论文部分内容阅读
针对利用非稳定流抽水试验资料确定潜水含水层参数传统方法的不足,系统分析考虑垂直分量和弹性释水的Neuman潜水井流模型解析解的基础上,利用实码加速遗传算法(RAGA)和自适应BP神经网络模型相结合对Neuman潜水井流模型解析解进行优化求解,提出确定潜水含水层水文地质参数的Neuman-BP法。以计算实例表明,Neuman-BP法不需分抽水时间———降深过程的前、后段分别进行参数确定,避免了前、后段所求导水系数T的不一致,既充分利用了抽水试验数据,又获得了较高精度的参数,简化了参数确定过程。
Aiming at the deficiency of the traditional method of determining aquifer parameters by using unsteady flow pumping test data and systematically analyzing the analytic solution of Neuman’s model of flow field considering the vertical component and elastic release water, The Neuman-BP method for determining the hydrogeological parameters of submerged aquifers is proposed by combining the BP neural network model with the analytical solution of the Neuman wellbore flow model. The calculation example shows that the Neuman-BP method does not need to be sub-pumping time --- the process of lowering the front and rear of the parameters were determined to avoid the front and rear sections of the conductivity coefficient T inconsistent, both make full use of pumping Experimental data, but also obtained a higher precision parameters, simplifying the parameter determination process.