Performance Map Construction for a Centrifugal Diffuser with Data Mining Techniques
Performance Map Construction for a Centrifugal Diffuser with Data Mining Techniques
复制标题
DOI：
10.1299/jcst.4.36
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
K. Shimoyama;K. Sugimura;Shinkyu Jeong;S. Obayashi
中科院分区：
文献类型：
--
作者：
K. Shimoyama;K. Sugimura;Shinkyu Jeong;S. Obayashi
性能图表示性能与几何参数之间的关系，对于工程师对要设计的产品初步规格做出初步决策至关重要。然而，实际设计往往需要同时考虑各种性能和几何参数。因此，生成的性能图必须以高维形式构建。基于这些要求，本文提出并演示了借助数据挖掘技术构建性能图。数据挖掘能够揭示包含性能和几何参数的高维数据中的特征模式。因此，数据挖掘结果便于解释性能与几何关系的复杂特征，并帮助工程师通过解释发现工程设计的新知识。对离心式扩压器的当前演示表明，数据挖掘技术适用于高维性能图构建，并且实际获取了从传统准一维喷管理论中未知的扩压器设计新知识。
Performance maps, which represent relations between performance and geometry parameters, are essential for engineers to make a first decision on preliminary specification of a product to be designed. However, actual design often needs to consider various performance and geometry parameters simultaneously. Therefore, the resulting performance maps must be constructed in a high-dimensional form. Based on these requirements, this paper proposes and demonstrates performance map construction with the aid of data mining techniques. Data mining can reveal characteristic patterns in high-dimensional data with performance and geometry parameters. Therefore, the data mining results make it easy to interpret complex features of performance vs. geometry relations, and help engineers to discover new knowledge for engineering design through interpretation. The present demonstration of a centrifugal diffuser demonstrated that the data mining techniques are suitable and applicable to high-dimensional performance map construction, together with actual acquisition of new knowledge for diffuser design that was unknown from conventional quasi-one-dimensional nozzle theory.