爆破振动对边坡稳定性影响的FA-IGA-LSSVM模型
发布时间：2019-02-10 19:03
【摘要】：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.
[Abstract]:In order to predict the slope stability in mining blasting process, factor analysis, immune algorithm and least square support vector machine are combined to extract the blasting amplitude, main frequency duration, rock weight and cohesion. Angle of slope and height of slope affect 7 indexes. The dimension of sample data is reduced by factor analysis, and a common factor is extracted. The model is trained with 29 groups of measured sample data, and the slope stability prediction model based on factor analysis and IGA-LSSVM is constructed, and the model is tested by the method of back generation estimation, and the error rate is 3 / 29. The other five groups of samples were used to test the generalization ability of the model and compared 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 error rate of the prediction result is 0.
【作者单位】： 辽宁工程技术大学工商管理学院;
【基金】：国家自然科学基金项目(51404125)
【分类号】：TD235
[Abstract]:In order to predict the slope stability in mining blasting process, factor analysis, immune algorithm and least square support vector machine are combined to extract the blasting amplitude, main frequency duration, rock weight and cohesion. Angle of slope and height of slope affect 7 indexes. The dimension of sample data is reduced by factor analysis, and a common factor is extracted. The model is trained with 29 groups of measured sample data, and the slope stability prediction model based on factor analysis and IGA-LSSVM is constructed, and the model is tested by the method of back generation estimation, and the error rate is 3 / 29. The other five groups of samples were used to test the generalization ability of the model and compared 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 error rate of the prediction result is 0.
【作者单位】： 辽宁工程技术大学工商管理学院;
【基金】：国家自然科学基金项目(51404125)
【分类号】：TD235
【参考文献】
相关期刊论文 前1条
1 杨帆;林琛;周绮凤;符长虹;罗林开;;基于随机森林的潜在k近邻算法及其在基因表达数据分类中的应用[J];系统工程理论与实践;2012年04期
【共引文献】
相关期刊论文 前10条
1 郭东锋;姚忠达;徐迎波;舒俊生;;基于化学成分的烤烟香型分类研究[J];湖南文理学院学报(自然科学版);2013年04期
2 王志宏;韩璐;戚磊;;随机森林分类方法在储层岩性识别中的应用[J];辽宁工程技术大学学报(自然科学版);2015年09期
3 李辉;冯东梅;马寒;;路堑开挖爆破对民房危害的随机森林预测模型[J];辽宁工程技术大学学报(自然科学版);2015年12期
4 温廷新;张波;;露天煤矿边坡稳定性的随机森林预测模型[J];科技导报;2014年Z1期
5 温廷新;张波;邵良杉;;煤与瓦斯突出预测的随机森林模型[J];计算机工程与应用;2014年10期
6 李飞;;森林采伐生态安全的现状及对策研究[J];生物技术世界;2014年12期
7 王秀华;王建珍;;一种并行的加速K-近邻分类方法[J];太原师范学院学报(自然科学版);2014年04期
8 张胜君;陈后金;;乳腺X线图像结构扭曲检测的一种新方法[J];系统工程理论与实践;2013年03期
9 孙远帅;陈W，
本文编号：2419432
本文链接：https://www.wllwen.com/kejilunwen/kuangye/2419432.html
