• CN:11-2187/TH
  • ISSN:0577-6686

机械工程学报 ›› 2025, Vol. 61 ›› Issue (2): 36-45.doi: 10.3901/JME.2025.02.036

• 仪器科学与技术 • 上一篇    

扫码分享

基于多源数据密度估计自编码器的液体火箭发动机无监督异常检测

刘莘1, 王珺2, 陈景龙1, 刘子俊2   

  1. 1. 西安交通大学精密微纳制造技术全国重点实验室 西安 710049;
    2. 西安航天动力研究所 西安 710100
  • 收稿日期:2024-01-25 修回日期:2024-08-11 发布日期:2025-02-26
  • 作者简介:刘莘,男,1998年出生,博士研究生。主要研究方向为异常检测与故障诊断。E-mail:sliu7102@163.com;陈景龙(通信作者),男,1985年出生,博士,教授,博士研究生导师。主要研究方向为设备状态监测与智能诊断、装备运行可靠性与安全维护、智能制造、大数据分析与质量控制。E-mail:jlstrive2008@163.com
  • 基金资助:
    国家自然科学基金(52275129)和中央高校基本科研业务费(xzy022023062)资助项目。

Unsupervised Anomaly Detection for Liquid Rocket Engines with Multi-source Data Density Estimation Autoencoder

LIU Shen1, WANG Jun2, CHEN Jinglong1, LIU Zijun2   

  1. 1. State Key Laboratory for Manufacturing Systems Engineering, Xi'an Jiaotong University, Xi'an 710049;
    2. Xi'an Aerospace Propulsion Institute, Xi'an 710100
  • Received:2024-01-25 Revised:2024-08-11 Published:2025-02-26

摘要: 液体火箭发动机热试车试验是发动机制造交付过程中的关键环节,基于热试车试验开展高准确性异常检测是保障发动机安全可靠运行及载人登月任务顺利执行的重要手段。针对发动机多部件运行状态响应相互叠加干扰且非线性系统多部件差异退化趋势导致的异常识别误报率、漏报率高的技术难题,基于液体火箭发动机健康运行状态监测数据,提出多源数据密度估计自编码器的无监督异常识别方法。利用微观单元特征嵌入与全局结构化信息建模的编码器学习细粒度特征表示,然后通过解码器进行重建以学习健康状态数据分布。同时,通过高斯混合密度估计网络约束促使自编码器实现更好的特征表示与信息重建。最后,构建基于数据特征空间表示与数据分布的双重尺度下的异常检测评估分数,定义了液体火箭发动机健康状态运行下的正常情形约束边界,最终实现了多源监测数据下的发动机整机系统级异常智能检测。同型号及跨型号下液体火箭发动机地面热试车试验多源数据异常检测任务结果证明了所提方法的有效性和优越性。

关键词: 异常检测, 液体火箭发动机, 无监督学习, 自编码器

Abstract: Liquid rocket engine hot fire tests represent a pivotal phase in the engine manufacturing and delivery process. Conducting high-accuracy anomaly detection during hot fire tests is a crucial method to ensure the secure and dependable operation of the engine, as well as the successful execution of manned lunar missions. To address the technical challenges associated with the high false positive and false negative rates in anomaly detection caused by the interference of multiple component operational responses and the nonlinear system with differential degradation trends among engine components, an unsupervised learning method of multi-source data density estimation autoencoder is proposed based on liquid rocket engine health operation status monitoring data. Fine-grained feature representations are learned using micro patch feature embedding with a global structured information modeling encoder, and then reconstructed by a decoder to learn health state data distributions. Meanwhile, utilizing gaussian mixture density estimation network constraints enables the autoencoder to achieve improved feature representation and information reconstruction. Finally, the anomaly detection evaluation score based on the dual scales of data feature space representation and data distribution is constructed, the normal situation constraint boundaries under the healthy state operation of the liquid rocket engine are defined, and the intelligent detection of anomalies at the engine system level under the multi-source monitoring data is finally realized. The results of the multi-source data anomaly detection task for the ground thermal test of liquid rocket motors under the same type and across types prove the effectiveness and superiority of the proposed method.

Key words: anomaly detection, liquid rocket engines, unsupervised learning, autoencoder

中图分类号: