论文部分内容阅读
为对矿山开采爆破过程中边坡的稳定性进行预测,将因子分析、免疫算法及最小二乘支持向量机相结合,共提取爆破振幅、主频率、主频率持续时间、岩石重度、粘聚力、边坡角、边坡高度7个影响指标.通过因子分析对样本数据进行降维,提取出一个公共因子.利用实际测量的29组样本数据对模型进行训练,构建基于因子分析和IGA-LSSVM的边坡稳定性预测模型;采用回代估计法对模型进行检验,误判率为3/29.使用其他5组样本检验模型的泛化能力,同时与基本最小二乘支持向量机进行对比,结果表明:所得模型的预测精度高于基本最小二乘支持向量机,预测结果的误判率为0.
In order to predict the slope stability during mining blasting, factor analysis, immune algorithm and least square support vector machine are combined to extract the amplitude of blasting, main frequency, duration of main frequency, rock weight and cohesion , Slope angle and slope height.A factor analysis was used to reduce the dimension of the sample data to extract a common factor.Using 29 sample data from the actual measurement to train the model to construct a model based on factor analysis and IGA-LSSVM And the false positive rate was 3/29.The other five groups of samples were used to test the generalization ability of the model and the comparison with the basic least squares support vector machine, The results show that the prediction accuracy of the model is higher than that of the basic least squares support vector machine, and the false positive rate of the prediction result is zero.