遗传神经网络在铁矿石需求预测中的应用

将遗传算法与BP神经网络结合,利用遗传算法的全局搜索优化BP网络的初始权重,有效地克服了BP算法的局部收敛和收敛速度慢等问题.使用主成分分析法选取输入变量,并将建立的混合模型应用于铁矿石需求预测中.实验表明,该方法改善了预测精度,达到了较好的预测效果.

Application of Genetic Neural Network in Forecast of Iron Ore Demand

Combining genetic algorithms with BP neural network,using genetic algorithms’s global search to optimize BP network initial weights,the local convergence,slow convergence and other issues of BP algorithm were overcome effectively.Principal component analysis was used to select input variables,and the established hybrid model was used in iron ore demand prediction.Experiments show that this method can improve the prediction accuracy and achieve better prediction.