论文部分内容阅读
针对某冶炼生产企业针铁矿法沉铁过程Fe2+浓度和Fe3+浓度难以实时检测的问题,在奥拓昆普生产设备和工艺的基础上,利用改进最小二乘支持向量机模型具有对小样本进行非线性预测、过程神经网络可充分表达历史数据序列中时间累积效应的特点,提出一种基于信息熵方法的集成预测模型.仿真实验表明,集成预测模型具有良好的预测性能,预测效果能满足针铁矿法沉铁过程对铁离子浓度值的误差要求.
Aiming at the problem of Fe2 + concentration and Fe3 + concentration difficult to be detected in real time in goose feather iron process of a smelting enterprise, based on the production equipment and technology of Alto Quintiles, the improved least squares support vector machine model has the advantages of small samples Linear prediction, process neural network can fully express the characteristics of time accumulation in historical data series, and propose an integrated forecasting model based on information entropy method.The simulation results show that the integrated forecasting model has good predictive performance and the forecasting effect can satisfy the needles of iron Error Requirement of Ferric Ion Concentration Value in Mining Process of Iron Deposit.