航天器环境工程2026，Vol.43Issue(2)：148-160,13.DOI:10.12126/see.2025122
基于深度学习的固体火箭发动机地面试验系统故障诊断方法
A deep learning-based method for fault diagnosis of solid rocket motor ground test systems
孙旭阳 1高永刚 1邓伟锋 1王卓凡 2姚怡倩1
作者信息
- 1. 西安航天动力测控技术研究所
- 2. 西安航天复合材料研究所:西安 710025
- 折叠
摘要
Abstract
Fault diagnosis of solid rocket motor ground test systems is crucial for test data analysis and status evaluation.To achieve automatic fault diagnosis,a method integrating a Conditional Generative Adversarial Network(CGAN)with a Long Short-Term Memory network and a self-attention mechanism(LSTM-Transformer)was proposed.First,real fault signals were augmented by CGAN.Then,based on the augmented dataset,an LSTM-Transformer model was developed to detect and classify abnormal signals.Experimental results on multiple types of fault signals showed that,while satisfying real-time engineering constraints,the proposed method improved detection accuracy by 8.59%compared with conventional methods.In addition,the model exhibited strong robustness and good generalization capability,indicating promising application prospects in solid rocket motor ground tests.关键词
固体火箭发动机/地面试验系统/故障诊断/传感器信号/数据增强/深度学习Key words
solid rocket motor/ground test system/fault diagnosis/sensor signals/data augmentation/deep learning分类
航空航天引用本文复制引用
孙旭阳,高永刚,邓伟锋,王卓凡,姚怡倩..基于深度学习的固体火箭发动机地面试验系统故障诊断方法[J].航天器环境工程,2026,43(2):148-160,13.
