Aircraft Wing Digital Twin Model Validation Test Program Design
Digital twins have gradually become a research focus in military simulation in recent years.In order to ensure the credibility of the digital twin model,validation tests are crucial.The weight of the wing of a certain type of existing aircraft is affected by several factors,and according to its digital twin model,some test data are generated by simulation,and the two methods of non-parametric regression based on Gaussian process and parametric regression based on particle swarm algorithm are used to construct a model of the influence of these factors on the weight of the wing.A method of determining the sample size of validation test based on the Bayesian-based modified power prior is put forward.A test design method based on the particle swarm algorithm is proposed,which prevents the test design from falling into the local optimal solution.Finally,experiments are carried out in combination with cases,and the results verify the effectiveness of the above methods.
digital twinmodel credibilityexperimental designparticle swarm algorithmsample size calculation