optimizing blast-induced ground vibration reduction using an integrated ann-eoa model: a case study of sarcheshmeh copper mine

Blast-induced ground vibrations pose significant environmental and safety challenges in open-pit mining operations،particularly in geologically complex areas. this study develops an integrated artificial neural network-equilibrium optimizer algorithm (ann-eoa) model to predict and optimize blast-induced ground vibrations specifically for the sarcheshmeh copper mine's sensitive western wall. the ann model demonstrated exceptional predictive accuracy (r² = 0.96) in forecasting peak particle velocity (ppv) based on seven key blasting parameters. the eoa then successfully identified an optimal blasting configuration that predicts a 34% reduction in ppv to 6.72 mm/s،achieved through optimized burden (6m)،spacing (7m)،delay time (50ms)،and charge parameters. this research bridges a critical gap between generalized ai models and site-specific applications،providing both a practical solution for vibration mitigation at sarcheshmeh and a transferable methodology that advances the integration of computational intelligence with mining engineering challenges. the findings underscore the importance of accounting for specific geological conditions in blast optimization while highlighting the need for field validation as the essential next step.

optimizing blast-induced ground vibration reduction using an integrated ann-eoa model: a case study of sarcheshmeh copper mine

blast-induced ground vibrations pose significant environmental and safety challenges in open-pit mining operations،particularly in geologically complex areas. this study develops an integrated artificial neural network-equilibrium optimizer algorithm (ann-eoa) model to predict and optimize blast-induced ground vibrations specifically for the sarcheshmeh copper mine's sensitive western wall. the ann model demonstrated exceptional predictive accuracy (r² = 0.96) in forecasting peak particle velocity (ppv) based on seven key blasting parameters. the eoa then successfully identified an optimal blasting configuration that predicts a 34% reduction in ppv to 6.72 mm/s،achieved through optimized burden (6m)،spacing (7m)،delay time (50ms)،and charge parameters. this research bridges a critical gap between generalized ai models and site-specific applications،providing both a practical solution for vibration mitigation at sarcheshmeh and a transferable methodology that advances the integration of computational intelligence with mining engineering challenges. the findings underscore the importance of accounting for specific geological conditions in blast optimization while highlighting the need for field validation as the essential next step.