基于GSA-LSSVM的岩石爆破块度预测

Prediction of Rock Blasting Fragmentation Based on GSA-LSSVM

为了提高露天矿山爆破开挖的作业效率、增加经济效益,精准地预测爆破块度分布至关重要。文章将万有引力搜索智能算法(GSA)与最小二乘支持向量机结合,形成GSA-LSSVM预测模型,首次将该预测模型应用到爆破块度的预测当中。结合现有有关的矿山爆破块度数据,并依次运用GSA-LSSVM、LS-SVM、Kuz-Ram三种块度模型进行数据预测、分析。根据预测结果分析可知:在三种不同的爆破块度预测模型中,精度最高的为GSA-LSSVM模型,佐证了将该模型运用于预测露天矿山爆破块度的可行性及预测精度的优势。

During blasting and excavation of open pit mines,it is importance to predict the blasting fragmentation accurately and reasonably for improving the working efficiency and economic benefit.In this paper,GSA-LSSVM prediction model is formed by combining GSA with LS-SVM.Based on the existing statistical data of mine blasting fragmentation,three models,GSA-LSSVM,LS-SVM and Kuz-Ram,were respectively used to make predictions.The research results show that GSA-LSSVM model has the highest prediction accuracy,which proves that the model has advantages in predicting blasting fragmentation in open pit mines.