高炉料面的分类与案例匹配算法

发布时间：2018-04-19 02:29

本文选题：高炉 + 料面　；参考：《控制理论与应用》2017年03期

【摘要】：本文基于改进的k-means算法及分级案例库匹配技术提出一种研究高炉料面和煤气流关系的方法.为了获取煤气流分布情况,首先提出了改进的基于新型有效性指标评价的k-means算法,并将该算法与其它多种算法进行比较,证明了该方法的高效性和准确性.继而在此基础上提出了案例库匹配技术,从而获得与当前料面最为匹配的历史料面.最后,将匹配算法与改进的灰色相似性匹配算法和欧式近邻匹配算法进行比较.结果表明,分级匹配算法具有更高的分辨率和效率.在多次试验中匹配准确率高达92.5%,比其他几种算法更加准确,更适合研究料面与煤气流关系,指导布料操作.
[Abstract]:Based on the improved k-means algorithm and the hierarchical case base matching technique, this paper presents a method to study the relationship between the charging surface and the gas flow.In order to obtain the distribution of gas flow, an improved k-means algorithm based on the evaluation of new validity index is proposed, and compared with other algorithms, the efficiency and accuracy of the method are proved.Then, the case base matching technology is proposed to obtain the historical material surface that is the best match with the current material surface.Finally, the matching algorithm is compared with the improved grey similarity matching algorithm and the Euclidean nearest neighbor matching algorithm.The results show that the hierarchical matching algorithm has higher resolution and efficiency.In many experiments, the matching accuracy is up to 92.5, which is more accurate than other algorithms, and is more suitable for studying the relationship between material surface and gas flow and guiding the operation of cloth.
【作者单位】：北京科技大学自动化学院;
【基金】：国家自然科学基金重点项目(61673056,61333002,61673055)资助~~
【分类号】：TF54;TP301.6

【相似文献】