基于极限学习神经模糊系统的多旋翼无人机执行器故障检测与隔离。

Actuator fault detection and isolation on multi-rotor UAV using extreme learning neuro-fuzzy systems.

机构信息

Air Traffic Management Research Institute, Nanyang Technological University, 637460, Singapore.

School of Mechanical and Aerospace Engineering, Nanyang Technological University, 639798, Singapore.

出版信息

ISA Trans. 2023 Jul;138:168-185. doi: 10.1016/j.isatra.2023.02.026. Epub 2023 Feb 27.

DOI:10.1016/j.isatra.2023.02.026

PMID:36906441

Abstract

Undetected partial actuator faults on multi-rotor UAVs can lead to system failures and uncontrolled crashes, necessitating the development of accurate and efficient fault detection and isolation (FDI) strategy. This paper proposes a hybrid FDI model for a quadrotor UAV that integrates an extreme learning neuro-fuzzy algorithm with a model-based extended Kalman filter (EKF). Three FDI models using Fuzzy-ELM, R-EL-ANFIS, and EL-ANFIS are compared based on training, validation performances, and sensitivity to weaker and shorter actuator faults. They are also tested online for linear and nonlinear incipient faults by measuring their isolation time delays and accuracies. The results show that the Fuzzy-ELM FDI model exhibits greater efficiency and sensitivity, while Fuzzy-ELM and R-EL-ANFIS FDI models demonstrate better performance than a conventional neuro-fuzzy algorithm, ANFIS.

摘要

多旋翼无人机上未被检测到的部分执行器故障会导致系统故障和失控坠毁，因此需要开发准确和高效的故障检测和隔离（FDI）策略。本文提出了一种四旋翼无人机的混合 FDI 模型，该模型将极限学习神经模糊算法与基于模型的扩展卡尔曼滤波器（EKF）相结合。基于训练、验证性能以及对较弱和较短执行器故障的敏感性，比较了三个使用模糊 ELM、R-EL-ANFIS 和 EL-ANFIS 的 FDI 模型。还通过测量它们的隔离时滞和准确性，在线测试了它们对线性和非线性初始故障的性能。结果表明，模糊 ELM FDI 模型具有更高的效率和敏感性，而模糊 ELM 和 R-EL-ANFIS FDI 模型的性能优于传统的神经模糊算法 ANFIS。