Liquid rocket engine(LRE)fault diagnosis is critical for successful space launch missions,enabling timely avoidance of safety hazards,while accurate post-failure analysis prevents subsequent economic losses.However,th...Liquid rocket engine(LRE)fault diagnosis is critical for successful space launch missions,enabling timely avoidance of safety hazards,while accurate post-failure analysis prevents subsequent economic losses.However,the complexity of LRE systems and the“black-box”nature of current deep learning-based diagnostic methods hinder interpretable fault diagnosis.This paper establishes Granger causality(GC)extraction-based component-wise multi-layer perceptron(GCMLP),achieving high fault diagnosis accuracy while leveraging GC to enhance diagnostic interpretability.First,component-wise MLP networks are constructed for distinct LRE variables to extract inter-variable GC relationships.Second,dedicated predictors are designed for each variable,leveraging historical data and GC relationships to forecast future states,thereby ensuring GC reliability.Finally,the extracted GC features are utilized for fault classification,guaranteeing feature discriminability and diagnosis accuracy.This study simulates six critical fault modes in LRE using Simulink.Based on the generated simulation data,GCMLP demonstrates superior fault localization accuracy compared to benchmark methods,validating its efficacy and robustness.展开更多
Granger因果关系在时间序列建模中具有重要意义,但传统方法存在难以捕捉复杂非线性关系等诸多局限性。本文在相关工作的基础上提出GCGAN模型,首次将生成对抗网络应用于时间序列中的Granger因果关系发现。通过设计多头生成器的架构建模...Granger因果关系在时间序列建模中具有重要意义,但传统方法存在难以捕捉复杂非线性关系等诸多局限性。本文在相关工作的基础上提出GCGAN模型,首次将生成对抗网络应用于时间序列中的Granger因果关系发现。通过设计多头生成器的架构建模目标序列,在训练时对生成器施加稀疏诱导惩罚项,并在提取因果关系矩阵时引入阈值方法,GCGAN能够精准找寻高维时间序列中的复杂Granger因果关系。本研究为时间序列Granger因果关系发现提供了新的深度学习范式。Granger causality plays a significant role in time series modeling. However, traditional methods struggle with capturing complex nonlinear relationships among others limitations. Building on previous studies, this paper introduces the GCGAN model, marking the first application of Generative Adversarial Networks (GANs) to Granger causality discovery in time series. By designing a multi-head generator architecture to model target sequences, imposing sparse inducing penalties on the generator during training, and introducing a threshold method when extracting the causality matrix, GCGAN can accurately identify complex Granger causalities in high-dimensional time series. This study provides a novel deep learning paradigm for the discovery of Granger causality in time series.展开更多
文摘Liquid rocket engine(LRE)fault diagnosis is critical for successful space launch missions,enabling timely avoidance of safety hazards,while accurate post-failure analysis prevents subsequent economic losses.However,the complexity of LRE systems and the“black-box”nature of current deep learning-based diagnostic methods hinder interpretable fault diagnosis.This paper establishes Granger causality(GC)extraction-based component-wise multi-layer perceptron(GCMLP),achieving high fault diagnosis accuracy while leveraging GC to enhance diagnostic interpretability.First,component-wise MLP networks are constructed for distinct LRE variables to extract inter-variable GC relationships.Second,dedicated predictors are designed for each variable,leveraging historical data and GC relationships to forecast future states,thereby ensuring GC reliability.Finally,the extracted GC features are utilized for fault classification,guaranteeing feature discriminability and diagnosis accuracy.This study simulates six critical fault modes in LRE using Simulink.Based on the generated simulation data,GCMLP demonstrates superior fault localization accuracy compared to benchmark methods,validating its efficacy and robustness.
文摘Granger因果关系在时间序列建模中具有重要意义,但传统方法存在难以捕捉复杂非线性关系等诸多局限性。本文在相关工作的基础上提出GCGAN模型,首次将生成对抗网络应用于时间序列中的Granger因果关系发现。通过设计多头生成器的架构建模目标序列,在训练时对生成器施加稀疏诱导惩罚项,并在提取因果关系矩阵时引入阈值方法,GCGAN能够精准找寻高维时间序列中的复杂Granger因果关系。本研究为时间序列Granger因果关系发现提供了新的深度学习范式。Granger causality plays a significant role in time series modeling. However, traditional methods struggle with capturing complex nonlinear relationships among others limitations. Building on previous studies, this paper introduces the GCGAN model, marking the first application of Generative Adversarial Networks (GANs) to Granger causality discovery in time series. By designing a multi-head generator architecture to model target sequences, imposing sparse inducing penalties on the generator during training, and introducing a threshold method when extracting the causality matrix, GCGAN can accurately identify complex Granger causalities in high-dimensional time series. This study provides a novel deep learning paradigm for the discovery of Granger causality in time series.
