结合量子协同旅鼠算法与<italic style="font-style: italic">K</italic>-modes的航空数据聚类算法

贾深; 黄鹤; 高涛; 王会峰

doi:null

您当前的位置：

首页 >

文章列表页 >

结合量子协同旅鼠算法与K-modes的航空数据聚类算法

更新时间：2026-04-14

- 结合量子协同旅鼠算法与K-modes的航空数据聚类算法
- An Aviation Data Clustering Algorithm Combining the Quantum Collaborative Lemming Algorithm with K-modes
- 西安交通大学学报 2026年
- 作者机构：
  
  1.长安大学，电子与控制工程学院，710064，西安
  2.长安大学，智慧高速公路信息融合与控制重点实验室，710064，西安
- 作者简介：
- 基金信息：
- DOI：
  中图分类号： TP301.6
- 收稿：2026-01-16，
  
  修回：2026-04-13，
  
  录用：2026-04-14，
- 稿件说明：
移动端阅览
贾深, 黄鹤, 高涛, 等. 结合量子协同旅鼠算法与K-modes的航空数据聚类算法[J/OL]. 西安交通大学学报, 2026.

JIA Shen, HUANG He, GAO Tao, et al. An Aviation Data Clustering Algorithm Combining the Quantum Collaborative Lemming Algorithm with K-modes[J/OL]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY, 2026.
贾深, 黄鹤, 高涛, 等. 结合量子协同旅鼠算法与K-modes的航空数据聚类算法[J/OL]. 西安交通大学学报, 2026. DOI：

JIA Shen, HUANG He, GAO Tao, et al. An Aviation Data Clustering Algorithm Combining the Quantum Collaborative Lemming Algorithm with K-modes[J/OL]. JOURNAL OF XI’AN JIAOTONG UNIVERSITY, 2026. DOI：

摘要

低空经济的快速崛起催生了城市空中交通、无人机物流等新兴业态，航班运行状态的精准感知与延误风险的智能预判已成为民航安全运营的核心需求。针对低空经济背景下航空运行数据离散属性多、异构性强，以及

-modes聚类存在初始中心敏感、易陷入局部最优和复杂数据适应能力不足等问题，提出一种量子协同人工旅鼠算法优化的

-modes聚类算法。构建QCALA-

modes框架，将量子隧穿初始化引入聚类中心生成过程，并设计自适应步长扰动、多洞穴协同挖掘、量子混沌螺旋觅食和三模式切换逃逸4种策略，在能量因子调控下实现全局搜索与局部开发协同优化。框架中，每个旅鼠个体被编码为一组候选聚类中心，以簇内离散度倒数为适应度函数，通过迭代寻优驱动

-modes完成中心选取与样本划分的联合优化；能量因子随迭代进程自适应衰减，动态切换勘探与开发阶段，在收敛速度与解质量之间实现有效平衡。采用8个标准测试函数、6个公开数据集及和鲸社区539 383条航班数据进行验证。在公开数据集上，QCALA-

modes在Aggregation数据集上的归一化互信息（Normalized Mutual Information，NMI）为0.906 2，优于

means的0.839 5和层次聚类的0.901 0；在Bupa数据集上的NMI为0.138 4，高于

means的0.000 9和层次聚类的0.000 1；在Records数据集上的NMI为0.531 9。4类航班模式延误率簇间极差达到35.44%，有效区分了高低风险运营模式，验证了所提方法的聚类辨识力与业务可解释性；所识别的高延误干线、低风险长途、高风险短途枢纽及午后非枢纽四类模式与实际运营规律高度契合，可直接支撑航空公司差异化调度策略制定、机场容量动态分配及旅客延误预警服务，实现延误风险的精细化主动管控，可为低空经济场景中航空运行状态精细化识别与延误风险分级管控提供方法支撑。

Abstract

The rapid rise of the low-altitude economy has fostered emerging sectors such as urban air mobility and drone-based logistics. Accurate perception of flight operational status and intelligent prediction of delay risks have become core requirements for the safe and efficient operation of civil aviation. To address the challenges posed by aviation operational data in the context of the low-altitude economy—characterized by abundant discrete attributes and strong heterogeneity—as well as the inherent limitations of the

-modes clustering algorithm

including sensitivity to initial cluster centers

susceptibility to local optima

and insufficient adaptability to complex data distributions

this paper proposes a

-modes clustering method optimized by the Quantum Collaborative Artificial L

emming Algorithm (QCALA). A QCALA-

modes integration framework is constructed by introducing quantum tunneling initialization into the cluster center generation process and designing four behavioral optimization strategies: adaptive step-size perturbation

multi-burrow collaborative mining

quantum chaotic spiral foraging

and three-mode switching escape

thereby achieving dynamic co-optimization of global exploration and local exploitation under the regulation of an energy factor. Within the framework

each lemming individual is encoded as a set of candidate cluster centers

with the reciprocal of intra-cluster dispersion serving as the fitness function; iterative optimization drives

