基于1D-CNN 的卫星姿态控制系统故障诊断方法 |
| |
引用本文: | 闻 新. 基于1D-CNN 的卫星姿态控制系统故障诊断方法[J]. 兵工自动化, 2020, 39(7) |
| |
作者姓名: | 闻 新 |
| |
作者单位: | 南京航空航天大学航天学院,南京 210016 |
| |
摘 要: | 为解决卫星姿态控制系统中自主故障检测和诊断的问题,提出一种改进的1D-CNN 卫星姿态控制系统故障诊断方法。以卫星姿态控制系统的故障诊断为背景,构建航天器姿态动力学模型,将卷积神经网络(convolutionalneural network,CNN)与快速卷积算法相结合,对卷积神经网络的拓扑结构进行改进,根据BP 算法,将1 维原始数据作为输入,结合反作用飞轮作为执行机构的技术特征,给出一种基于卷积神经网络的故障检测和隔离方法。仿真结果验证了该方法对卫星姿态控制系统实时故障检测和分类的有效性。
|
关 键 词: | 故障诊断;卷积神经网络;航天器姿态控制系统;反作用飞轮 |
收稿时间: | 2020-02-19 |
修稿时间: | 2020-03-27 |
Fault Diagnosis Method of Satellite Attitude Control System Based on 1D-CNN |
| |
Abstract: | To solve the problem of autonomous fault detection and diagnosis in satellite attitude control system, animproved one-dimensional convolution neural network fault diagnosis method is proposed. Based on the fault diagnosis ofsatellite attitude control system, the attitude dynamics model of spacecraft is constructed. The convolutional neural network(CNN) is integrated with fast convolution algorithm, and the topology of convolutional neural network is improved.According to BP algorithm, a fault detection and isolation method based on convolution neural network is proposed, whichtakes one-dimensional raw data as input and combines the technical characteristics of reaction flywheel as actuator. Thesimulation results verify the validity of this method for real-time fault detection and classification of satellite attitudecontrol system. |
| |
Keywords: | fault diagnosis convolutional neural network spacecraft attitude control system reaction flywheel |
|
| 点击此处可从《兵工自动化》浏览原始摘要信息 |
|
点击此处可从《兵工自动化》下载免费的PDF全文 |