论文部分内容阅读
铁水温度是高炉冶炼过程的关键参数,是影响高炉稳定顺行及节能降耗的重要指标。以高炉炉内热状态的重要指示剂-铁水温度为研究对象,在综合利用K-means聚类和支持向量机方法的各自优势和互补情况下,提出一种基于K-means聚类的支持向量机预测铁水温度的方法,该方法首先将训练样本数据分为m类,建立m个支持向量机回归预测模型,同时采用粒子群算法优化模型参数;其次建立m个判别函数,判别待预测样本数据属于哪一类;最后将待预测样本数据代入相应类的回归模型中进行预测。相比标准支持向量机预测,得到了较高的预测精度。
The temperature of hot metal is the key parameter in blast furnace smelting process, which is an important index that affects the stability of blast furnace and energy saving. Taking hot metal temperature, which is an important indicator of thermal state in blast furnace, as the research object, under the condition of comprehensive utilization of K-means clustering and support vector machine method respectively, a K-means clustering-based support vector machine Firstly, the training sample data is classified into m classes, and m support vector machine regression prediction models are established. At the same time, particle swarm optimization is used to optimize the model parameters. Secondly, m discriminant functions are established to determine whether the sample data to be predicted belongs to Which type; Finally, the data to be predicted sample into the corresponding regression model to predict. Compared with standard SVM prediction, higher prediction accuracy is obtained.