现代防御技术 ›› 2025, Vol. 53 ›› Issue (5): 215-226.DOI: 10.3969/j.issn.1009-086x.2025.05.022

• 仿真技术 • 上一篇    

改进鸽群优化的随机森林无人机传感器故障预测技术

刘媛媛, 袁荣, 邵书义, 陈谋   

  1. 南京航空航天大学 自动化学院,江苏 南京 211106
  • 收稿日期:2024-07-17 修回日期:2024-09-02 出版日期:2025-10-28 发布日期:2025-11-03
  • 通讯作者: 邵书义
  • 作者简介:刘媛媛(2000-),女,湖北宜昌人。硕士生,研究方向为故障诊断与容错控制。
  • 基金资助:
    国家自然科学基金联合基金重点支持项目(U2013201)

Fault Prediction Technology for UAVs Sensor Based on Random Forest Improved by Pigeon-Inspired Optimization

Yuanyuan LIU, Rong YUAN, Shuyi SHAO, Mou CHEN   

  1. College of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
  • Received:2024-07-17 Revised:2024-09-02 Online:2025-10-28 Published:2025-11-03
  • Contact: Shuyi SHAO

摘要:

无人机传感器故障预测对于提高系统可靠性和安全性具有重要意义,然而,当前预测方法存在准确性不足和计算复杂度高等问题。针对无人机传感器故障预测问题,研究了一种基于改进鸽群算法(pigeon-inspired optimization,PIO)的随机森林故障预测算法。利用小波包变换(wavelet packet transform,WPT)对故障特征进行提取。利用莱维飞行机制形成变异机制以提高种群的多样性,进而改善PIO易陷入局部最优的问题,并提高算法收敛速度和全局寻优能力。将改进的PIO用于随机森林算法中使其进行自主超参数优化,从而实现传感器故障的早期预测。仿真结果表明,经过改进PIO调优后的随机森林算法收敛速度更快,相较于传统算法在准确率上提升了20%以上,表明了提出的算法在无人机传感器故障预测中的有效性和优越性。

关键词: 小波包变换, 改进鸽群算法, 随机森林, 莱维飞行, 无人机传感器故障

Abstract:

The prediction of UAV sensor faults is of great significance for improving system reliability and safety. However, current prediction methods suffer from insufficient accuracy and high computational complexity. To address this issue, this study proposed a random forest fault prediction algorithm based on improved pigeon-inspired optimization (PIO). The wavelet packet transform (WPT) was employed to extract fault features, and the Levy flight mechanism was introduced to form a mutation mechanism to enhance population diversity, thereby alleviating the problem of PIO easily falling into local optima and enhancing both the convergence speed and global optimization ability of the algorithm. The improved PIO was then applied to the random forest algorithm to achieve autonomous hyperparameter optimization, enabling early prediction of sensor faults. Simulation results show that the random forest algorithm optimized by the improved PIO converged faster and achieved an accuracy improvement of more than 20% compared with traditional algorithms, indicating the effectiveness and superiority of the proposed method in UAV sensor fault prediction.

Key words: wavelet packet transform(WPT), improved pigeon-inspired optimization(PIO), random forest, Levy flight, drone sensor fault

中图分类号: