Research on Module-level Fault Diagnosis of Avionics System Based on Residual Convolutional Neural Network
Yuhang Huang1Linlin Shi2Yucheng Lu1
1. Guangzhou Institute of Technology,Xidian University2. The Fifth Electronics Research Institute of Ministry of Industry and Information Technology
摘要:This paper simulates the module-level soft fault signal of the avionics system by means of fault injection, selects the CPLD power supply voltage AC value as the analysis object, and samples through the sliding window to obtain the data set. Based on the residual neural network to improve,1*1 convolution and global average pooling layer are introduced. It is verified on the data set and compared with the traditional fully connected neural network and one-dimensional convolutional neural network. The experiment proves that the proposed fault diagnosis method based on residual convolutional neural network(Res-CNN) has achieved significant improvement.
会议名称:
2021年第四届算法、计算和人工智能国际会议
会议时间:
2021-12-22
会议地点:
中国海南三亚
- 专辑:
工程科技Ⅱ辑; 信息科技
- 专题:
航空航天科学与工程; 自动化技术
- DOI:
10.26914/c.cnkihy.2021.055305
- 分类号:
TP183;V267
引文网络
- 参考文献
- 引证文献
- 共引文献
- 同被引文献
- 二级参考文献
- 二级引证文献
相关推荐
- 相似文献
- 读者推荐
- 相关基金文献
- 关联作者
- 相关视频