基于主从加权灰色关联的模型综合一致性检验

Study on Comprehensive Consistency Test of Models Based on Double Weighted Gray Relational

为了全面检验仿真模型的一致性,提出了一种基于主从加权灰色关联的模型综合一致性检验方法。主加权过程依据各阶段的相对重要性对各个阶段赋权,分别计算各阶段的灰色关联度。从加权过程根据参考数据与行为序列数据之间的误差进行灰色关联系数的权值确定,最后进行综合一致性检验。同时,考虑了曲线之间的距离,减小了灰色关联模型验证的风险。最后,通过实例分析与比较验证了改进灰色关联度模型验证方法的有效性和实用性。

In order to improve quality of consistency test,a new relational model named double weighted gray relational was proposed. The first structure was main frame of the new model,in which the process of system was divided into many phases by its practical characteristics in work,and then different phases were weighted by its contribution to the whole system. The second weight was to improve the accuracy of model. Its weight was fixed by the distance of reference data and test data. By doing this,the new model was in view of the similarity by subtraction and the nearness by division between the simulation and flight-test time series,so it had higher accuracy and reliability. Finally,two case studies were given to show reasonability and validity of the improved model.