集对理论聚类分析法综合预测煤与瓦斯突出

发布时间：2018-05-02 23:08

本文选题：煤与瓦斯突出 + 集对理论聚类分析法　；参考：《西安科技大学学报》2015年05期

【摘要】：基于集对理论和聚类分析相结合的方法,将现行的钻屑指标法、钻孔瓦斯涌出初速度法、电磁辐射法和单项指标法等单因素单数值预测煤与瓦斯突出的方法和指标,通过集对理论综合运用一个具体的集对联系度数学模型表达出来,结合系统聚类分析思想,通过计算预测系统联系度之间的同异反距离,按照同异反模式识别的"择近原则",来辨别待测样本系统所属的类别,从而进行多因素综合预测煤与瓦斯突出。通过以焦作九里山矿巷道掘进工作面为例,应用综合预测模型计算分析煤与瓦斯突出预测指标的实例数据,结合相似权计算法确定各指标因素权重,提高预测模型精度,预测结果符合现场实际情况,取得了良好的预测效果。
[Abstract]:Based on the combination of set pair theory and cluster analysis, the methods and indexes of single factor and single numerical prediction of coal and gas outburst, such as drilling cuttings index method, initial velocity method of gas emission from borehole, electromagnetic radiation method and single index method, are used to predict coal and gas outburst. By means of set pair theory, a specific mathematical model of set pair connection degree is used to express it. Combined with the idea of system cluster analysis, the similarity, difference and inverse distance between system connection degree are calculated and predicted. According to the "nearest selection principle" of the same, different and anti-pattern recognition, the classification of the sample system to be tested is identified, and the multi-factor comprehensive prediction of coal and gas outburst is carried out. Taking Jiaozuo Jiulishan coal mine roadway driving face as an example, this paper applies the comprehensive prediction model to calculate and analyze the actual data of coal and gas outburst prediction index, and combines the similarity weight calculation method to determine the weight of each index factor and improve the precision of the prediction model. The prediction results are in line with the actual situation in the field and good prediction results have been obtained.
【作者单位】：西安科技大学能源学院;教育部西部矿井开采及灾害防治重点实验室;西安石油大学电子工程学院;
【基金】：陕西省创新团队项目(2012KCT-09) 国家自然科学基金项目(51134019)
【分类号】：TD713.2

【参考文献】