摘要
为降低高炉生产焦炭的消耗,对高炉操作参数和燃料比指标进行关联性分析,提出了一种组合聚类分析与神经网络进行高炉焦比指标预测的方法。聚类分析将数据集聚划分为几类,数据的相似度比较高,分类训练相应的神经网络模型,实现高炉焦比指标的预测。结合聚类分析构建的神经网络模型,用某高炉生产数据进行仿真学习,并跟传统的神经网络模型进行比较。结果表明,加入聚类分析的神经网络模型平均绝对误差降低3.13 kg/t,平均相对误差降低5.19%。
In order to reduce the coke consumption of blast furnace, a relevance analysis is carried out for operation parameters and fuel ratio of blast furnce, and a prediction method that is combining clustering analysis and neural network for coke ratio of blast furnace is proposed. The data cluster is divided into seveval classes by clustering analysis, the data similarity is high, and the neural network model is used to realize the prediction of coke ratio. By combining the neural network with clustering analysis, the data in one blast furnace is simulated, and the results are compared with the traditional neural network model. The results show that the improved neural network has a higher accuracy, the average absolute error can be decreased by 3.13 kg/t, and the average relative error can be decreased by 5.19%.
出处
《辽宁科技大学学报》
CAS
2010年第3期245-247,257,共4页
Journal of University of Science and Technology Liaoning
关键词
聚类分析
神经网络
预测
高炉
焦比
clustering
neural network
prediction
blast furnace
coke ratio
