矿岩可爆性分级的距离判别方法及应用

A Distance Discriminant Analysis Method for Orebody Blastability Classification and Its Application

矿岩可爆性的准确判定对采矿设计、安全生产等具有重要意义.将马氏距离判别法引入到矿岩可爆性分级中,建立了矿岩可爆性等级分类的距离判别模型.选用岩石抗压强度、岩石容重、岩石完整性系数和炸药单耗4项指标作为判别因子,将35个矿岩可爆性实例作为学习样本进行训练,建立了相应的判别函数对待判样本进行分类,结果表明经过训练后的模型误判率为零.将判别模型应用于工程实例,判别结果也与BP神经网络方法相符,表明该模型具有良好的判别功能,可以在实际工程中进行推广应用.

Accurate classification of orebody blastability has great significance for mining design and safety production. Based on the principle of Mahalanobis distance discriminant analysis（ DDA）,a classification model of orebody blastability is built. Four main control factors including compressive strength,bulk density,intactness coefficient of rock mass and explosive specific charge,are regarded as the discriminant factors of the DDA model. Six discriminant functions are established through training 35 orebody blastability samples from different mines,and the ratio of mistake-distinguish is zero. Seven orebody blastability instances are used to verify the DDA model. The effectiveness of DDA model is verified by comparing with the result of BP neural network. The results show that the DDA model is reasonable,effective,and applicable to practical engineering.