关键词: 深部开采, 岩石工程系统, 岩石可钻性, 人工神经网络, 中深孔凿岩台车

Abstract: The study of rock drillability has a direct impact on mine drilling efficiency and mining operation cost.At present,most of the models and methods for constructing drillability classification rely on various rock physical and mechanical parameters and various statistical analysis methods,which have certain limitations.Rock drillability is not only a unilateral attribute of rock,but also reflects the comprehensive characteristics of the interaction between rock and drilling tools.Based on the theory of rock engineering system (RES),by considering various rock mechanical properties and rock drilling construction parameters as a complete system,neural network coding method is applied to construct the overall interaction strength matrix GRSE,and a comprehensive prediction model of rock drillability classification is established,so as to reveal the complex relationship between various influencing factors and the degree of influence on rock drillability.The model is applied to the construction operation of the deep hole rock drilling rig at the level of -430 m in Chengchao Iron Mine.The results show that the rock quality index (RQD),gypsum content,iron ore grade,and impact pressure all have effects on rock drillability.Based on the above discussion resutls,the physical and mechanical properties of the level of ore rock,mineral composition content and rock drilling parameters are analyzed comprehensively,and according to the drillability level of ore and rock,the regional prediction and classification of this level are carried out.Based on classification results,the drilling parameters and technology of rock are optimized on site,and the unit drilling quantity is increased.