摘要
为准确预测导水裂隙带高度,有效地预防煤矿开采中溃水安全事故,根据导水裂隙带相关理论研究和实测资料分析选取开采深度、煤层的倾斜角、厚度、硬度、岩层结构等8项指标作为导水裂隙带高度预测的特征指标,采用基于因子分析的APSO-LSSVM导水裂隙带高度预测模型.利用典型矿区导水裂隙带高度实测资料中的18组数据对该模型进行训练与检验,并将其预测结果与PSO-LSSVM、LSSVM模型预测结果分别进行比较.结果表明:APSO-LSSVM模型的预测精度高于PSO-LSSVM模型和LSSVM模型,对样本具有较强的识别能力.
In order to accurately predict the height of the water guiding fracture zone and effectively prevent the water collapse safety accident in coal mining,according to the theoretical research and measured data analysis of the water-conducting fracture zone,eight indexes such as mining depth,coal seam inclination angle,thickness,hardness and rock stratum structure are selected as the characteristic indexes of the water-conducting fracture zone height prediction.Using height predictive model of APSO-LSSVM water-conducting fracture zone is used to carry out factor analysis.The model was used to train and test 18 sets of data from the highly measured data of the water-cracking zone of a typical mining area.The prediction results are compared with the prediction results of PSO-LSSVM and LSSVM models.The results show that the prediction accuracy of the APSO-LSSVM model is higher than that of the PSO-LSSVM model and the LSSVM model,and it has strong recognition ability for the sample.
作者
毛志勇
赖文哲
黄春娟
MAO Zhiyong;LAI Wenzhe;HUANG Chunjuan(College of Business Administration,Liaoning Technical University,Huludao 125105,China)
出处
《辽宁工程技术大学学报（自然科学版）》
CAS
北大核心
2020年第1期34-40,共7页
Journal of Liaoning Technical University (Natural Science)
基金
国家自然科学基金(71771111).
关键词
导水裂隙带高度
相关性分析
因子分析
自适应粒子群算法
最小二乘支持向量机
height of water flowing fractured zone
correlation analysis
factor analysis
adaptive particle swarm optimization
least squares support vector machine
