Abstract:

Aiming at the problem of autonomous positioning of plume source in 3D space, this paper introduces the historical data mechanism and proposes an autonomous positioning strategy based on the cuckoo search algorithm combined with the improved fuzzy C-means clustering algorithm. The cuckoo search algorithm is used to generate the position information of the robot positioning, which avoids the blindness of the robot collecting the plume concentration and realizes the autonomy of the positioning. The generated position information and the collected smoke plume concentration at the position constitute the feature vector, and the improvement is adopted. The fuzzy C-means clustering algorithm clusters a new set of eigenvectors composed of the eigenvectors and historical eigenvectors to obtain a three-dimensional space plume concentration distribution area, which provides a search range for the cuckoo search algorithm. The proposed method is verified by an example and compared with the positioning algorithm of the last two years. The results show that the method is better than the two-year positioning algorithm in terms of average running time and convergence precision, and can average 0.1450 meters. The convergence accuracy is autonomously located near the plume source, providing a methodological support for the plume source location.

Key words: autonomous positioning, cuckoo search, fuzzy C-means, cluster analysis, convergence accuracy

摘要：

针对三维空间鲜有人研究烟羽源自主定位的问题，引入利用历史数据机制，提出了布谷鸟搜索算法结合改进的模糊C均值聚类算法的自主定位策略。采用布谷鸟搜索算法产生机器人定位的位置信息，避免了机器人采集烟羽浓度的盲目性，实现了定位的自主性。将产生的位置信息及采集的该位置处烟羽浓度构成特征向量，采用改进的模糊C均值聚类算法对该组特征向量和历史特征向量构成的一组新的特征向量聚类分析，获取三维空间烟羽浓度分布区域，为布谷鸟搜索算法提供了搜索范围。通过实例对所提出的方法进行验证，并与最近两年的定位算法进行对比，结果表明：该方法在平均运行时间和收敛精度方面均优于最近两年的定位算法，且能够以平均0.145 0 m的收敛精度自主定位到烟羽源附近，为烟羽源定位提供了方法支持。

关键词: 自主定位, 布谷鸟搜索, 模糊C均值, 聚类分析, 收敛精度