基于混合蛙跳算法的混凝土坝加权变形预报模型

Weighted deformation forecast model for concrete dams based on shuffled frog leaping algorithm

利用混合蛙跳算法的优化特点,将大坝安全监控统计模型的求解转换为多目标函数的优化问题;引入调整系数修正回归因子,考虑调整系数与回归因子之间的协调关系,利用混合蛙跳算法同步确定调整系数和回归系数,建立基于混合蛙跳算法的混凝土坝加权变形预报模型。工程算例应用结果表明,该模型具有较优的中长期预报能力,可提高大坝安全监控统计模型的预报精度,在大坝安全监控领域具有一定的工程应用意义。

By means of the optimization features of the shuffled frog leaping algorithm, the solution to the statistical model for dam safety monitoring was converted to the optimization of the multi-objective function. The adjustment coefficients were introduced to correct the change of the regression factors. Considering the relationship between the adjustment coefficients and the regression factors, the values of the adjustment coefficients and the regression factors were synchronously determined by use of the shuffled frog leaping algorithm. A weighted deformation forecast model for a concrete dam was established based on the shuffled frog leaping algorithm. The engineering examples show that the proposed model has superior long-term forecasting ability, and it may enhance the forecasting accuracy of the traditional statistical model for dam safety monitoring. It has certain application value for engineering in the field of dam safety monitoring.