Random Forest -Wang, L., Gu, H. & Zhang, Q. (2025). Random Forest model for precise cooling load estimation in optimized and non-optimized form. Chemical Product and Process Modeling, 20(4), 523-553.
https://doi.org/10.1515/cppm-2024-0033
[35]
Boutahri, Y., & Tilioua, A. (2024). Machine learning-based predictive model for thermal comfort and energy optimization in smart buildings. Results in Engineering, 22, 102148.
https://doi.org/10.1016/j.rineng.2024.102148
[36]
Tang, P., Yuan, Z., Yu, Y., & Gao, B. (2026). Monotonicity-constrained physics-informed deep neural network for chiller energy consumption prediction: Extrapolation performance and constraint improvement. Energy and Buildings, 359, 117299.
https://doi.org/10.1016/j.enbuild.2026.117299
[37]
Liu, J., Fan, R., Li, Z., Harnpornchai, N., & Qian, J. (2026). Proactive cooling control algorithm for data centers based on LSTM-driven predictive thermal analysis. Applied System Innovation, 9(1), 21. https://doi.org/10.3390/asi9010021
https://doi.org/10.3390/asi9010021
[38]
Hajjaji, I., Ait Mansour, A., & Dahmouni, H. (2026). AI-driven energy optimization in university microgrid: A hybrid LSTM-RNN forecasting consumption patterns approach. Energy Reports, 15, 109023.
https://doi.org/10.1016/j.egyr.2025.109023
