基于PSO_GM_MC的某混凝土双曲拱坝监控模型

Displacement Prediction of Concrete Double Curvature Dam Based on PSO_GM_MC Model

大坝位移的准确预测对大坝安全监控具有重要意义。针对传统的GM(1,1)模型在大坝位移监控中存在预测误差较大的问题,利用粒子群优化算法(PSO)对背景值权重参数寻优重构,借助马尔科夫链(MC)实现残差优化,建立了大坝位移的PSO_GM_MC监控模型。实例分析表明,PSO_GM_MC监控模型与传统灰色模型GM(1,1)相比,在大坝位移预测精度上有较大提高,可用于大坝位移的安全监控。

Accurate prediction of dam displacement is of great significance for dam safety monitoring.The traditional GM（1,1）model has large prediction errors in dam displacement.The particle swarm optimization algorithm（PSO）was adopted to optimize background weight parameter of GM（1,1）model.Then,Markov chain was used to correct residual errors,and the dam displacement monitoring PSO_GM_MC model was established.An example analysis shows that the prediction precision of PSO_GM_MC model for dam displacement is increased compared with the traditional GM（1,1）model,and it can be used as a new kind of prediction method in dam displacement prediction.