利用果蝇算法反演概率积分法开采沉陷预计参数

发布时间：2018-04-25 07:11

本文选题：开采沉陷 + 果蝇算法　；参考：《金属矿山》2016年06期

【摘要】：针对概率积分法开采沉陷预计参数反演时存在算法复杂、计算量大等问题,将具有算法简单、计算量小、精度高等特点的果蝇算法引入到概率积分法开采沉陷预计参数反演中,研究了利用果蝇算法反演概率积分法开采沉陷预计参数的基本原理,构造了下沉拟合值与实测值均方差最小的适应度函数模型。结合安徽省某煤矿的实测数据,分别采用果蝇算法、遗传算法以及粒子群算法反演概率积分法开采沉陷预计参数,并以下沉拟合值与实测值的均方差为各算法反演精度的评价标准进行对比分析,结果表明:利用果蝇算法反演出的下沉拟合值与实测值的均方差(33.7 mm)以及相对中误差(1.4%)均小于同类条件下遗传算法、粒子群算法的反演结果,说明果蝇算法适用于反演概率积分法开采沉陷预计参数,对于提高概率积分法开采沉陷预计的精度有一定的参考价值。
[Abstract]:In order to solve the problems of complex algorithm and large amount of calculation in the inversion of prediction parameters of mining subsidence by probabilistic integration method, the Drosophila algorithm, which has the characteristics of simple algorithm, small amount of calculation and high precision, is introduced into the inversion of prediction parameters of mining subsidence of probabilistic integration method. The basic principle of mining subsidence prediction parameters by using the inversion probability integration method of Drosophila algorithm is studied, and a fitness function model with minimum mean square deviation of subsidence fitting value and measured value is constructed. Based on the measured data of a coal mine in Anhui Province, the predictive parameters of subsidence were extracted by using Drosophila algorithm, genetic algorithm and particle swarm optimization algorithm respectively. The mean square deviation of the subsidence fitting value and the measured value is taken as the evaluation standard of the inversion accuracy of each algorithm. The results show that the mean square deviation (RMS) and relative median error (RMS) obtained by using Drosophila algorithm are less than those of genetic algorithm and particle swarm optimization algorithm under the same condition. The result shows that Drosophila algorithm is suitable for mining subsidence prediction parameters by inverse probabilistic integration method and has certain reference value for improving the precision of mining subsidence prediction by probabilistic integration method.
【作者单位】：中国矿业大学环境与测绘学院;国土环境与灾害监测国家测绘地理信息局重点实验室;江苏省资源环境信息工程重点实验室;
【基金】：“十二五”国家科技支撑计划项目(编号:2012BAB13B03) 国家自然科学基金青年基金项目(编号:41104011) 江苏高校优势学科建设工程项目(编号:SZBF2011-6-B35) 江苏省资源环境信息工程重点实验室基金项目(编号:JS201309)
【分类号】：TD327

【相似文献】