Prediction of Peak Particle Velocity Caused by Blasting Using Deep Learning Method in Large-Scale Open-Pit Mines (Case Studies: Sungun Ahar and Golgohar Open-Pit Mines in Sirjan)

Mohammadi Sarqini, Davood; Ataei, Mohammad; Mikaeil, Reza; Esmaeilzadeh, Akbar

doi:10.22034/ijme.2025.2055780.2039

Prediction of Peak Particle Velocity Caused by Blasting Using Deep Learning Method in Large-Scale Open-Pit Mines (Case Studies: Sungun Ahar and Golgohar Open-Pit Mines in Sirjan)

Document Type : research - paper

Authors

Davood Mohammadi Sarqini ¹

mohammad Ataei ²

reza mikaeil ³

akbar Esmaeilzadeh ⁴

¹ Ph.D. Candidate, Faculty of Mining, Petroleum and Geophysics, Shahrood University of Technology, Iran

² Professor, Faculty of Mining, Petroleum and Geophysics, Shahrood University of Technology, Iran

³ Associate Professor, Faculty of Industries and Mining Technologies, Urmia University of Technology, Iran

⁴ Assistant Professor, Faculty of Industries and Mining Technologies, Urmia University of Technology, Iran

10.22034/ijme.2025.2055780.2039

Abstract

Mining is one of the most important economic driving sectors of any country, and its production rate is highly dependent on the quality of the blasting process, which is considered one of the most common exploitation methods. One of the main challenges during the blasting process is serious damage to facilities. Therefore, during the construction and operation of these facilities, consideration should be given to investigating and predicting the vibration consequences. For this purpose, by collecting data related to blasting in the two mines of Gol Gohar and Songun , after analyzing and describing them, the peak particle velocity has been predicted based on the distance and amount of explosives. To achieve this goal, considering the quantity and nature of the data, a deep learning method was used. In this study, an attempt was made to obtain acceptable results by searching for optimal values for hyperparameters through trial and error. The coefficient of determination(R2), mean absolute percentage error(MAPE), and root mean square error(RMSE) were considered as indices of model quality evaluation. For better judgment, the performance of the selected method was compared with the performance of three methods: support vector machine, stochastic gradient descent, and adaptive boosting. The R2, for the four above methods was 0.952, 0.809, 0.845, and 0.911, respectively. For the RMSE index, the values were: 2.670, 5.308, 4.773, and 3.631. The values of the MAPE index for the four above methods were: 2.003, 2.119, 2.786, and 1.887. According to the values of the indices, the deep learning method had the best performance due to its flexibility in architecture and better adaptation to the characteristics of the problem. It can be said that in relation to complex and uncertain problems, such as those in the mining field, deep learning-based methods suggests good capabilities.

Keywords

Vibration waves

Peak particle velocity

Blasting distance

Amount of explosives

Deep learning

Subjects

Mining exolpitation and underground spaces

Dindarloo, S.R., 2015. Prediction of blast-induced ground vibrations via genetic programming. International Journal of Mining Science and Technology 25(6): 1011–5.

## Ghasemi, E., Kalhori, H., Bagherpour, R., 2016. A new hybrid ANFIS–PSO model for prediction of peak particle velocity due to bench blasting. Engineering with Computers 32: 607–14.

## Hasanipanah, M., Golzar, S.B., Larki, I.A., Maryaki, M.Y., Ghahremanians, T., 2017. Estimation of blast-induced ground vibration through a soft computing framework. Engineering with Computers 33: 951–9.

## Asl, P.F., Monjezi, M., Hamidi, J.K., Armaghani, D.J., 2018. Optimization of flyrock and rock fragmentation in the Tajareh limestone mine using metaheuristics method of firefly algorithm. Engineering with Computers 34: 241–51.

## Nguyen, H., Bui, X.-N., Tran, Q.-H., Moayedi, H., 2019. Predicting blast-induced peak particle velocity using BGAMs, ANN and SVM: a case study at the Nui Beo open-pit coal mine in Vietnam. Environmental Earth Sciences 78(15): 479.

