Logo image
A Nonlinear Root Cause Diagnosis Method Based on Deep Autoregressive Granger Analysis
會議論文集

A Nonlinear Root Cause Diagnosis Method Based on Deep Autoregressive Granger Analysis

J.-G. Zhu, J.-G. Wang, S.-X. Yang, Y.-Z. Xue, R. Chen, Y. Yao 和 H.-L. Chen
Proceedings of 2026 IEEE 15th Data Driven Control and Learning Systems Conference, DDCLS 2026, 頁碼.1313-1318
2026

摘要

DeepAR Granger Causality Nonlinear Process Root Cause Diagnosis Failure analysis Fault detection Nonlinear analysis Nonlinear simulations Safety engineering Statistical tests Time series Time series analysis Uncertainty analysis Autoregressive modelling Causal relationships Deep autoregressive model Diagnosis methods Granger Causality Industrial processs Nonlinear process Root cause Root cause diagnose Times series Numerical methods
In industrial processes, fault diagnosis is a core technology for ensuring the stable operation of industrial systems. Accurate identification of causal relationships between variables is crucial for root cause localization. Conventional Granger causality analysis can only capture linear causal interactions, making them unsuitable for the complex nonlinear causal relationships in industrial processes. This paper proposes a nonlinear Granger fault root cause diagnosis method based on the Deep Autoregressive Model (DeepAR). This method combines the time series probabilistic prediction model with the Granger analysis, leveraging DeepAR to model uncertainty and to learn similar time-series trends. Experiments using numerical simulation and the Tennessee Eastman process demonstrate that the proposed method can accurately identify the fault root cause variable and detect causal relationships consistent with the mechanistic analysis. © 2026 IEEE.

檔案與連結 (1)

url
https://www.scopus.com/inward/record.uri?eid=2-s2.0-105046575551&doi=10.1109%2fDDCLS71227.2026.11610324&partnerID=40&md5=112a541da5c6592abfb927685baf82cd檢視

相關連結

指標

1 檢視次數

詳細資料

Logo image