论文部分内容阅读
随着深部开采推进,大量遗留的采空区已成为安全高效采矿的重大隐患,采空区危险性的合理评价至关重要。针对影响采空区危险度的因素复杂性和不确定性,以高峰矿105号矿体深部碎裂矿段11个实测采空区为样本数据,选取采空区结构尺寸的跨度、暴露面积和高度3个独立影响因素作为定量化评价指标,基于粗糙集(RS)理论的指标权重计算方法,引入不确定性人工智能理论,建立采空区危险度辨别的正态云模型,以最大综合确定度原则辨别各采空区的危险度,并实现了采空区三维数值模型的实证分析。研究结果表明:数值模拟结果与正态云模型辨别结果基本一致。
With the development of deep mining, a large number of mined-out areas have become a major hidden danger of safe and efficient mining. The reasonable assessment of the danger of mined-out areas is of crucial importance. In view of the complexity and uncertainty of the factors that affect the risk of goaf area, taking the 11 measured gob areas in the deep fragmented ore section of No.105 ore deposit in Gaofeng Mine as sample data, the span, the area of exposure and Height of three independent factors as a quantitative evaluation index, based on rough set theory (RS) index weight calculation method, the introduction of the theory of uncertainty artificial intelligence, to establish the risk of mined-out area of the normal cloud model to determine the maximum comprehensive determination Degree principle to distinguish the risk of goaf, and to achieve the three-dimensional numerical model of goaf area empirical analysis. The results show that the results of numerical simulation and normal cloud model are basically the same.