The article presents an innovative approach to developing an intelligent control system
for managing temperature and water level in smart home systems. The proposed method integrates an
adaptive PID controller with fuzzy logic algorithms, enabling dynamic adjustment of the PID controller
coefficients in real time. The mathematical model of the system incorporates heat balance equations,
differential heat transfer relations, and nonlinear models of fluid loss. The adaptive control algorithms
developed within the study allow the system to effectively respond to changes in input data.
A comprehensive analysis of the membership functions is conducted, along with adaptive tuning
of the PID coefficients based on fuzzy logic principles. This approach significantly enhances control
accuracy and overall system efficiency. The study also identifies and addresses key limitations of
classical PID controllers-such as inertia, overshoot, oscillations, and high sensitivity to external
disturbances-by proposing robust algorithmic solutions.
The article presents an innovative approach to developing an intelligent control system
for managing temperature and water level in smart home systems. The proposed method integrates an
adaptive PID controller with fuzzy logic algorithms, enabling dynamic adjustment of the PID controller
coefficients in real time. The mathematical model of the system incorporates heat balance equations,
differential heat transfer relations, and nonlinear models of fluid loss. The adaptive control algorithms
developed within the study allow the system to effectively respond to changes in input data.
A comprehensive analysis of the membership functions is conducted, along with adaptive tuning
of the PID coefficients based on fuzzy logic principles. This approach significantly enhances control
accuracy and overall system efficiency. The study also identifies and addresses key limitations of
classical PID controllers-such as inertia, overshoot, oscillations, and high sensitivity to external
disturbances-by proposing robust algorithmic solutions.
| № | Author name | position | Name of organisation |
|---|---|---|---|
| 1 | Zaynidinov H.N. | DSc, professor | Tashkent university of information technologies named after Muhammad al-Khwarizmi |
| 2 | Hodjaeva .F. | PhD | Samarkand State University named after Sharof Rashidov |
| 3 | Singh D.. | Professor | Hankuk University of Foreign Studies (Global Campus) |
| № | Name of reference |
|---|---|
| 1 | 1. Ershov I.A. Ispol'zovanie effektivnykh metodov fil'tratsii signala dlya obrabotki dannykh s optovolokonnogo datchika temperatury [Elektronnyy resurs] // CyberLeninka. 2021. Rezhim dostupa: https://cyberleninka.ru/article/n/ispolzovanieeffektivnyh-metodov-filtratsii-signala-dlya-obrabotkidannyh-s-optovolokonnogo-datchika-temperatury 2. Kim J., Park S. Energy-efficient temperature control using extended Kalman filter in smart heating ELECTRICAL AND COMPUTING ENGINEERING 36 Technical science and innovation. №2/2025 systems // Journal of Energy Efficiency. 2018. Vol. 12. P. 145-158. DOI: https://doi.org/10.1007/s12053-018-9573-2 3. Nguyen T., Zhao X., Chen J. Multi-dimensional signal processing for smart heating systems using EKF and adaptive filters // International Journal of Control. 2020. Vol. 93, No. 3. P. 567-580. DOI:https://doi.org/10.1080/00207179.2019.1655478 |
| 2 | 3. Nguyen T., Zhao X., Chen J. Multi-dimensional signal processing for smart heating systems using EKF and adaptive filters // International Journal of Control. 2020. Vol. 93, No. 3. P. 567-580. DOI:https://doi.org/10.1080/00207179.2019.1655478 4. Chen H., Wang L. Accuracy comparison of EKF and RLS in signal filtering for smart home applications // IEEE Transactions on Smart Systems. 2021. Vol. 9, No. 4. P. 534-542. DOI: https://doi.org/10.1109/TSS.2021.3097632 5. Tan P., Li H., Zhao X. Hybrid EKF-RLS filtering for balancing accuracy and adaptability in smart home systems // Smart Infrastructure Journal. 2022. Vol. 11. P. 98-115. DOI: https://doi.org/10.1109/SIJ.2022.3112234 6. Akhmedov R. Problems of energy resource management in Uzbekistan and ways to solve them // Economics and Management. 2020. No. 8. P. 45-52. |
| 3 | 7. Zaynidinov H.N., Hodjaeva D.F. Approximation by splines and fuzzy logic algorithm in water filling control in a smart home system // International Conference on Adaptive Learning Technologies. 2024. Vol. 5. P. 157-160. 8. Zaynidinov H.N., Hodjaeva D.F. Integration of the spline function and fuzzy logic algorithm in the management of clean water filling in a smart home system // Innovative: International Multidisciplinary Journal of Applied Technology. 2023. Vol. 2, No. 5. P. 181-186. 9. Hodjaeva D.F. Technical and Software Features of a Smart Plug // Artificial Intelligence and Information Technologies. London: CDC Press, 2024. Vol. 1. P. 551- 557. ISBN: 9781032700502 |
| 4 | 10. Zaynidinov H., Xuramov L., Khodjaeva D. Intelligent algorithms of digital processing of biomedical images in wavelet methods // Artificial Intelligence, Blockchain, Computing and Security: Book Chapter. 2023. Vol. 2. P. 648-653. 11. Nazarov F.M., Yarmatov S. Optimization of Prediction Results Based on Ensemble Methods of Machine Learning // 2023 International Russian Smart Industry Conference (SmartIndustryCon), Sochi, Russian Federation. 2023. P. 181-185. DOI: 10.1109/SmartIndustryCon57312.2023.10110726 12. Makhmadiyarovich N.F., Sherzodjon Y. Methods of increasing data reliability based on distributed and parallel technologies based on blockchain // Artificial Intelligence, Blockchain, Computing and Security. 2023. Vol. 2. P. 637–642. ISBN: 9781032684994 |
| 5 | 13. Nazarov F.M., Yarmatov S., Xamidov M. Machine Learning Price Prediction on Green Building Prices // 2024 International Russian Smart Industry Conference (SmartIndustryCon), Sochi, Russian Federation. 2024. P. 906-911. DOI:10.1109/SmartIndustryCon61328.2024.10515790 14. Nazarov F.M., Xamidov M.M. Eye State Classification Method for Detecting Physiological Deviations in Drivers Based on CNN Algorithm // 2024 International Russian Automation Conference (RusAutoCon). IEEE. 2024. P. 802-807. 15. Makhmudov F., Turimov D., Xamidov M., Nazarov F., Cho Y.-I. Real-Time Fatigue Detection Algorithms Using Machine Learning for Yawning and Eye State // Sensors. 2024. Vol. 24, No. 23. Article 7810. DOI: https://doi.org/10.3390/s24237810 |