基于GA-PSO融合算法的开采沉陷Richards预计模型参数优化  

Parameter Optimization on Richards Model of Mining Subsidence Based on GA-PSO Hybrid Algorithm

作　　者：卢克东 徐良骥[1] 牛亚超 LU Kedong;XU Liangji;NIU Yachao(School of Geodesy and Geomatics,Anhui University of Science and Technology,Huainan 232001,China)

机构地区：[1]安徽理工大学空间信息与测绘工程学院,安徽淮南232001

出　　处：《金属矿山》2021年第2期155-160,共6页Metal Mine

基　　金：国家自然科学基金项目(编号:41472323);安徽省对外合作计划项目(编号:201904b11020015)。

摘　　要：在矿区开采地表沉降动态预计模型建立过程中,针对Richards时间函数模型参数在地质采矿条件复杂情况下难以一次性准确求取的问题,采用遗传粒子群(Genetic Algorithm and Particle Swarm Optimization,GA-PSO)融合算法对Richards模型参数进行动态修正,建立了一种基于GA-PSO融合算法的Richards时间函数参数优化模型。通过与传统GA算法和变步长果蝇优化算法(Fruit Fly Optimization,FOA)进行比较,结果表明:GA-PSO算法对Richards模型参数优化效果良好。通过单点举例和选取部分特征点验证的方法,得出GA-PSO算法模型在各个时期的预计中误差最大为14.43 mm,最小中误差为1.48 mm,最大平均误差为11.16 mm,最小平均误差为1.23 mm,且GA-PSO算法模型精度高于拟合模型和变步长FOA模型。研究表明:经过GA-PSO算法优化参数后的Richards模型能够更加高效,有助于精确构建矿区地表移动动态预计模型。In the process of establishing the dynamic prediction model of ground subsidence in the mining area,in order to solve the problem that the parameters of the Richards time function model are difficult to obtain at one time under the complicated geological mining conditions,genetic algorithm and particle swarm optimization(Genetic Algorithm and Particle Swarm Optimization,GA-PSO)is adopted to dynamically modify the Richards model parameters,and a Richards time parameter optimization model based on GA-PSO hybrid algorithm is established.Compared with the traditional GA algorithm and Fruit Fly Optimization(FOA)algorithm,the results show that the GA-PSO algorithm has a good effect on the parameter optimization of Richards model.Through single point examples and the method of selecting partial feature points for verification,the GA-PSO algorithm model can be obtained in each period with the maximum predicted error of 14.43 mm,the minimum median error of 1.48 mm,the maximum average error of 11.16 mm and the minimum average error of 1.23 mm,and the accuracy of GA-PSO algorithm model is higher than that of fitting model and FOA model with variable step size.The above study results further indicated that the Richards model optimized by GA-PSO algorithm can be more efficient,which is help for accurately constructing the dynamic prediction model of mining area surface movement.

关 键 词：开采沉陷 GA-PSO融合算法 Richards函数模型 参数优化 

分 类 号：TD325[矿业工程—矿井建设]