解决多工序制造中质量预测的时滞与频段干扰问题
PAF-Net: Phase-Aligned Frequency Decoupling Network for Multi-Process Manufacturing Quality Prediction
- 通过频域能量对齐时间滞后数据，实现多工序同步
- 在4个真实数据集上比基线模型低7.06%均方误差
- 适合工业质检、智能制造领域研究者参考
多工序制造中的精准质量预测对工业效率至关重要，但受限于三大核心挑战：工序间的时间延迟交互、具有混合周期性的重叠操作，以及共享频带内的跨工序依赖。为此，我们提出PAF-Net，一种频率解耦的时间序列预测框架，包含三项关键创新：(1) 基于频域能量引导的相位相关对齐方法，用于同步时间滞后的质量序列，解决时序错位问题；(2) 结合离散余弦变换（DCT）分解与频率独立块注意力机制，捕捉单个序列内的异质运行特征；(3) 频率解耦交叉注意力模块，抑制无关频率噪声，聚焦于共享频带内的有效依赖关系。在4个真实数据集上的实验表明，PAF-Net优于10个知名基线模型，均方误差降低7.06%，平均绝对误差降低3.88%。代码已开源：https://github.com/StevenLuan904/PAF-Net-Official。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。