PAF-Net: Phase-Aligned Frequency Decoupling Network for Multi-Process Manufacturing Quality Prediction
This work improves industrial efficiency for manufacturing sectors by providing more accurate quality predictions, though it appears incremental as it builds on existing frequency-based methods.
The paper tackled quality prediction in multi-process manufacturing by addressing time-lagged interactions, overlapping operations, and inter-process dependencies, resulting in PAF-Net outperforming 10 baselines with 7.06% lower MSE and 3.88% lower MAE on real-world datasets.
Accurate quality prediction in multi-process manufacturing is critical for industrial efficiency but hindered by three core challenges: time-lagged process interactions, overlapping operations with mixed periodicity, and inter-process dependencies in shared frequency bands. To address these, we propose PAF-Net, a frequency decoupled time series prediction framework with three key innovations: (1) A phase-correlation alignment method guided by frequency domain energy to synchronize time-lagged quality series, resolving temporal misalignment. (2) A frequency independent patch attention mechanism paired with Discrete Cosine Transform (DCT) decomposition to capture heterogeneous operational features within individual series. (3) A frequency decoupled cross attention module that suppresses noise from irrelevant frequencies, focusing exclusively on meaningful dependencies within shared bands. Experiments on 4 real-world datasets demonstrate PAF-Net's superiority. It outperforms 10 well-acknowledged baselines by 7.06% lower MSE and 3.88% lower MAE. Our code is available at https://github.com/StevenLuan904/PAF-Net-Official.