基于主成分分析(PCA)与GA-BP结合的转炉终点锰含量预测研究
首发时间:2018-11-06
摘要:为提高转炉炼钢终点锰含量的预测精度,本文分析了影响转炉炼钢终点锰含量的因素,提出了将主成分分析与GA-BP神经网络相结合的转炉炼钢终点锰含量预测方法。使用主成分分析法对多个影响终点锰含量的因素进行降维处理或重新组合,将处理后所得较少的主成分变量作为样本输入GA-BP神经网络进行训练而得到转炉炼钢终点锰含量预测模型,通过将PCA-GA-BP模型预测结果与GA-BP神经网络模型预测结果相比较,结果显示:基于主成分分析的预测模型的精度较高,泛化性能好,预测误差在±0.025%范围内的命中率达到86%,均方误差为2.78×10-8,且模型的训练速度有了显著的提升。
关键词: 钢铁冶金 转炉 终点锰含量 BP神经网络 遗传算法 主成分分析
For information in English, please click here
Concentrate Prediction of End-point Manganese Content for BOF Steelmaking Process Based on Principal Component Analysis (PCA)and GA-BP
Abstract:In order to improve the prediction accuracy of the prediction model of end-point manganese content for BOF steelmaking process,a data processing method based on the combination of principal component analysis and BP neural network was presented by analyzing its influential factors during BOF steelmaking process. By using principal component analysis,the amount of variables which affect the end-point manganese content will be reduced. Then the principal components are employed to train the BP neural network in order to obtain the prediction model of end-point manganese content for BOF steelmaking process. In comparison with the network model which uses the original variables as the inputs to predict the end-point manganese content, the results show that GA-BP neural network prediction modeling method based on principal component analysis method has the better prediction accuracy and the better generalization performance , The hit ratio of the model is 86% when the predictive errors of the model are within ±0.025%, and the mean square error is 2.78×10-8. and this modeling method has both high efficiency in calculation.
Keywords: Iron and steel metallurgy BOF end-point manganese content BP neural network genetic algorithm PCA
引用
No.****
动态公开评议
共计0人参与
勘误表
基于主成分分析(PCA)与GA-BP结合的转炉终点锰含量预测研究
评论
全部评论0/1000