煤炭工程 ›› 2019, Vol. 51 ›› Issue (5): 148-153.doi: 10.11799/ce201905034

• 研究探讨 • 上一篇    下一篇

基于GA-SVM的煤矿岩巷爆破效果智能预测

马鑫民,范浩宇,林天舒,杨立云   

  1. 中国矿业大学(北京)
  • 收稿日期:2019-03-11 修回日期:2019-03-26 出版日期:2019-05-20 发布日期:2019-06-10
  • 通讯作者: 马鑫民 E-mail:mxm@cumtb.edu.cn

Intelligent Prediction of Blasting Effect of Coal Mine Roadway Based on GA-SVM

  • Received:2019-03-11 Revised:2019-03-26 Online:2019-05-20 Published:2019-06-10

摘要: 煤矿岩石巷道爆破效果预测对合理优化爆破参数、提高爆破效率具有重要意义。针对煤矿岩石巷道爆破效果影响因素多、难以进行爆破效果准确预测等关键技术难题,提出基于GA-SVM融合技术的爆破效果预测模型,实现爆破效果科学、合理预测。首先,基于综合分析、专家打分法等确定影响煤矿岩巷爆破效果关键指标|然后,根据不同矿区典型案例建立爆破效果预测样本库,并对样本进行数据处理|最后,将预测模型应用于实际工程,预测结果与爆破实际分类结果吻合。研究成果可为巷道爆破预测提供一种新思路。

关键词: 支持向量机, 遗传算法, 煤矿巷道, 爆破效果, 预测

Abstract: Prediction of blasting effect of rock roadway in the coal mine is of great significance for rational optimization of blasting parameters and improvement of blasting efficiency. Aiming at the key technical problems such as many factors affecting the blasting effect of rock roadway in the coal mine, which are difficult to accurately predict the blasting effect, a prediction model of blasting effect based on GA-SVM fusion technology is proposed to realize scientific and reasonable prediction of blasting effect. Firstly, based on a comprehensive analysis and expert scoring method, the key impact indicators affecting the blasting effect of coal mine rock roadway were determined. Secondly, according to typical cases in different mining areas, the sample database of blasting effect prediction was established and the samples were processed. Thirty sets of data were used for training, and the other 12 groups were used for prediction, the prediction accuracy was about 92%. Finally, the prediction model has been applied to practical projects. The predicted results coincided with the actual classification of blasting. The research results can provide a new idea for roadway blasting prediction.

中图分类号: