摘要
生物或者物体由于集群属性形成的群体行为常见于自然界中,群体行为研究有助于人类深入地了解自然界,并为智能集群控制提供理论指导。鱼群个体交互作用可以促使相邻鱼体共享信息,从而提高鱼类洄游成功率。本研究在自主搭建的仿生态鱼道下进行鱼类上溯行为实验,通过设置半圆形障碍物营造低湍动流场,开展鱼类个体及鱼群上溯实验。基于YOLOv5算法捕获不同流速条件下鱼群高精度鱼类运动轨迹,结合数模计算结果获取水力指标。跟踪鱼类在实验区域中的被动游泳行为,统计每种交互行为的特征参数。结合行为发生位置的水力指标,综合得出鱼类上溯全程运动策略与感知流场之间的响应关系。通过对鱼类交互行为、流场偏好度、边壁影响的分析,基于最小势能原理建立鱼群二维集群规则模型。本研究结果对解构鱼类在特定洄游场景中的动态上溯过程具有一定帮助,为流场中鱼类行为模式的刻画奠定了基础,为鲤科鱼类的交互运动提供了量化指标体系,可应用于鱼类游泳能力测试、上溯行为解构等具体行为场景,并为未来无人机集群编队设计和控制提供启发与帮助。
Group behaviors formed by organisms or objects due to cluster properties are common in nature.The study of group behavior helps human beings to deeply understand the natural world and provides theoretical guidance for intelligent cluster control.Individual interactions of fish schools can induce neighboring fish bodies to share information,thus improving the success rate of fish migration.In this study,fish upstream behavior experiments were carried out under the self-constructed ecological fish passage,and individual and school upstream experiments were carried out by setting semicircular obstacles to create a low-turbulence flow field.Based on the YOLOv5 algorithm,we captured the high-precision fish movement trajectories of the fish group under different flow conditions,and combined them with the results of numerical modeling to obtain hydraulic indicators.Track the passive swimming behavior of fish in the experimental area,and count the characteristic parameters of each interaction behavior.Combined with the hydraulic indicators at the location where the behaviors occurred,the response relationship between the movement strategy of the fish throughout the upstream journey and the perceived flow field was comprehensively derived.Through the analysis of fish interaction behaviors,flow field preference,and the influence of sidewalls,a two-dimensional cluster rule model of the fish population was established based on the principle of minimum potential energy.The results of this study are helpful in deconstructing the dynamic upstream process of fish in specific migratory scenarios.It will provide a system of quantitative indexes for the interactive movement of carp,which can be applied to specific behavioral scenarios such as the test of the swimming ability of fish,the deconstruction of upstreaming behaviors,and also provides inspiration for the design and control of future robotic swarming formations.
作者
周易
陈建
韩宇
张悦
贾凤聪
ZHOU Yi;CHEN Jian;HAN Yu;ZHANG Yue;JIA Fengcong(College of Water Resources and Civil Engineering,China Agricultural University,Beijing 100083,China;College of Engineering,China Agricultural University,Beijing 100083,China)
出处
《航空学报》
EI
CAS
CSCD
北大核心
2023年第S02期469-478,共10页
Acta Aeronautica et Astronautica Sinica
基金
兵团科技计划项目灌区高含沙渠道雷达测流关键技术研究及示范(2023AB060)
国家自然科学基金(51979275)
西北内陆河流域水系连通综合治理关键技术研究(202305510910168)
清华大学-宁夏银川水联网数字治水联合开放基金资助项目(sklhse2022-Iow08)
塔里木大学-中国农业大学联合基金(ZNLH202205)
关键词
鱼类集群
仿生算法
圆柱绕流
鱼类洄游
生态鱼道
fish schooling
bionic algorithms
columns
fish migration
ecological fish passage
