RUDALI FOYDALI QAZILMALARNI QAZIB OLISH JARAYONIDA YO‘QOTISHLARNI KAMAYTIRISHDA SUN’IY INTELLEKT TEXNOLOGIYALARIDAN FOYDALANISH

Authors

  • Serjanova Feriuza Iklasjan qizi Author Author

Keywords:

Keywords: sun’iy intellekt; ruda yo‘qotilishi; suyulish; mashinaviy o‘qitish; raqamli egizak; rudani saralash; burg‘ilash va portlatish; konchilikni optimallashtirish.

Abstract

Ruda yo‘qotilishi va rejasiz suyulishni kamaytirish yer osti hamda ochiq usuldagi konchilikda muhim muammolardan biridir, chunki loyihaviy va amaldagi qazib olish chegaralari o‘rtasidagi tafovutlar ajratib olinadigan metall miqdori, boyitish fabrikasiga beriladigan ruda sifati, ekspluatatsion xarajatlar va ishlab chiqarish prognozlarining ishonchliligiga bevosita ta’sir ko‘rsatadi. Ushbu tadqiqot geotexnik va geologik ma’lumotlar, burg‘ilash-portlatish parametrlari, bo‘shliq yoki sirtni skanerlash, mashina ko‘rishi asosida ruda/jinsni tasniflash hamda raqamli egizakdan qayta aloqa ma’lumotlarini birlashtiruvchi ruda yo‘qotishlarini nazorat qilishning integratsiyalashgan sun’iy intellekt (SI) tizimini ishlab chiqadi. Metodik yangilik shundan iboratki, yopiq siklli arxitekturada mashinaviy o‘qitish modellari qazib olish birligi darajasida suyulish va ruda yo‘qotilishi xavfini prognoz qiladi, optimallashtirish qatlami esa ishlab chiqarish va barqarorlik cheklovlari doirasida qazib olish chegaralari, portlatish parametrlari, selektiv yuklash va yo‘naltirish qarorlarini moslashtiradi. Ushbu metodik tadqiqot uchun muayyan konning maxfiy ma’lumotlari mavjud bo‘lmagani sababli, xalqaro adabiyotlarda keltirilgan diapazonlar asosida 240 ta ishlab chiqarish birligidan iborat shaffof simulyatsion tekshiruv to‘plami yaratildi. Oddiy chiziqli regressiya, tasodifiy o‘rmon, gradient boosting va extra trees modellari ajratilgan test to‘plamida taqqoslandi. Suyulishni prognoz qilishda gradient boosting R² = 0,822 natijani, ruda yo‘qotilishini prognoz qilishda esa extra trees R² = 0,838 natijani ko‘rsatdi. Yopiq siklli boshqaruvning illustrativ ssenariysida o‘rtacha suyulish 11,04% dan 8,14% gacha, o‘rtacha ruda yo‘qotilishi esa 7,40% dan 5,51% gacha kamaydi; bu mos ravishda 26,2% va 25,6% nisbiy qisqarishga teng. Simulyatsion qazib olish koeffitsiyenti 92,60% dan 94,49% gacha oshdi, ruda sifati indeksi esa 4,76% ga yaxshilandi. Natijalar shuni ko‘rsatadiki, eng katta amaliy samara bitta SI algoritmidan emas, balki prognozlash, sensorli kuzatuv, optimallashtirish va reja-amal natijalarini solishtirishni yagona qaror qabul qilish sikliga birlashtirishdan olinadi. Taklif etilgan yondashuv mahalliy ma’lumotlar sifati, geotexnik cheklovlar, model driftlari va inson nazorati aniq boshqarilgan taqdirda, muayyan kon uchun pilot joriy etishning metodik asosi bo‘lishi mumkin.

References

1.Jung, D., & Choi, Y. (2021). Systematic review of machine learning applications in mining: Exploration, exploitation, and reclamation. Minerals, 11(2), 148. https://doi.org/10.3390/min11020148

2.Azhari, F., Sennersten, C. C., Lindley, C. A., & Sellers, E. (2023). Deep learning implementations in mining applications: A compact critical review. Artificial Intelligence Review, 56, 14367-14402. https://doi.org/10.1007/s10462-023-10500-9

3.Nobahar, P., Xu, C., Dowd, P., & Shirani Faradonbeh, R. (2024). Exploring digital twin systems in mining operations: A review. Green and Smart Mining Engineering, 1(4), 474-492. https://doi.org/10.1016/j.gsme.2024.09.003

4.Jang, H., Topal, E., & Kawamura, Y. (2015). Decision support system of unplanned dilution and ore-loss in underground stoping operations using a neuro-fuzzy system. Applied Soft Computing, 32, 1-12. https://doi.org/10.1016/j.asoc.2015.03.043

5.Zhao, X., & Niu, J. (2020). Method of predicting ore dilution based on a neural network and its application. Sustainability, 12(4), 1550. https://doi.org/10.3390/su12041550

6.Erdogan Erten, G., Bozkurt Keser, S., & Yavuz, M. (2021). Grid search optimised artificial neural network for open stope stability prediction. International Journal of Mining, Reclamation and Environment, 35(8), 600-617. https://doi.org/10.1080/17480930.2021.1899404

7.Abd Elwahab, A., Topal, E., & Jang, H. D. (2023). Review of machine learning application in mine blasting. Arabian Journal of Geosciences, 16, 133. https://doi.org/10.1007/s12517-023-11237-z

8.Chimunhu, P., Shirani Faradonbeh, R., Topal, E., Asad, M. W. A., & Ajak, A. D. (2024). Development of novel hybrid intelligent predictive models for dilution prediction in underground sub-level mining. Mining, Metallurgy & Exploration, 41, 2079-2098. https://doi.org/10.1007/s42461-024-01029-8

9.Chimunhu, P., Shirani Faradonbeh, R., Topal, E., Asad, M. W. A., & Ajak, A. D. (2025). Dilution prediction in underground open stope mining using gene expression programming and backpropagation artificial neural network algorithms. Mining Technology, 134(2), 105-120. https://doi.org/10.1177/25726668251348707

10.Mariz, J. L. V., Ferraz, T. S. G., Lima, M. P., Silva, R. M. A., & Jang, H. (2025). Predicting dilution in underground mines with stacking artificial intelligence models and genetic algorithms. Applied Sciences, 15(11), 5996. https://doi.org/10.3390/app15115996

11.Peukert, D., Xu, C., & Dowd, P. (2022). A review of sensor-based sorting in mineral processing: The potential benefits of sensor fusion. Minerals, 12(11), 1364. https://doi.org/10.3390/min12111364

12.Robben, C., & Wotruba, H. (2019). Sensor-based ore sorting technology in mining-Past, present and future. Minerals, 9(9), 523. https://doi.org/10.3390/min9090523

13.Shatwell, D. G., Murray, V., & Barton, A. (2023). Real-time ore sorting using color and texture analysis. International Journal of Mining Science and Technology, 33(6), 659-674. https://doi.org/10.1016/j.ijmst.2023.03.004

14.Noriega, R., Pourrahimian, Y., & Askari-Nasab, H. (2025). Deep reinforcement learning based real-time open-pit mining truck dispatching system. Computers & Operations Research, 173, 106815. https://doi.org/10.1016/j.cor.2024.106815

15.Ozyurt, M. C. (2026). Prediction of rock fragmentation by blasting using symbolic regression and explainable artificial intelligence. Applied Sciences, 16(15), 7673. https://doi.org/10.3390/app16157673

Downloads

Published

2026-09-30