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OA
A deep learning-based method for fault diagnosis of solid rocket motor ground test systems
固体火箭发动机地面试验系统的故障诊断对于试验数据分析与状态评估有重要意义.为实现地面试验系统故障的自动诊断,文章提出一种融合条件生成对抗网络(CGAN)与长短期记忆网络-自注意力机制(LSTM-Transformer)的诊断方法.首先,基于真实故障信号,利用 CGAN 对数据进行增强;然后基于增强后的数据集,利用 LSTM-Transformer 模型对异常信号进行检测和分类.多个类别故障信号的检测实验结果表明,在满足工程实时性要求的前提下,所提方法较传统方法的检测准确率提高了8.59%,且模型具有较好的鲁棒性和泛化能力,在固体火箭发动机地面试验中具备良好的应用前景.
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.
孙旭阳;高永刚;邓伟锋;王卓凡;姚怡倩
西安航天动力测控技术研究所西安航天动力测控技术研究所西安航天动力测控技术研究所西安航天复合材料研究所:西安 710025西安航天动力测控技术研究所
航空航天
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
solid rocket motorground test systemfault diagnosissensor signalsdata augmentationdeep learning
《航天器环境工程》 2026 (2)
148-160,13
评论