用基于统计模式识别的优化BP网络预报转炉的终点磷含量

Prediction of End Phosphorus in Converter Steelmaking Using Optimized BP Network Based on SPR

用模式识别和神经网络建立PLSBP的转炉终点磷含量降维网络模型,克服了PLS法和BP法各自的缺陷。用该模型设计了4个冶炼工艺参数点,预测值与实际值比较吻合。

A model of predicting end phosphorus in converter steelmaking was established based on the PLS-BP dimensionality reduction net using SPR and ANN to avoid the defaults of PLS and BP individually. Four parameter points were designed and the predicted resalts were in agreement with measured ones.