## Arthur, C.K., Temeng, V.A., Ziggah, Y.Y., 2020. Novel approach to predicting blast-induced ground vibration using Gaussian process regression. Engineering with Computers 36(1): 29–42.

## Bui, X.-N., Choi, Y., Atrushkevich, V., Nguyen, H., Tran, Q.-H., Long, N.Q., et al., 2020. Prediction of blast-induced ground vibration intensity in open-pit mines using unmanned aerial vehicle and a novel intelligence system. Natural Resources Research 29(2): 771–90.

## Fang, Q., Nguyen, H., Bui, X.-N., Nguyen-Thoi, T., 2020. Prediction of blast-induced ground vibration in open-pit mines using a new technique based on imperialist competitive algorithm and M5Rules. Natural Resources Research 29(2): 791–806.

## Yang, H., Nikafshan Rad, H., Hasanipanah, M., Bakhshandeh Amnieh, H., Nekouie, A., 2020. Prediction of vibration velocity generated in mine blasting using support vector regression improved by optimization algorithms. Natural Resources Research 29(2): 807–30.

## Azimi, Y., Khoshrou, S.H., Osanloo, M., 2019. Prediction of blast induced ground vibration (BIGV) of quarry mining using hybrid genetic algorithm optimized artificial neural network. Measurement 147: 106874.

## Nguyen, H., Bui, X.-N., Bui, H.-B., Mai, N.-L., 2020. A comparative study of artificial neural networks in predicting blast-induced air-blast overpressure at Deo Nai open-pit coal mine, Vietnam. Neural Computing and Applications 32(8): 3939–55.

## Zhang, W., Nian-Jie., Ren, J., Li, C., 2021. Peak particle velocity of vibration events in underground coal mine and their caused stress increment. Measurement 169: 108520, Doi: 10.1016/J.MEASUREMENT.2020.108520.

## Zhang, X., Nguyen, H., Choi, Y., Bui, X.-N., Zhou, J., 2021. Novel Extreme Learning Machine-Multi-Verse Optimization Model for Predicting Peak Particle Velocity Induced by Mine Blasting. Natural Resources Research, Doi: 10.1007/s11053-021-09960-z.

## Zeng, J., Roussis, P., Mohammed, A., Maraveas, C., Fatemi, S., Armaghani, D., et al., 2021. Prediction of Peak Particle Velocity Caused by Blasting through the Combinations of Boosted-CHAID and SVM Models with Various Kernels. Applied Sciences 11: 3705, Doi: 10.3390/APP11083705.

## Sonkar, R., Dhekne, P.Y., Londhe, N.D., 2022. Prediction of Peak Particle Velocity of Blast-induced Ground Vibrations using Boosted Regression Trees Authored. Journal of Mines, Metals and Fuels: 203–13.

## Chandrahas, N.S., Choudhary, B.S., Venkataramayya, M.S., Yewuhalashet, F., 2024. An inventive approach for simultaneous prediction of mean fragmentation size and peak particle velocity using futuristic datasets through improved techniques of genetic XG Boost algorithm. Mining, Metallurgy & Exploration 41(5): 2391–405.

## Yuan, H., Zou, Y., Li, H., Ji, S., Gu, Z., He, L., et al., 2025. Assessment of peak particle velocity of blast vibration using hybrid soft computing approaches. Journal of Computational Design and Engineering 12(2): 154–76.

##حسن، مومیوند., 1392. پیش بینی سرعت ذره ای حداکثر لرزش زمین ناشی از انفجار با استفاده تحلیل نتایج حاصل از شرایط متعدد ژئومکانیکی. همایش انجمن زمین شناسی مهندسی و محیط زیست ایران,.

##حسن، مومیوند., 1402. خردایش سنگ و کنترل پیامدهای ناشی از انفجار. 1, ارومیه: دانشگاه ارومیه ##