摘要
为了减少在参考输出完备时仿真模型选择的主观性,提出了基于主成分分析和灰色综合评判的仿真模型选择方法。依据数据特征将仿真输出分为静态、缓变和速变三类数据,并分别从多个方面充分刻画了各类数据之间的差异;基于主成分分析从多个相关的数据差异中提取出少数几个独立的主成分;利用灰色综合评判对主成分进行综合分析,进而得到仿真模型的选择结果。通过实例应用,表明了方法的有效性。
To reduce the subjectivity of result for selecting the simulation model when the reference output is complete, the selection method of simulation model based on principal component analysis and grey comprehensive evaluation was proposed. The simulation outputs were divided into three kinds of static data, gradual data and fast data according to the data feature, and the measure models of differences for each kind data were given. The correlation among the fea^tre differences was eliminated via principal component analysis, and several independent principal components were gained. The independent principal components were integrated based on grey comprehensive evaluation, and the selection result of simulation model was gained. In the application, the validity of the method is showed.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2016年第11期2677-2683,共7页
Journal of System Simulation
关键词
仿真模型选择
仿真模型可信性
主成分分析
灰色综合评判
selection of simulation model
credibility of simulation model
principal component analysis
grey comprehensive evaluation