摘要
常规灰色关联分析应用于仿真模型验证时,仅考虑了时间序列之间的相似性,忽略了时间序列之间的接近性,但这种接近却属于仿真模型的误差范畴,因此使用常规灰色关联分析进行仿真模型验证存在一定的风险,针对这一问题,提出了一种加权阵灰色关联度模型,综合了时间序列之间的相近性和相似性两个方面,因此提高了模型验证的准确性和可靠性,同时该模型可以同时处理具有多个特征行为的关联分析问题,给出了具体的基于加权灰色关联分析的模型验证的操作过程,并证明了改进模型满足灰色关联四定理。通过实例分析验证了改进模型的合理性和有效性。
When used to validation of simulation models,ordinary gray relational analysis(GRA) usually stresses the similarity but ignores the nearness between the simulation test time series and flight test time series,while the nearness is part of model error.To reduce the risk in application of GRA to validation of simulation models,a new matrix gray relational analysis was proposed,which was in view of the similarity and the nearness between the simulation test time series and flight test time series,so it had a higher accuracy and reliability.The new model could solve the relational analysis problem with many characteristics of behavior and the operational steps in details are listed.It is proved that the improved model satisfies the four grey relational axioms.A case study shows the reasonability and validity of the improved model.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2015年第6期1159-1164,1174,共7页
Journal of System Simulation
关键词
模型验证
加权阵灰色关联
灰色关联度
可信度
仿真
validation of simulation models
weight matrix gray relational analysis
gray relational degree
credibility
simulation