PAF-Net: Phase-Aligned Frequency Decoupling Network for Multi-Process Manufacturing Quality Prediction

2025-07-30

AI Summary

Quality prediction in multi-stage manufacturing faces three key challenges: temporal lag, periodic aliasing, and spectral band coupling. To address these, this paper proposes a frequency-domain decoupling framework for time-series forecasting. It introduces a novel frequency-energy-guided phase alignment mechanism to achieve cross-stage temporal synchronization, and designs independent-band attention and decoupled cross-attention modules to isolate overlapping periodic components and model stage-wise dependencies without interference—all within the Discrete Cosine Transform (DCT) domain. The method integrates DCT, frequency-energy analysis, patch-based attention, and a frequency-decoupled cross-attention network. Evaluated on four real-world industrial datasets, it consistently outperforms ten state-of-the-art baselines, achieving average reductions of 7.06% in MSE and 3.88% in MAE. Results demonstrate the effectiveness and advancement of frequency-domain decoupling for quality prediction in complex manufacturing processes.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Time-Series/Data Streams

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

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.

Problem

• Synchronizing time-lagged quality series in manufacturing
• Handling overlapping operations with mixed periodicity
• Managing inter-process dependencies in shared frequency bands

Innovation

• Phase-correlation alignment synchronizes time-lagged quality series
• Frequency independent patch attention captures operational features
• Frequency decoupled cross attention suppresses noise in shared bands