A multi-level temporal graph network with LSTM, graph convolutions, multi-level pooling, and local-global fusion outperforms baselines on the Tennessee Eastman process for industrial fault diagnosis.
Challenges and opportunities of deep learning-based process fault detection and diagnosis: A review.Neural Computing and Applications, 35(1):211–252, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-Level Temporal Graph Networks with Local-Global Fusion for Industrial Fault Diagnosis
A multi-level temporal graph network with LSTM, graph convolutions, multi-level pooling, and local-global fusion outperforms baselines on the Tennessee Eastman process for industrial fault diagnosis.