A multi-layer perceptron-based swarm drone performance testing method

Abstract

The application relates to a multi-layer perception-based swarm UAV performance test method, and belongs to the technical field of UAV testing. The method solves the problem that the performance test result is inaccurate due to the single UAV test parameter and the inability to evaluate dynamic performance in the prior art. The method comprises the following steps: constructing a test scene, respectively performing support test, emergence test and efficiency test on the UAV swarm, and collecting original data of support parameters, emergence parameters and efficiency parameters; comprehensively evaluating the support parameters by using a dynamic grey analytic hierarchy process to generate a support comprehensive score; calculating an emergence comprehensive score based on the emergence parameters; wherein the emergence parameters comprise the number of node failures, formation reconstruction time and communication delay time; inputting the efficiency parameters into a pre-trained efficiency prediction model to predict an efficiency comprehensive score; and inputting the support comprehensive score, the emergence comprehensive score and the efficiency comprehensive score into a multi-layer perception model to obtain a performance evaluation result.