arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.09358cs.LGcs.NE
收藏

考虑漂移的在线动态学习用于非平稳多变量时间序列:应用于烧结质量预测

Drift-Aware Online Dynamic Learning for Nonstationary Multivariate Time Series: Application to Sintering Quality Prediction

National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University(东北大学工业智能与系统优化国家级前沿科学中心);De Montfort University(德蒙福特大学);Innovative Artificial Intelligence Cluster, Digital Future Institute, De Montfort University(德蒙福特大学数字未来研究所创新人工智能集群);Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University), Ministry of Education(东北大学智能工业数据解析与优化教育部重点实验室)

Yumeng Zhao, Shengxiang Yang, Xianpeng Wang

AI总结:

本文提出DA-MSDL框架,通过在线自适应机制在非平稳数据流中保持鲁棒的多输出预测性能,利用多尺度双分支卷积网络分离局部波动与长期趋势,并通过最大均值差异检测漂移,实现快速分布对齐和灾难性遗忘缓解。

摘要:

准确预测非平稳多变量时间序列仍是复杂工业系统中的关键挑战,例如铁矿石烧结。在实践中,显著的概念漂移叠加显著的标签验证延迟迅速降低了离线训练模型的性能。现有基于静态架构或被动更新策略的方法难以同时提取多尺度时空特征并克服稳定性-可塑性困境。为此,提出了一种考虑漂移的多尺度动态学习(DA-MSDL)框架,通过在线自适应机制在非平稳数据流中维持稳健的多输出预测性能。该框架采用多尺度双分支卷积网络作为主干,分离局部波动与长期趋势,从而增强对复杂动态模式的表征能力。为克服标签延迟瓶颈,DA-MSDL利用最大均值差异(MMD)进行无监督漂移检测。通过量化特征分布中的在线统计偏差,DA-MSDL在推理前主动触发模型适应。此外,开发了一种漂移严重性引导的分层微调策略。通过动态内存队列中的优先经验回放,该方法实现了快速分布对齐并有效缓解灾难性遗忘。在真实世界工业烧结数据和公开基准数据集上的长周期实验表明,DA-MSDL在严重概念漂移下始终优于代表性基线。表现出强跨领域泛化能力和预测稳定性,所提框架为非平稳环境中的质量监控提供了有效的在线动态学习范式。

英文摘要:

Accurate prediction of nonstationary multivariate time series remains a critical challenge in complex industrial systems such as iron ore sintering. In practice, pronounced concept drift compounded by significant label verification latency rapidly degrades the performance of offline-trained models. Existing methods based on static architectures or passive update strategies struggle to simultaneously extract multi-scale spatiotemporal features and overcome the stability-plasticity dilemma without immediate supervision. To address these limitations, a Drift-Aware Multi-Scale Dynamic Learning (DA-MSDL) framework is proposed to maintain robust multi-output predictive performance via online adaptive mechanisms on nonstationary data streams. The framework employs a multi-scale bi-branch convolutional network as its backbone to disentangle local fluctuations from long-term trends, thereby enhancing representational capacity for complex dynamic patterns. To circumvent the label latency bottleneck, DA-MSDL leverages Maximum Mean Discrepancy (MMD) for unsupervised drift detection. By quantifying online statistical deviations in feature distributions, DA-MSDL proactively triggers model adaptation prior to inference. Furthermore, a drift-severity-guided hierarchical fine-tuning strategy is developed. Supported by prioritized experience replay from a dynamic memory queue, this approach achieves rapid distribution alignment while effectively mitigating catastrophic forgetting. Long-horizon experiments on real-world industrial sintering data and a public benchmark dataset demonstrate that DA-MSDL consistently outperforms representative baselines under severe concept drift. Exhibiting strong cross-domain generalization and predictive stability, the proposed framework provides an effective online dynamic learning paradigm for quality monitoring in nonstationary environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