曹芳菲, 朱怀石, 杜长坤, 路平立(通讯作者). 智能无人系统专辑+基于深度学习的高超声速飞行器执行器零样本故障辨识[J]. 工程科学学报. DOI: 10.13374/j.issn2095-9389.2023.09.27.001
引用本文: 曹芳菲, 朱怀石, 杜长坤, 路平立(通讯作者). 智能无人系统专辑+基于深度学习的高超声速飞行器执行器零样本故障辨识[J]. 工程科学学报. DOI: 10.13374/j.issn2095-9389.2023.09.27.001
Deep learning based actuator fault identification with hypersonic vehicles: A zero-shot case[J]. Chinese Journal of Engineering. DOI: 10.13374/j.issn2095-9389.2023.09.27.001
Citation: Deep learning based actuator fault identification with hypersonic vehicles: A zero-shot case[J]. Chinese Journal of Engineering. DOI: 10.13374/j.issn2095-9389.2023.09.27.001

智能无人系统专辑+基于深度学习的高超声速飞行器执行器零样本故障辨识

Deep learning based actuator fault identification with hypersonic vehicles: A zero-shot case

  • 摘要: 近年来,基于深度学习的故障诊断已经通过大量数据进行了深入的研究。然而,深度学习技术的巨大成功是基于可以获取大量带标签的训练样本的假设。在实际问题中,经常面临数据不平衡、未标记的数据太少或没有数据的情况。基于此,本文研究了高超声速飞行器在零样本情况下的故障辨识问题。“零样本”表示在训练过程中没有目标故障样本。针对这一特点,使用人工定义的故障描述来表征未知故障。具体而言,即利用关系网络学习将已知故障样本与定义的未知故障描述进行比较。进一步,为实现特征提取,结合卷积神经网络中及长短期记忆神经网络,构建深度神经网络结构。最后,通过在Winged-Cone (翼椎体)构型的高超声速飞行器上进行零样本故障辨识实验诊断执行器故障,证明在没有目标故障样本的情况下,可以完成对目标故障的诊断工作。

     

    Abstract: Deep learning based fault diagnosis has been investigated a lot via massive amount of data. In this paper, the fault identification problem is considered for hypersonic vehicles in the zero-shot case. ``Zero-shot'' indicates that target fault samples are not available in the training process. To tackle this challenge, the fault description by human-defined is used to characterize the unknown fault. Specifically, a relation network is utilized which learns to compare the known fault samples against the defined unknown fault description. In the feature extraction, a deep neural network structure is constructed by adding long and short term memory neural network to the convolution neural networks. The zero-sample fault identification experiments are carried out on a hypersonic vehicle with Winged-Cone configuration to diagnose actuator fault. The results show that it is indeed possible to diagnose target faults without their samples.

     

/

返回文章
返回