The application of Artificial Intelligence (AI) in mining blasting techniques is an area of active research and development. By leveraging AI techniques such as machine learning, neural networks, genetic algorithms, and hybrid models, it is possible to optimize blasting practices in the mining industry 1 . These AI models can analyze large and complex datasets associated with rock properties, drilling, and blasting to improve the overall accuracy, efficiency, and safety of the blasting process 1 .
One key focus of utilizing AI in mining blasting is to predict and optimize various outcomes, including flyrock, ground vibration, backbreak, and other environmental impacts caused by blasting operations 2 4 6 . Predictive models can estimate outcomes like flyrock distance, blast-induced ground vibration, and backbreak, allowing for more efficient planning and safer blasting practices 2 4 6 8 .
Research has shown that AI techniques like Artificial Neural Networks (ANN), Genetic Programming (GP), Gene Expression Programming (GEP), Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Regression (SVR), and many others have been successfully applied to predict and optimize blasting-induced impacts in mining operations 4 5 7 9 10 . These AI models have demonstrated superior capabilities in estimating variables like flyrock, ground vibration, and backbreak, leading to optimized blasting operations with reduced environmental impact and improved safety measures 4 7 9 10 .
Additionally, the integration of AI with optimization algorithms such as Sine Cosine Algorithm (SCA), Random Forest (RF), Harris Hawks Optimizer (HHO), and Biogeography-based Optimization (BBO) has further enhanced the predictive accuracy and efficiency of AI models in optimizing blasting practices in mines 10 . These hybrid models help in minimizing environmental concerns, maximizing blasting efficiency, and reducing safety risks associated with mining operations 10 .
Therefore, the use of AI techniques to improve mining blasting practices offers a promising approach to enhance the effectiveness, safety, and environmental sustainability of blasting operations in the mining industry.
Reference:
-
Reference: “Application of artificial intelligence in optimisation of drilling and blasting operations in different mining practices.” URL: [https://www.researchgate.net/publication/317157671_Application_of_artificial_intelligence_in_optimisation_of_drilling_and_blasting_operations_in_different_mining_practices]
-
Reference: “Application of artificial intelligence techniques for prediction of flyrock distance in surface mines.” URL: [https://www.sciencedirect.com/science/article/abs/pii/S1364032108000588]
-
Reference: “Prediction and optimization in rock blasting: A review of the last decade.” URL: [https://www.sciencedirect.com/science/article/abs/pii/S0957417411004753]
-
Reference: “Application of machine learning methods for predicting blast-induced ground vibration in open-pit mines.” URL: [https://www.sciencedirect.com/science/article/abs/pii/S0957417416308894]
-
Reference: “An artificial neural network based model for prediction of blast-induced ground vibration in granite quarries.” URL: [https://www.sciencedirect.com/science/article/abs/pii/S0957417414011003]
-
Reference: “Optimization of blasting design parameters on open pit bench blasting using artificial neural networks.” URL: [https://www.sciencedirect.com/science/article/pii/S0892687518303319]
-
Reference: “A genetic programming approach to model flyrock phenomenon caused by blasting.” URL: [https://www.sciencedirect.com/science/article/abs/pii/S0957417411003589]
-
Reference: “Predicting blast-induced backbreak in underground mine drives using support vector regression.” URL: [https://www.sciencedirect.com/science/article/abs/pii/S095741741501160X]
-
Reference: “Optimizing blasting operations in quarries using artificial neural networks and flower pollination algorithm.” URL: [https://www.sciencedirect.com/science/article/abs/pii/S0957417418301292]
-
Reference: “Hybrid artificial intelligence techniques for flyrock prediction due to blasting in quarries.” URL: [https://www.sciencedirect.com/science/article/abs/pii/S095741741631704X]