-modes to jointly optimize center selection and sample assignment. The energy factor decays adaptively with the progression of iterations

dynamically switching between exploration and exploitation phases to strike an effective balance between convergence speed and solution quality. The proposed method is validated using eight standard benchmark functions

six public datasets

and 539

383 flight records collected from the Heywhale Community. On the public datasets

QCALA-

modes achieves an NMI of 0.9062 on the Aggregation dataset

outperforming

means (0.8395) and hierarchical clustering (0.9010); on the Bupa dataset

its NMI reaches 0.1384

surpassing

means (0.0009) and hierarchical clustering (0.0001); on the Records dataset

the NMI is 0.5319. Experiments on aviation data demonstrate that the optimal clustering performance is obtained at

= 4

with the algorithm converging after 14 iterations. The delay rates of the four identified flight operation patterns are 49.51%

30.67%

66.11%

and 35.13%

respectively

yielding an inter-cluster range of 35.44%

which effectively differentiates high-risk from low-risk operational modes. These results validate the clustering discriminability and business interpretability of the proposed

method

The identified four modes—high-delay trunk routes

low-risk long-haul routes

high-risk short-haul hubs

and afternoon non-hub operations—are highly consistent with actual operational patterns. These modes can directly support the formulation of differentiated scheduling strategies for airlines

dynamic airport capacity allocation

and passenger delay warning services. This facilitates the precise and proactive management of delay risks. Moreover

it provides methodological support for the refined identification of aviation operation statuses and the tiered control of delay risks within low-altitude economic scenarios.

关键词

Keywords

references

黄鹤 , 马浩然 , 刘国权 , 等 . 采用局部-全局区域重检测机制的无人机长期跟踪算法 [J ] . 西安交通大学学报 , 2024 , 58 ( 06 ): 1 - 13 .

HUANG HE , MA HAORAN , LIU GUOQUAN , et al . Long-term tracking algorithm for drones employing local-global region re-detection mechanism [J ] . Journal of Xi'an Jiaotong University , 2024 , 58 ( 06 ): 1 - 13 .

MATTIEV J , DAVITYAN M , KAVSEK B . ACMKC: A Compact Associative Classification Model Using K-Modes Clustering with Rule Representations by Coverage [J ] . Mathematics , 2023 , 11 ( 18 ).

TEJA, S. G, SHARATH, P. Clustering categorical data: Soft rounding K-modes [J ] . Information and Computation , 2024 , 296 , 105115 .

SURYANARAYANA G , PRASAD L N C K , SENTHIL C P M , et al . Novel dynamic K-modes clustering of categorical and non-categorical dataset with optimized genetic algorithm based feature selection [J ] . Multimedia Tools and Applications , 2022 , 81 ( 17 ): 24399 - 24418 .

CHUNYING Z , RUIYAN G , JIAHAO W , et al . MD-SPKM: A set pair k-modes clustering algorithm for incomplete categorical matrix data [J ] . Intelligent Data Analysis ,202 1 , 25 ( 6 ): 1507 - 1524 .

黄鹤 , 黄佳慧 , 刘国权 , 等 . 采用混合策略联合优化的模糊C-均值聚类信息熵点云简化算法 [J ] . 西安交通大学学报 , 2024 , 58 ( 07 ): 214 - 226 .

HUANG H , HUANG J H , LIU G Q , et al . Fuzzy C-means clustering information entropy point cloud simplification algorithm based on joint optimization with hybrid strategy [J ] . Journal of Xi'an Jiaotong University , 2024 , 58 ( 7 ): 214 - 226 .

SUI J , TIAN Z , WANG Z . Multiple strategies improved spider wasp optimization for engineering optimization problem solving [J ] . Scientific Reports , 2024 , 14 ( 1 ): 29048 .

XIAO Y. , CUI H. , KHURMA A. R. , et al . Artificial lemming algorithm: a novel bionic meta-heuristic technique for solving real-world engineering optimization problems [J ] . Artificial Intelligence Review , 2025 , 58 ( 3 ): 84 - 96 .

NGUYEN L V H . Quantum Tunneling: History and Mystery of Large Amplitude Motions over a Century .[J ] . The journal of physical chemistry letters , 2024 , 16 ( 1 ): 104 - 113 .

黄鹤 , 李潇磊 , 杨澜 , 等 . 引入改进蝠鲼觅食优化算法的水下无人航行器三维路径规划 [J ] . 西安交通大学学报 , 2022 , 56 ( 07 ): 9 - 18 .

