Quyosh quritgichlari qishloq xo‘jaligi mahsulotlarini tabiiy sharoitda
samarali quritish uchun mo‘ljallangan ekologik va energiya tejamkor quritish
tizimlaridan biridir. Ushbu qurilmalar quyosh energiyasidan foydalangan holda,
mahsulotdagi namlikni optimallashtiradi va mahsulot sifatini saqlab qolishga
yordam beradi. Biroq quyosh quritgichlarining samaradorligi atrof-muhit harorati,
quyosh radiatsiyasi va havo oqimi kabi tashqi omillarga bog‘liq bo‘lib, ushbu
parametrlarni real vaqt rejimida boshqarish muhim hisoblanadi. An’anaviy PI
rostlagichlar bunday o‘zgaruvchan sharoitlarda yetarli darajada samarali bo‘la
olmaydi, chunki ularning rostlanish vaqti uzoq va ortiqcha chetlashishlar yuqori
bo‘ladi. Mazkur tadqiqotda quyosh quritgichlarining samaradorligini oshirish
uchun sun’iy neyron to‘rlarga asoslangan bashoratli boshqarish tizimi ishlab
chiqildi va uning ishlash natijalari PI rostlagich bilan solishtirildi. MATLAB R2014a
dasturining Simulink dasturiy paketida quritish jarayonining matematik modeli
ishlab chiqilib, turli boshqarish usullari bo‘yicha kompyuter simulyatsiyalari
amalga oshirildi. Tadqiqot natijalari shuni ko‘rsatdiki, bashoratli neyrorostlagich
bilan boshqarilgan tizimning rostlanish vaqti 160 sekundni tashkil etib, an’anaviy
PI rostlagich bilan boshqarilgan tizimga nisbatan 36 % tezroq natijaga erishildi
(PI rostlagich uchun rostlanish vaqti 250 sekund). Shuningdek, neyroboshqarish
tizimi haroratni ±1,2 °C aniqlikda barqaror ushlab turish imkonini berdi, bu esa
PI rostlagichga qaraganda sezilarli darajada yuqori aniqlikka ega ekanligini
ko‘rsatdi. Natijalar shuni tasdiqlaydiki, sun’iy neyron to‘rlarga asoslangan
boshqarish tizimi quyosh quritgichlarining barqaror ishlashini ta’minlash, energiya
sarfini optimallashtirish va mahsulot sifatini oshirishda muhim rol o‘ynaydi. Ushbu
usul qishloq xo‘jaligi mahsulotlarini quritish texnologiyalarini avtomatlashtirish va
ekologik jihatdan samarali qilish imkonini beradi. Olingan natijalar ushbu tizimni
sanoat miqyosida keng joriy etish istiqbollarini ko‘rsatadi.
Quyosh quritgichlari qishloq xo‘jaligi mahsulotlarini tabiiy sharoitda
samarali quritish uchun mo‘ljallangan ekologik va energiya tejamkor quritish
tizimlaridan biridir. Ushbu qurilmalar quyosh energiyasidan foydalangan holda,
mahsulotdagi namlikni optimallashtiradi va mahsulot sifatini saqlab qolishga
yordam beradi. Biroq quyosh quritgichlarining samaradorligi atrof-muhit harorati,
quyosh radiatsiyasi va havo oqimi kabi tashqi omillarga bog‘liq bo‘lib, ushbu
parametrlarni real vaqt rejimida boshqarish muhim hisoblanadi. An’anaviy PI
rostlagichlar bunday o‘zgaruvchan sharoitlarda yetarli darajada samarali bo‘la
olmaydi, chunki ularning rostlanish vaqti uzoq va ortiqcha chetlashishlar yuqori
bo‘ladi. Mazkur tadqiqotda quyosh quritgichlarining samaradorligini oshirish
uchun sun’iy neyron to‘rlarga asoslangan bashoratli boshqarish tizimi ishlab
chiqildi va uning ishlash natijalari PI rostlagich bilan solishtirildi. MATLAB R2014a
dasturining Simulink dasturiy paketida quritish jarayonining matematik modeli
ishlab chiqilib, turli boshqarish usullari bo‘yicha kompyuter simulyatsiyalari
amalga oshirildi. Tadqiqot natijalari shuni ko‘rsatdiki, bashoratli neyrorostlagich
bilan boshqarilgan tizimning rostlanish vaqti 160 sekundni tashkil etib, an’anaviy
PI rostlagich bilan boshqarilgan tizimga nisbatan 36 % tezroq natijaga erishildi
(PI rostlagich uchun rostlanish vaqti 250 sekund). Shuningdek, neyroboshqarish
tizimi haroratni ±1,2 °C aniqlikda barqaror ushlab turish imkonini berdi, bu esa
PI rostlagichga qaraganda sezilarli darajada yuqori aniqlikka ega ekanligini
ko‘rsatdi. Natijalar shuni tasdiqlaydiki, sun’iy neyron to‘rlarga asoslangan
boshqarish tizimi quyosh quritgichlarining barqaror ishlashini ta’minlash, energiya
sarfini optimallashtirish va mahsulot sifatini oshirishda muhim rol o‘ynaydi. Ushbu
usul qishloq xo‘jaligi mahsulotlarini quritish texnologiyalarini avtomatlashtirish va
ekologik jihatdan samarali qilish imkonini beradi. Olingan natijalar ushbu tizimni
sanoat miqyosida keng joriy etish istiqbollarini ko‘rsatadi.
Солнечные сушилки являются одними из экологически чистых
и энергосберегающих систем сушки, предназначенных для эффективного
обезвоживания сельскохозяйственной продукции в естественных
условиях. Эти установки, используя солнечную энергию, оптимизируют
влажность продукции и способствуют сохранению её качества. Однако
эффективность солнечных сушилок зависит от внешних факторов,
таких как температура окружающей среды, солнечная радиация и поток
воздуха, поэтому управление этими параметрами в режиме реального
времени имеет важное значение. Традиционные PI-регуляторы в условиях
изменяющейся среды оказываются недостаточно эффективными из-за
длительного времени их настройки и наличия значительных отклонений. В данном исследовании для повышения эффективности солнечных сушилок
разработана прогнозирующая система управления на основе искусственных
нейронных сетей, и её работа была сопоставлена с системой на основе
PI-регулятора. В программной среде MATLAB R2014a, с использованием
пакета Simulink, была построена математическая модель процесса
сушки и проведено компьютерное моделирование по различным методам
управления. Результаты исследования показали, что система, управляемая
прогнозирующим нейрорегулятором, достигла времени настройки в
160 секунд, что на 36 % быстрее по сравнению с системой на PI-регуляторе
(время настройки – 250 секунд). Кроме того, нейроуправляющая система
обеспечила стабилизацию температуры с точностью ±1,2 °C, что
свидетельствует о значительно более высокой точности по сравнению с
PI-регулятором. Полученные результаты подтверждают, что система
управления на основе искусственных нейронных сетей играет важную
роль в обеспечении стабильной работы солнечных сушилок, оптимизации
энергопотребления и повышении качества продукции. Данный подход
открывает возможности для автоматизации технологий сушки
сельскохозяйственной продукции и их экологически эффективного
применения. Полученные данные указывают на перспективы широкого
внедрения данной системы в промышленном масштабе.
Solar dryers are among the environmentally friendly and energy-efficient
drying systems designed for effective dehydration of agricultural products under
natural conditions. These systems, by utilizing solar energy, optimize the moisture
content of products and help preserve their quality. However, the efficiency of solar
dryers depends on external factors such as ambient temperature, solar radiation,
and airflow, making real-time control of these parameters essential. Traditional
PI controllers are not sufficiently effective under such variable conditions due to
their long tuning time and significant overshoot. In this study, a predictive control
system based on artificial neural networks (ANN) was developed to enhance the
performance of solar dryers and was compared with a PI-controller-based system.
