自适应变异粒子群优化灰色模型在变形分析中的应用

标准灰色模型GM(1,1)以序列第一个分量作为初始条件进行灰色微分建模,未能充分利用序列中的新信息;其背景值的构造本质上采用了数值积分中的梯形法,精度不高。针对上述缺点,提出一种基于粒子群算法的灰色预测模型,即PSOGM(1,1)模型,对初始值和背景值参数进行优化,并将模型应用于岩体变形分析中。计算结果表明,PSOGM(1,1)模型具有较高的预测精度,可作为变形分析的一种新方法。

The grey model based on adaptive mutation practical swarm optimization algorithm and its application in deformation monitoring

GM （1, 1）uses the first component of sequence as the initial conditions for grey differential modeling, failing to make full use of new information in the sequence. The structure of its background value essentially uses the gradient method in the numerical integration, causing that the accuracy is not high. In view of the above shortcomings, it propose a grey model based on practical swarm optimization algorithm, which is the PSOGM（1,1）model, optimizing the parameters of initial values and background values. This model is applied to the rock mass deformation monitoring. The calculation results show that the PSOGM（1,1）model has the higher prediction accuracy. So the PSOGM（1,1）model can be used for deformation monitoring： as a new method.