基于随机森林与神经网络的铝电解分子比预测

Predicted molecular ratio of aluminum reduction based on random forest and neural network

本文基于随机森林与神经网络方法对铝电解过程中的分子比进行预测。使用采集到的包括电流、电压和铝水平等数据作为自变量,分子比作为因变量,基于随机森林回归算法的嵌入式特征选择的方法选择最优特征子集。然后将该最优子集作为神经网络的输入预测铝电解过程中的分子比参数,最终得到了很好的预测效果,从而验证了该方法的有效性与准确性。

Based on the random forest and neural network method the molecular ratio in the process of aluminum reduction is predicted.Using collected data including current,voltage,and aluminum level as independent variables and molecular ratio as a dependent variable,and optimal feature subset is selected based on the embedded feature selection method of the random forest regression algorithm.Then the optimal subset is used as the input of the artificial neural network to predict the molecular ratio parameters in the aluminum reduction process,and finally a good prediction effect is obtained,thus verifying the effectiveness and accuracy of the method.