A Hybrid-Driven Rule-Based System Towards Centralized Online Performance Assessment of Aircraft Swarms in an Open World

Multi-aircraft systems act as a typical physical entity of swarm intelligence, the advancement of which is definitely one of the most important indicators to measure the comprehensive strength of a country. Online performance assessment serves as the prerequisite for instant configuration adjustment of aircraft swarms, the informative results produced by which can provide strong decision support for the latter, thus facilitating the highperformance operation of aircraft swarms. However, most of the existing research in this area is carried out based on the assumption of a closed world, i.e., all the frames of discernment involved are presumed to be complete and exhaustive, which is not the case due to the unavoidable uncertainties in subjective cognition and objective environment. With this in mind, a novel centralized rule-based system is established for online assessing the undulant performance of aircraft swarms in an open circumstance, which is grounded in our preceding achievements, the extended belief rule base methodology, and the generalized evidence theory. The representation, acquisition, aggregation, and optimization of the rule base in the system are presented in turn. The advent of this system aims to promote the development of the data-knowledge hybrid-driven information processing paradigm.