基于改进CS优化算法的灰色神经网络预测模型

On a Forecasting Model of Grey Neural Network Based on Improved Cuckoo Search Optimal Algorithm

为了提高灰色神经网络在人工智能预测领域中的预测准确性,提出一种改进布谷鸟算法优化灰色神经网络的预测方法.通过改进的布谷鸟算法对常规灰色神经网络(GNN)的白化参数进行优化,寻找出最优初始化参数,并将其结果作为灰色神经网络的输入,建立了基于改进布谷鸟优化的灰色神经网络预测模型,在此基础上,采用该方法对煤与瓦斯突出进行预测.仿真实验表明,该模型的预测精度要优于标准灰色神经网络和基于粒子群算法的灰色神经网络等方法.

In order to improve the prediction accuracy of the Gray Neural Network(GNN)in the field of artificial intelligence prediction,the GNN based on the Improved Cuckoo Search Algorithm(CS-GNN)has been proposed in this paper.To find out the optimal initialization parameters,the conventional GNN whitening parameters have been optimized by the improved cuckoo search algorithm,and the results been used as the input of the GNN.A Grey Neural Network model based on improved cuckoo search optimization has been built and used to predict coal and gas outburst.The simulation experiment result indicates that the prediction accuracy of the model is higher than that of the conventional GNN and the GNN based on Particle swarm algorithm(PSO-GNN).