改进型果蝇算法优化的灰色神经网络变形预测

针对灰色神经网络权值阈值的不确定性,该文提出改进型果蝇优化算法优化的灰色神经网络预测模型。通过添加逃脱系数修改适应度函数,同时引入三维空间搜索的概念扩大了果蝇搜索范围对基本果蝇优化算法进行改进,避免算法陷入早熟收敛的陷阱,加快收敛速度,有效地提高了算法的优化性能。利用改进型果蝇优化算法优化灰色神经网络参数建立预测模型。选用实际工程沉降数据仿真模拟,验证该模型的预测性能,并将预测结果与果蝇优化算法灰色神经网络、粒子群优化灰色神经网络和灰色神经网络进行比较。结果表明,改进型果蝇优化算法优化的灰色神经网络预测模型预测精度更高,拟合程度更好。

Deformation prediction of grey neural network based on modified fruit fly algorithm

In order to overcome the problem of uncertainty in grey neural network model(GNNM),this paper proposed a prediction model of grey neural network optimized by modified fruit fly optimization algorithm.Fitness function was modified by the addition of jump coefficients,at the same time,the concept of three-dimensional space search was introduced to expand the scope of the fruit fly to improve the optimization algorithm,which could avoid the local extreme value and improve the searching ability of the algorithm.The improved algorithm was used to optimize the parameters of grey neural network,and the optimal value was obtained by training the grey neural network model.The prediction performance of the model was verified by the simulation of the actual engineering deformation data,and the results were compared with the grey neural network of the fruit fly optimization,the grey neural network and the grey neural network prediction model of the particle swarm optimization algorithm.The results showed that the prediction accuracy and fitting degree of improved fruit fly optimization algorithm of grey neural network were higher.