Effective control of blasting outcomes depends on a thorough understanding of rock geology and the integration of geological characteristics with blast design parameters.This study underscores the importance of adapting blast design parameters to geological conditions to optimize the utilization of explosive energy for rock fragmentation.To achieve this,data on fifty geo-blast design parameters were collected and used to train machine learning algorithms.The objective was to develop predictive models for estimating the blast oversize percentage,incorporating seven controlled components and one uncontrollable index.The study employed a combination of hybrid long-short-term memory(LSTM),support vector regression,and random forest algorithms.Among these,the LSTM model enhanced with the tree seed algorithm(LSTM-TSA)demonstrated the highest prediction accuracy when handling large datasets.The LSTM-TSA soft computing model was specifically leveraged to optimize various blast parameters such as burden,spacing,stemming length,drill hole length,charge length,powder factor,and joint set number.The estimated percentage oversize values for these parameters were determined as 0.7 m,0.9 m,0.65 m,1.4 m,0.7 m,1.03 kg/m^(3),35%,and 2,respectively.Application of the LSTM-TSA model resulted in a significant 28.1%increase in the crusher's production rate,showcasing its effectiveness in improving blasting operations.
