针对各种可能工况,通过降强有限元法分析拱坝稳定安全储备系数和相应的坝肩变形场,利用人工神经网络强非线性映射的特点,建立稳定安全储备系数和相应坝肩变形场的映射关系,结合坝肩实测变形场,提出基于实测变形资料的稳定安全储备系数分析方法。应用实例表明,该方法有效可行,为利用变形资料评判拱坝的稳定性提供了量化依据。
The arch darn safety factor and the deformation field of dam abutment were analyzed using the strength reduction finite element method under different load conditions. The mapping relationship between the safety factor and the deformation field was established using a BP artificial neural network. An analysis method for the safety factor was presented based on the deformation observation. Case studies show that the proposed method is feasible and effective, and that it can provide a quantitative basis for arch dam stability evaluation.