基于模糊聚类和专家评分机制的无人机多层次模块划分方法  

Multi-level module partition method of UAV based on fuzzy clustering and expert scoring mechanism

作　　者：杨建峰 肖和业[3] 李亮 白俊强[3] 董维浩 YANG Jianfeng;XIAO Heye;LI Liang;BAI Junqiang;DONG Weihao(School of Aeronautic,Northwestern Polytechnical University,Xi’an 710072,China;Unit 95889 of the PLA,Jiuquan 735018,China;Unmanned System Technology Research Institute,Northwestern Polytechnical University,Xi’an 710072,China)

机构地区：[1]西北工业大学航空学院,陕西西安710072 [2]中国人民解放军95889部队,甘肃酒泉735018 [3]西北工业大学无人系统技术研究院,陕西西安710072

出　　处：《系统工程与电子技术》2022年第8期2530-2539,共10页Systems Engineering and Electronics

摘　　要：本文基于初步划分-综合评价-精准划分的多层次递进模块划分架构,为模块化无人机设计中模块划分提供可信、有效的方法。以提升模块划分结果的可信度为目标,在模块划分指标评价中引入基于专家信度的评分机制,形成了基于模糊聚类和专家评分机制的多层次模块划分方法。以一次性、可重复使用无人机为例,采用本文提出的模块划分方法,进行零部件聚类并形成模块划分方案。由模块划分结果可知,本文模块划分方法可对不同模式的无人机获得符合其使用特点、可信的模块划分方案,进而验证了方法的合理性和有效性。Based on the multi-level progressive module partition architecture of preliminary partition-comprehensive evaluation-precision partition, this paper provides a credible and effective method for module partition in modular unmanned aerial vehicle(UAV) design. In order to improve the credibility of the results of module partition, a scoring mechanism using expert reliability is introduced in the evaluation of module partition indicators. A multi-level module partition method is presented by applying fuzzy clustering and expert scoring mechanism. Taking the one-time and reusable UAVs as examples, the proposed module partition method is adopted to cluster the components and form a module partition scheme. Through the results of the module partition, it can be seen that the proposed method can provide a reliable module partition scheme and satisfy their application characteristics for different kinds of UAVs. Therefore, the rationality and effectiveness of the method is further verified.

关 键 词：模块化无人机 模块划分方法 模糊聚类 专家信度 网络层次结构 粒子群优化算法 

分 类 号：V279[航空宇航科学与技术—飞行器设计] TB472[一般工业技术—工业设计]