人工神经网络
磷
炼钢
反向传播
可解释性
碱性氧气炼钢
人工智能
均方误差
约束(计算机辅助设计)
计算机科学
数学
过程(计算)
内容(测量理论)
统计
冶金
材料科学
数学分析
操作系统
几何学
作者
Kai-xiao Zhou,Wen‐Hui Lin,Jiankun Sun,Jiangshan Zhang,Dezheng Zhang,Xiaoming Feng,Qing Liu
标识
DOI:10.1007/s42243-021-00655-6
摘要
Dephosphorization is essential content in the steelmaking process, and the process after the converter has no dephosphorization function. Therefore, phosphorus must be removed to the required level in the converter process. In order to better control the end-point phosphorus content of basic oxygen furnace (BOF), a prediction model of end-point phosphorus content for BOF based on monotone-constrained backpropagation (BP) neural network was established. Through the theoretical analysis of the dephosphorization process, ten factors that affect the end-point phosphorus content were determined as the input variables of the model. The correlations between influencing factors and end-point phosphorus content were determined as the constraint condition of the model. 200 sets of data were used to verify the accuracy of the model, and the hit ratios in the range of ± 0.005% and ± 0.003% are 94% and 74%, respectively. The fit coefficient of determination of the predicted value and the actual value is 0.8456, and the root-mean-square error is 0.0030; the predictive accuracy is better than that of ordinary BP neural network, and this model has good interpretability. It can provide useful reference for real production and also provide a new approach for metallurgical predictive modeling.
科研通智能强力驱动
Strongly Powered by AbleSci AI