宇航学报 ›› 2022, Vol. 43 ›› Issue (7): 964-973.doi: 10.3873/j.issn.1000-1328.2022.07.013

• 推进技术与动力 • 上一篇    下一篇

数据驱动的运载火箭氧涡轮泵异常分析方法

王冠,王婧雨,刘巧珍,宋征宇   

  1. 1. 北京宇航系统工程研究所,北京 100076; 2. 中国运载火箭技术研究院,北京 100076
  • 收稿日期:2021-10-19 修回日期:2022-02-21 出版日期:2022-07-15 发布日期:2022-07-15
  • 基金资助:
    民用航天“十三五”技术预先研究项目

Data driven Anomaly Analysis Method of Launch Vehicle Oxygen Turbopump

WANG Guan, WANG Jingyu, LIU Qiaozhen, SONG Zhengyu   

  1. 1.Beijing Institute of Astronautical Systems Engineering, Beijing 100076, China;2.China Academy of Launch Vehicle Technology, Beijing 100076, China
  • Received:2021-10-19 Revised:2022-02-21 Online:2022-07-15 Published:2022-07-15

摘要: 基于模糊聚类和LSTM网络,提出了一种数据驱动的运载火箭发动机氧涡轮泵数据异常分析方法。通过模糊聚类对工况复杂,标签不完整的数据样本进行预分类,得到完整的标签并且分析特征贡献度,为LSTM网络的特征筛选和训练打下基础;通过LSTM网络对氧涡轮泵数据进行预测,并计算预测结果与原始数据之间的平均误差,再根据非参数阈值计算方法计算的阈值判据来判断设备是否异常,最终实现了氧涡轮泵数据驱动的故障检测报警,相较于红线阈值检测方法准确率提升7%。

关键词: 火箭发动机, 故障检测, 氧涡轮泵, 模糊聚类, 长短期记忆网络

Abstract: Based on fuzzy clustering and LSTM network, a data driven anomaly analysis method of launch vehicle engine oxygen turbopump data is proposed. Firstly, fuzzy clustering is used to pre classify the data samples with complex working conditions and incomplete labels to obtain complete labels and analyze the feature contribution, which lays a foundation for feature screening and training of LSTM network. The LSTM network is used to predict the data of the oxygen turbopump, and the average error between the predicted results and the original data is calculated. Then the threshold criterion calculated by the non parametric threshold calculation method is used to determine whether the turbopump is abnormal. Finally, the fault detection and alarm driven by the oxygen turbopump data are realized, and the accuracy is improved by 7% compared with the red line threshold detection method.

Key words: Launch vehicle engine, Anomaly detection, Oxygen turbopump, Fuzzy clustering, LSTM networks

中图分类号: