Reservoir dams have varying degrees of damage and hidden dangers under long-term and complex operating conditions, engineering problems mainly focus on the gradual decrease of seepage stability and guarantee rate of deformation and stability of dam foundation. However, due to the complexity of the dam foundation structure and the surrounding environment, the performance degradation of the dam foundation caused by the aging of the impervious structure lacks a systematic study of the process and its mechanism, In particular, the determination of relevant seepage parameters is complicated, moreover the simulation accuracy of its inversion model is not enough to meet the needs of long-term stability evaluation of the dam foundation. In order to study the seepage stability of the dam foundation of the reservoir during operation, a three-dimensional finite element model of complex geological bodies is combined with artificial neural network to establish a model of inversion of seepage field in the dam foundation, According to the 22 groups of predicted grouting schemes, five groups of representative grouting schemes were selected and the seepage characteristics of the same location were analyzed. The conclusions as below: (1) the inversion predicted that when the permeability coefficient was in the range of 3.0 × 10⁻⁶ cm/s to 5.0 × 10⁻⁶ cm/s, the change range was small, and the curtain's anti-seepage effect was more obvious. (2) The analysis of the dam base surface and the bottom of the grouting area shows that the difference between the water head and seepage gradient of the dam base surface and the bottom of the grouting area under the GZ₇ and GZ₃ schemes vary significantly with the grouting effect. Among them, especially in the GZ₃ scheme, the key parts of the dam foundation surface F2 ~ F4: the seepage gradient value gradually increases, and all reach the maximum value in the GZ₃ scheme; For G6 ~ G15 at the bottom of the grouting area, the water head value under the GZ₃ scheme is gradually smaller than the three grouting schemes of GZ₁₁, GD₃ and GD₇, as the water head value gradually decreases, the anti-seepage effect becomes more and more obvious. The above results show that the inversion prediction range is in good agreement with the actual law, when the permeability coefficient is within the predicted range, the anti-seepage effect is optimal. (3) The difference of the water head and seepage gradient difference between the dam foundation and the grouting area near the curtain changes significantly with the grouting effect. Characteristics of seepage field in key parts of the dam foundation under the six curtain grouting coefficients, the water head value F1-F2 decreased by 75%, F3-F13 decreased by 28%, the seepage gradient value F1-F2 decreased by 88%, and F3-F13 decreased by 29%, namely the grouting effect of the dam foundation and the grouting area gradually weakens as the distance between the characteristic part and the curtain increases. The research in this paper can provide a theoretical reference for the analysis and evaluation of dam seepage conditions.

在长期和复杂的运行条件下，水库大坝具有不同程度的破坏和隐患，工程问题主要集中在渗流稳定性的逐渐降低以及大坝基础变形和稳定的保证率上。然而，由于大坝基础结构和周围环境的复杂性，由于不透水结构的老化导致大坝基础的性能下降，缺乏对过程及其机理的系统研究，特别是对相关渗流的确定。参数复杂，而且其反演模型的仿真精度不足以满足大坝基础长期稳定性评估的需要。为了研究水库坝基在运行过程中的渗流稳定性，将复杂地质体的三维有限元模型与人工神经网络相结合，建立大坝基础渗流场反演模型，根据22组预测的灌浆方案，选择了5组具有代表性的灌浆方案。分析了同一位置的渗流特征。结论如下：（1）反演预测了渗透系数在3.0×10范围内^-6 cm / s至5.0×10 ^-6 cm / s，变化范围小，窗帘的防渗效果更加明显。（2）对坝基和灌浆区底部的分析表明，在GZ ₇和GZ ₃方案下，坝基和灌浆区底部的水头和渗流梯度之间的差异显着具有灌浆效果。其中，特别是在GZ ₃方案中，坝基面F2〜F4的关键部分：渗流梯度值逐渐增大，并在GZ ₃方案中均达到最大值。对于灌浆区底部的G6〜G15，GZ ₃下的水头值方案逐渐小于GZ ₁₁，GD ₃和GD ₇的三种注浆方案。，随着水头值逐渐减小，防渗效果变得越来越明显。上述结果表明，反演预测范围与实际规律基本吻合，当渗透系数在预测范围内时，防渗效果最佳。（3）坝基与帷幕附近灌浆区的水头差和渗流梯度差随灌浆效果的变化而显着变化。在六个帷幕灌浆系数的作用下，坝基关键部位的渗流场特征，水头值F1-F2下降了75％，F3-F13下降了28％，渗透梯度值F1-F2下降了88％， F3-F13下降了29％，即，随着特征部分与幕布之间的距离增加，坝基和灌浆区域的灌浆效果逐渐减弱。本文的研究可为大坝渗流条件的分析和评价提供理论参考。