HUANG HE , LI XIAOLEI , YANG LAN , et al . Three-dimensional Path Planning for Underwater Unmanned Vehicles with Improved Batray Feeding Optimization Algorithm [J ] . Journal of Xi'an Jiaotong University , 2022 , 56 ( 07 ): 9 - 18 .

HU B , ZHU Y , TU L , et al . Equivalent Modeling with Passive Filter Parameter Clustering for Photovoltaic Power Stations Based on a Particle Swarm Optimization K-Means Algorithm [J ] . Energy Engineering , 2025 , 123 ( 1 ).

ZHOU R . Attack an image cipher algorithm combined new DNA operation with chaotic map [J ] . The European Physical Journal Plus , 2025 , 140 ( 9 ): 817 .

ALLAH R M R , Hassanien E A , Marafie A . An improved equilibrium optimizer for numerical optimization: A case study on engineering design of the shell and tube heat exchanger [J ] . Journal of Engineering Research , 2024 , 12 ( 2 ): 240 - 255 .

YANCHI Z , JIANHUA C , JING C , et al . Global-best brain storm optimization algorithm based on chaotic difference step and opposition-based learning [J ] . Scientific Reports , 2024 , 14 ( 1 ): 6432 .

ZHU Y , ZHANG W , WANG H , et al . An Improved Chaotic Quantum Multi-Objective Harris Hawks Optimization Algorithm for Emergency Centers Site Selection Decision Problem [J ] . Computers , Materials & Continua, 2025 , 82 ( 2 ): 21 77 - 2198 .

ALJEBREEN M , ALOHALI A M , MAHGOUB H , et al . Multi-Objective Seagull Optimization Algorithm with Deep Learning-Enabled Vulnerability Detection for Secure Cloud Environments [J ] . Sensors , 2023 , 23 ( 23 ): 9383

许德刚 , 王再庆 , 郭奕欣 , 等 . 鲸鱼优化算法研究综述 [J ] . 计算机应用研究 , 2023 , 40 ( 02 ): 328 - 336 .

XU D G , WANG Z Q , GUO Y X , et al . Review of whale optimization algorithm research [J ] . Application Research of Computers , 2023 , 40 ( 2 ): 328 - 336 .

黄鹤 , 李昕芮 , 吴琨 , 等 . 引入改进飞蛾扑火的K均值交叉迭代聚类算法 [J ] . 西安交通大学学报 , 2020 , 54 ( 09 ): 32 - 39 .

HUANG H , LI X R , WU K , et al . K-means cross-iterative clustering algorithm with improved moth-flame optimization [J ] . Journal of Xi'an Jiaotong University , 2020 , 54 ( 9 ): 32 - 39 .

DADGOSTAR S , DEHKORDI M P , KHODARAHMI S , etal . Automated HoneyBee Subspecies Identification Using Advanced Wing Venation Analysis and Adaptive Hierarchical Clustering [J ] . Ecology and evolution , 2025 , 15 ( 9 ): e72101 .

WANG C , FU A , LI W , et al . Intelligent Identification of Hidden Dangers in Hydrogen Pipeline Transmission Station Using GWO-Optimized Apriori Algorithm [J ] . Energies , 2024 , 17 ( 18 ): 1 - 15 .

SHARMA R , SHARMA K , BALA M . Efficient feature selection for histopathological image classification with improved multi-objective WOA [J ] . Scientific Reports , 2024 , 14 ( 1 ): 1 - 17 .

LONG T , JIANG Y , HUANG G , et al . An improved SSI method for structural parameter identification using MCKF-based denoising and DBSCAN-based clustering techniques [J ] . Structures , 2025 , 1 - 18 .

SHUDONG W , YU Z , YUANYUAN Z , et al . Graph attention autoencoder model with dual decoder for clustering single-cell RNA sequencing data [J ] . Applied Intelligence , 2024 , 54 ( 6 ): 5136 - 5146 .

ZHAOWEN L , JIE Z , FANG L , et al . Uncertainty measurement for single cell RNA-seq data via Gaussian kernel: Application to unsupervised gene selection [J ] . Engineering Applications of Artificial Intelligence , 2024 , 1 - 17

HEYWHALE . AIRLINE DATASET [Data set ] . HeyWhale Community. Retrieved August 5 , 2025 , from https://w ww .heywhale.com https://www.heywhale.com

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

EBSILON软件在热电联产系统优化中的应用综述

语义区分和子图整合驱动的知识图谱表示学习方法

结构-语义-残差协同的图像压缩框架：面向隐私保护与高保真重建

三塔合一间接空冷系统结构参数对夏季运行特性的影响研究

水蒸气掺混对氨裂解气旋流燃烧与排放特性的影响研究

结合量子协同旅鼠算法与K-modes的航空数据聚类算法

An Aviation Data Clustering Algorithm Combining the Quantum Collaborative Lemming Algorithm with K-modes

DOI：

摘要

Abstract

关键词

Keywords

references