Prediction of blast-induced flyrock by using neural-imperialist competitive method (Case Study: Sungun Copper Mine).

Saved in:

Bibliographic Details
Title:	Prediction of blast-induced flyrock by using neural-imperialist competitive method (Case Study: Sungun Copper Mine).
Alternate Title:	Predviđanje udaljenosti odbacivanja minirane stijenske mase korištenjem algoritma imperijalističke konkurencije (studija slučaja: rudnik bakra Sungun).
Authors:	Hanifehnia, Jalil¹, Esmaeilzadeh, Akbar² a.esmailzadeh@uut.ac.ir, Mikaeil, Reza², Atalou, Solat¹
Source:	Rudarsko-Geološko-Naftni Zbornik. 2024, Vol. 39 Issue 5, p109-120. 12p.
Subject Terms:	Artificial neural networks, Imperialist competitive algorithm, Copper mining, Artificial intelligence, *Sensitivity analysis
Abstract (English):	This research focuses on conducting studies that predict the distance of blast-induced flyrock, which is an undesirable environmental phenomenon in open-pit mines. While there are experimental methods available for predicting blastinduced flyrock, the complex process of assessing the distance of flyrock has reduced the efficiency of these approaches. This study employs artificial intelligence methods and statistical techniques to forecast the flyrock distance in the Sungun copper mine. Thus, an Artificial Neural Network (ANN-MLP) and a new hybrid model of Artificial Neural Network (ANN) optimized by the Imperialist Competitive Algorithm (ICA), known as (ICA-ANN), are used to predict the flyrock distance, considering crucial parameters such as the number of holes, hole spacing, burden, total charge, specific drilling, charge per hole and specific charge. The results showed that the Artificial Neural Network, with RMSE, MAE, and R² error values of 9.31 m, 7.10 m, and 0.81, respectively, was able to predict the flyrock distance well compared to the measured data in the test phase. However, the implementation of the imperialist competitive algorithm optimizer in the neural network enhanced the prediction of the flyrock distance, yielding RMSE, MAE, and R² values of 5.66 m, 4.60 m, and 0.89, respectively. Finally, by performing sensitivity analysis on the input parameters of the flyrock distance, it was determined that the amount of explosive consumption and the number of holes have the greatest impact on the blastinduced flyrock distance. [ABSTRACT FROM AUTHOR]
Abstract (Croatian):	U ovome istraživanju provedena je studija koja procjenjuje udaljenosti odbacivanja minirane stijenske mase, a to je nepoželjna pojava u okolišu površinskih kopova. Iako postoje dostupne eksperimentalne metode za predviđanje udaljenosti odbacivanja minirane stijenske mase, njihova je učinkovitost smanjena zbog složenosti procesa procjene. Ova studija koristi se metodama umjetne inteligencije i statističke tehnike za predviđanje udaljenosti odbacivanja minirane stijenske mase u rudniku bakra Sungun. Stoga se umjetna neuronska mreža (ANN-MLP) i novi hibridni model umjetne neuronske mreže (ANN) optimiziran algoritmom imperijalističke konkurencije (ICA), poznatim kao (ICA-ANN), koriste za predviđanje udaljenosti odbacivanja minirane stijenske mase uzimajući u obzir ključne parametre kao što su broj bušotina, razmak između bušotina, izbojnica, ukupna količina eksploziva, specifičnosti bušenja, eksplozivno punjenje po bušotini i specifična potrošnja eksploziva. Rezultati su pokazali da je umjetna neuronska mreža, s RMSE od 9,31 m, MAE od 7,10 m i R² od 0,81, bila u stanju dobro predvidjeti duljinu odbacivanja u usporedbi s izmjerenim podatcima u ispitnoj fazi. Međutim, implementacija algoritma imperijalističke konkurencije u neuronskoj mreži poboljšala je predviđanje udaljenosti odbacivanja, uz vrijednosti RMSE od 5,66 m, MAE od 4,60 m i R ² od 0,89. Analizom osjetljivosti na ulazne parametre duljine odbacivanja utvrđeno je da količina utroška eksploziva i broj bušotina imaju najveći utjecaj na udaljenost odbacivanja minirane stijenske mase. [ABSTRACT FROM AUTHOR]
Database:	Energy & Power Source

Description
Abstract:	This research focuses on conducting studies that predict the distance of blast-induced flyrock, which is an undesirable environmental phenomenon in open-pit mines. While there are experimental methods available for predicting blastinduced flyrock, the complex process of assessing the distance of flyrock has reduced the efficiency of these approaches. This study employs artificial intelligence methods and statistical techniques to forecast the flyrock distance in the Sungun copper mine. Thus, an Artificial Neural Network (ANN-MLP) and a new hybrid model of Artificial Neural Network (ANN) optimized by the Imperialist Competitive Algorithm (ICA), known as (ICA-ANN), are used to predict the flyrock distance, considering crucial parameters such as the number of holes, hole spacing, burden, total charge, specific drilling, charge per hole and specific charge. The results showed that the Artificial Neural Network, with RMSE, MAE, and R² error values of 9.31 m, 7.10 m, and 0.81, respectively, was able to predict the flyrock distance well compared to the measured data in the test phase. However, the implementation of the imperialist competitive algorithm optimizer in the neural network enhanced the prediction of the flyrock distance, yielding RMSE, MAE, and R² values of 5.66 m, 4.60 m, and 0.89, respectively. Finally, by performing sensitivity analysis on the input parameters of the flyrock distance, it was determined that the amount of explosive consumption and the number of holes have the greatest impact on the blastinduced flyrock distance. [ABSTRACT FROM AUTHOR]
ISSN:	03534529
DOI:	10.17794/rgn.2024.5.8