基于奇异谱分析与PSO优化SVM的混凝土坝变形监控模型

针对混凝土坝自动化变形监测数据存在噪声成分，且变形与环境影响因素间呈现出复杂的非线性关系等问题，提出了基于奇异谱分析(SSA)与粒子群算法(PSO)优化支持向量机(SVM)的混凝土坝变形监控模型。模型利用SSA对实测变形进行分解，提取其蕴含的趋势与周期性成分并对变形加以重构；在此基础上，采用基于PSO优化的SVM对重构变形与环境影响因素间复杂的非线性函数关系进行挖掘。实例验证结果表明，该模型具有较好的拟合与预测精度，可以有效地挖掘实测变形蕴含的数据特征，减小噪声成分对建模精度的影响，具有一定的工程应用价值。

Dam deformation monitoring model based on singular spectrum analysis and SVM optimized by PSO

Considering the noise components in automatic monitoring data and the complex nonlinear relationship between dam deformation and environmental factors, a dam deformation monitoring model based on singular spectrum analysis(SSA) and support vector machine(SVM) optimized by particle swarm optimization(PSO) was proposed. SSA was used to decompose the measured deformation, and its intrinsic trend and periodic components were extracted and reconstructed. The complex nonlinear relationship between reconstruction deformation and environmental factors was then mined based on SVM optimized by PSO. The case validation results show that the model has good fitting and prediction accuracy and it can effectively mine the data characteristics inherent in the measured deformation, reduce the influence of noise components on the modeling accuracy, and has certain engineering application value.