Advanced Analytics for Rock Blasting and Explosives Engineering in Mining

Mariz, Jorge Luiz Valença; Soofastaei, Ali

doi:10.1007/978-3-030-91589-6_13

Cited by 5 publications

(3 citation statements)

References 253 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Raina and Bhatawdekar define fly-rock as the extreme propulsion of fractured rock caused by explosive energy [9]. This has also been explained by Mariz and Soofastaeias as an unexpected flinging of rock material during blasting due to the explosive substance's high force [10]. Considering all the negative environmental effects of blasting, induced flyrock generation is one of the major causes of human injury, mortality, and structural damage [11].…”

Section: Introductionmentioning

confidence: 98%

Safe small scale mine blasting operation: An application of soft computing techniques to predict blast-induced flyrock distance

Taiwo,

Hosseini,

Fissha

et al. 2023

Preprint

View full text Add to dashboard Cite

Flyrock is a major environmental and safety issue during mine production blasting. This can affect workers’ safety and efficiency. Blasting in mines can cause rock fragments to travel far to endanger workers, machinery, and nearby structures. Also, many rock excavation projects anticipated fly-rocks and prevent its impact. This study uses Long Short-term memory networks and seven other machine learning methods to predict the Akoko Edo dolomite Quarries' fly-rock distance. Two hundred and fifty-eight (258) blasting data samples were obtained for model-building. Fly-rock prediction was created using LSTM machine learning. The proposed LSTM fly-rock prediction model was tested using bidirectional recurrent neural networks (BRNN), support vector regressions (SVR-S, SVR-RBF, SVR-L, and SVR-P), and random forest (RF) models. Each modeling method is detailed enough for other scientists to replicate. The top three influencing parameters, which have different correlations with fly-rock, were used to create a fly-rock possibility assessment chart. After testing and training, each machine-learning method was compared. The model error analysis indices and coefficient of determination showed that the LSTM model was the best at predicting fly-rock distance. By accurately predicting fly-rock distance, the LSTM prediction model will go a long way to improve blast area reliability and safety.

show abstract

Section: Introductionmentioning

confidence: 98%

Safe small scale mine blasting operation: An application of soft computing techniques to predict blast-induced flyrock distance

Taiwo,

Hosseini,

Fissha

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The use of machine learning approaches, such as ANN, can help optimize explosive use in small-scale quarries [ 15 ]. The fragmentation-energy fan model, represented by the Swebrec function, can analyze the dependence of fragmentation on the powder factor and predict fragment sizes with high accuracy [ 19 , 20 ]. Other factors, such as the delay between holes and geotechnical properties of the rock mass, can also influence the powder factor and blasting.…”

Section: Introductionmentioning

confidence: 99%

Explosive utilization efficiency enhancement: An application of machine learning for powder factor prediction using critical rock characteristics

Olamide Taiwo,

Gebretsadik,

Abbas

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…During the 2017-2022 period, it grew from nearly USD 23.8 billion to USD 31.2 billion [9]. This growth is primarily related to the usage of these materials in the mining, quarrying, and construction industries [10][11][12]. From a practical point of view, the energetic compound should be powerful, stable, insensitive to mechanical stimuli, and provide a large quantities of energy release during intentional detonation [2][3][4].…”

Section: Introductionmentioning

confidence: 99%

Computational Studies of Energetic Property Peculiarities in Trinitrophenyl-Substituted Nitramines

Tamulienė

Šarlauskas

2023

Energies

View full text Add to dashboard Cite

This research was performed using Becke’s three-parameter hybrid functional approach with non-local correlation provided by Lee, Yang, and Parr and the cc-pVTZ basis set. The geometry, total energy, and heat of formation of the most stable conformers of the nitramines under study were obtained to obtain the density, resistance to shock stimuli, detonation pressure, and velocity of the materials under study. The results obtained allow us to predict new multipurpose energetic materials with a good balance between energy and stability. Our findings show that N-(2-nitroethyl)-N-(2,4,6-trinitrophenyl)nitramine, N-(2,4,6-trinitrophenyl)-N-[(3,4,5-trinitro-1H-pyrazol-1-yl)methyl]nitramine, N-(2,2-dinitroethyl)-N-(2,4,6-trinitrophenyl)nitramine, N-(2,2,2-trinitroethyl)-N-(2,4,6-trinitrophenyl)nitramine, and N-(trinitromethyl)-N-(2,4,6-trinitrophenyl)nitramine possess better explosive properties and a greater stability compared to tetryl, although they remain sensitive to shock stimuli. Referring to the results obtained, we recommend new tetryl analogs containing dinitroethyl, trinitroethyl, and trinitromethyl substituents for practical usage.

show abstract

Advanced Analytics for Rock Blasting and Explosives Engineering in Mining

Cited by 5 publications

References 253 publications

Safe small scale mine blasting operation: An application of soft computing techniques to predict blast-induced flyrock distance

Safe small scale mine blasting operation: An application of soft computing techniques to predict blast-induced flyrock distance

Explosive utilization efficiency enhancement: An application of machine learning for powder factor prediction using critical rock characteristics

Computational Studies of Energetic Property Peculiarities in Trinitrophenyl-Substituted Nitramines

Contact Info

Product

Resources

About