Simulation model evaluation method and device

Abstract

The invention discloses a simulation model evaluation method and device, and the method comprises the steps: extracting feature points of output data and reference data of a simulation model by a feature point extraction algorithm suitable for multi-dimensional data, so as to compress the size of the reference data as much as possible; and performing incremental clustering on the reference data toform a reference data rule and establish a topological network structure of the reference data, determining a simulation model evaluation index according to the topological network structure, and evaluating a simulation result of the simulation model according to the evaluation index. The technical problems of long evaluation process and low efficiency of a simulation model in the prior art are solved.

Description

technical field [0001] The present application relates to the technical field of model evaluation, in particular to a simulation model evaluation method and device. Background technique [0002] Simulation models are generally used to simulate the composition and operation of complex systems. Since the simulation model is not completely equal to the actual model, there is a certain difference between the output data of the simulation model after the system simulation and the output data of the actual model, so it is necessary to verify the credibility of the output data of the simulation model. [0003] At present, the traditional method of verifying the credibility of the output data of the simulation model is to verify and evaluate through verification, validation and accreditation (VV&A). The process is: directly compare the output data of the simulation model with the The reference data is compared numerically, and the credibility of the simulation model is determined a...

AI Technical Summary

Problems solved by technology

[0004] The technical problem solved by this application is: Aiming at the problem of poor accuracy of the evaluation results of the simulation model in the prior art, it provides an evaluation method of the simulation model and device, in the solution provided by the embodiment of the present application, not only the output data set and the reference data set of the simulation model are compressed through the preset feature point extraction algorithm to obtain the compressed output data set and the compressed reference data set, The amount of output data and reference data is reduced, thereby reducing the amount of calculation in the simulation model evaluation process and improving the efficiency of simulation model evaluation; the incremental clustering model is also used to construct the compressed reference data set. The topological network structure between the reference data, which determines the internal laws between the reference data, and realizes the automatic evaluation of the credibility of the simulation model according to the internal laws between the reference data, which improves the automation performance of the simulation model evaluation

Images