A mathematical model of the drying process was created in the MATLAB R2014a
environment using the Simulink software package, and computer simulations
were carried out for various control methods. The results showed that the system
controlled by the predictive neuro-controller achieved a settling time of 160
seconds, which is 36% faster compared to the PI-controlled system (settling time
of 250 seconds). Additionally, the neural control system maintained temperature
stability with an accuracy of ±1.2°C, demonstrating significantly higher precision
compared to the PI-controller. The results confirm that a control system based on
artificial neural networks plays a crucial role in ensuring the stable operation of
solar dryers, optimizing energy consumption, and improving product quality. This
approach enables the automation of agricultural drying technologies and ensures
their environmentally sustainable implementation. The findings indicate promising
prospects for the large-scale industrial application of this system.
| № | Author name | position | Name of organisation |
|---|---|---|---|
| 1 | Rejabov S.A. | tауаnсh dоktоrаnt | Tоshkent kimуо-teхnоlоgiуа instituti |
| 2 | Artikov A.A. | texnika fanlari doktori, professor | Toshkent kimyo-texnologiya instituti |
| 3 | Usmonov B.S. | texnika fanlari doktori, professor, rektor | Toshkent kimyo texnologiya instituti |
| 4 | To'raqulov Z.S. | texnika fanlari bo‘yicha falsafa doktori (PhD), “Аvtоmаtlаshtirish vа rаqаmli bоshqаruv” kаfedrаsi katta o‘qituvchisi | Toshkent kimyo-texnologiya instituti |
| № | Name of reference |
|---|---|
| 1 | Abdurasulovich, R. S., Shukurillayevich, U. B., & Asqarovich, A. A. (2024). Oʻrik mevasini majburiy konveksiyali quyosh quritgichida quritish vaqtini hisoblash [Calculation of drying time of apricot fruit in forced convection solar dryer]. (In Uzbek). Ilm-fan va innovatsion rivojlanish – Nauka i innovatsionnoe razvitiye – Science and Innovation Development, 7 (2), 48–60 |
| 2 | Abdurasulovich, R. S., Shukurillayevich, U. B., Isroilovich, U. K., & Asqarovich, A. A. (2024). Noqat’iy mantiq asosida bilvosita quyosh quritgichlarining harorat dinamikasini bashorat qilish [Forecasting the temperature dynamics of indirect solar dryers using fuzzy logic]. (In Uzbek). Ilm-fan va innovatsion rivojlanish – Nauka i innovatsionnoe razvitiye – Science and Innovation Development, 7 (5), 8–18. |
| 3 | Abduvaxitovna, S. S., & Isroilovich, U. K. (2024). Dorivor o‘simliklarni gelioquritish qurilmasida quritish jarayonini matematik modellashtirish [Mathematical modeling of the drying process of medicinal plants in a solar dryer]. (In Uzbek). Ilm-fan va innovatsion rivojlanish – Nauka i innovatsionnoe razvitiye – Science and Innovation Development, 7 (4), Article 4. |
| 4 | Arslankaya, S. (2023). Comparison of performances of fuzzy logic and adaptive neuro-fuzzy inference system (ANFIS) for estimating employee labor loss. Journal of Engineering Research, 11 (4), 469–477. https://doi.org/10.1016/j.jer.2023.100107 |
| 5 | Artikov, A. A., & Masharipova, Z. A. (2013). Komp’yuternoe otobrazhenie ravnovesiya protsessa sushki po temperature produkta [Computer display of the drying process equilibrium by product temperature]. (In Russian). Khranenie i pererabotka sel’khozsyr’ya – Storage and Processing of Agricultural Raw Materials, 2, 18–21. |
| 6 | Artikov, A., Mamatov, S., Kadirov, U., Masharipova, Z., & Mirkomilov, A. (2022). Computer simulation of the freeze drying process of beets. AIP Conference Proceedings, 2762 (1). https://pubs. aip.org/aip/acp/article-abstract/2762/1/020015/2832573 |
| 7 | Bal, L. M., Satya, S., & Naik, S. N. (2010). Solar dryer with thermal energy storage systems for drying agricultural food products: A review. Renewable and Sustainable Energy Reviews, 14 (8), 2298–2314. https://doi.org/10.1016/j.rser.2010.04.014 |
| 8 | Banana Drying Kinetics | IntechOpen. (2025). https://www.intechopen.com/chapters/68925 |
| 9 | Chabane, F., Bensahal, D., Brima, A., & Moummi, N. (2019). Solar drying of drying agricultural product (Apricot). Mathematical Modelling of Engineering Problems, 6 (1), 92–98. https://doi. org/10.18280/mmep.060112 |
| 10 | Ghani, N. M. A., Othman, A., Hashim, A. A. A., & Nasir, A. N. K. (2023). Comparative analysis of PID and fuzzy logic controllers for position control in double-link robotic manipulators. Journal of Intelligent Systems and Control, 2 (4), 183–196. https://doi.org/10.56578/jisc020401 |
| 11 | Goel, V., Dwivedi, A., Singh Mehra, K., Kumar Pathak, S., Tyagi, V. V., Bhattacharyya, S., & Pandey, A. K. (2024). Solar drying systems for domestic/industrial purposes: A state-of-art review on topical progress and feasibility assessments. Solar Energy, 267, 112210. https://doi.org/10.1016/ j.solener.2023.112210 |
| 12 | Janjai, S., & Bala, B. K. (2012). Solar drying technology. Food Engineering Reviews, 4 (1), 16–54. https://doi.org/10.1007/s12393-011-9044-6 |
| 13 | Koua, K. B., Fassinou, W. F., Gbaha, P., & Toure, S. (2009). Mathematical modelling of the thin layer solar drying of banana, mango and cassava. Energy, 34 (10), 1594–1602. https://doi. org/10.1016/j.energy.2009.07.005 |
| 14 | Madhankumar, S., Viswanathan, K., Taipabu, M. I., & Wu, W. (2023). A review on the latest developments in solar dryer technologies for food drying process. Sustainable Energy Technologies and Assessments, 58, 103298. https://doi.org/10.1016/j.seta.2023.103298 |
| 15 | Martynenko, A. (2018). Intelligent control in drying. https://doi.org/10.1201/9780429443183 |
| 16 | Masharipova, Z. A., Artikov, A. A., & Rakhmatov, F. O. (2020). Maxsulotlarni quritish jarayonlarini komp’yuterda modellashtirish va optimal sharoitlarni xisoblash [Computer modeling of drying processes and calculation of optimal conditions]. (In Uzbek). 151 p. |
| 17 | Rejabov, S., Usmonov, B., Usmanov, K., & Artikov, A. (2024). Experimental comparison of open sun and indirect convection solar drying methods for apricots in Uzbekistan. The 3rd International Electronic Conference on Processes, 26. https://doi.org/10.3390/engproc2024067026 |
| 18 | Sidikov, I. Kh., Usmanov, K. I., Yakubova, N. S., & Kazakhbaev, S. A. (2020). Nechetkoye sinergeticheskoye upravleniye nelineynykh sistem [Fuzzy synergetic control of nonlinear systems]. (In Russian). https://doi.org/10.24412/2181-1431-2020-2-16-19 |
| 19 | Topal, M. E., Şahin, B., & Vela, S. (2024). Artificial neural network modeling techniques for drying kinetics of Citrus medica fruit during the freeze-drying process. Processes, 12 (7), Article 7. https://doi.org/10.3390/pr12071362 |
| 20 | Usmanov, K. I., Sultanova, Sh. A., & Rejabov, S. A. (2025). Application of artificial neural networks for predicting temperature in a solar dryer. Ilm-fan va innovatsion rivojlanish – Nauka i innovatsionnoe razvitiye – Science and Innovation Development, 8 (1), 8–20. |
| 21 | Yang, T., Zheng, X., Xiao, H., Shan, C., Yao, X., Li, Y., & Zhang, J. (2023). Drying temperature precision control system based on improved neural network PID controller and variable-temperature drying experiment of cantaloupe slices. Plants, 12 (12), Article 12. https://doi.org/10.3390/ plants12122257 |
| 22 | Yusupbekov, N. R., Adilov, F. T., & Aytbaev, J. A. (2024). Fuzzy models and optimization by distillation units in the Aspen HYSYS software environment. Chemical Technology, Control and Management, 5, 30–34. https://doi.org/10.59048/2181-1105.1625 |